Large language models (LLMs) can predict interpersonal attraction from conversation transcripts, but it remains unclear what a speech predictor can add beyond transcript-only LLM prediction. Using Japanese speed-dating conversations, we combine predictions from a transcript-only LLM and a supervised speech predictor to estimate participants' reported liking of their partners. We show that speech can complement transcript-only LLM prediction, but that this complementarity is conditional rather than universal. Combining the two predictions significantly improves pairwise ranking accuracy over the transcript-only LLM alone in all evaluated conditions. By contrast, gains in per-participant Pearson $r$ vary across conversation rounds and rating directions, with none significant after correction. Retrospectively, these $r$ gains are concentrated among participants for whom the speech predictor is more accurate. Speech can therefore retain predictive value even when an LLM predicts attraction from transcripts. The relevant question is not simply whether speech helps, but where its complementarity emerges.
展开完整摘要收起摘要↓
Large language models (LLMs) can predict interpersonal attraction from conversation transcripts, but it remains unclear what a speech predictor can add beyond transcript-only LLM prediction. Using Japanese speed-dating conversations, we combine predictions from a transcript-only LLM and a supervised speech predictor to estimate participants' reported liking of their partners. We show that speech can complement transcript-only LLM prediction, but that this complementarity is conditional rather than universal. Combining the two predictions significantly improves pairwise ranking accuracy over the transcript-only LLM alone in all evaluated conditions. By contrast, gains in per-participant Pearson $r$ vary across conversation rounds and rating directions, with none significant after correction. Retrospectively, these $r$ gains are concentrated among participants for whom the speech predictor is more accurate. Speech can therefore retain predictive value even when an LLM predicts attraction from transcripts. The relevant question is not simply whether speech helps, but where its complementarity emerges.
Long-context LLM training suffers from a load-balancing problem that sequence packing does not solve. Packing samples into fixed-token sequences balances memory and linear-cost operators, but the dominant attention cost scales with the sum of squared sequence lengths. Thus, equally sized packed sequences drawn from a long-tailed corpus can carry substantially different attention workloads, creating data-parallel stragglers and pipeline bubbles. Existing approaches either balance at the granularity of sequences or microbatches, where an outlier can dominate an assignment, or disaggregate attention over a global worker pool whose communication domain grows with the data-parallel (DP) degree. We present Libra, which operationalizes the law of large numbers (LLN) as a scaling principle for load balancing: the attention-balancing pool need not grow with the DP degree. Libra groups packed sequences and their CP groups into fixed-size sequence pools. As DP scales out, Libra adds pools rather than enlarging each one, bounding every attention exchange. Variance-Reduced Sequence Placement makes this effective for finite, long-tailed workloads by co-locating sequences with complementary attention workloads to reduce residual inter-pool skew. Within each pool, Tiled Attention Pooling dispatches sequence-head SH-Tiles across GPUs, while a pipelined runtime overlaps tile exchange with attention. Libra exposes a drop-in context-parallel attention operator and a pluggable data sampler, requiring no changes to model layers, optimizers, or pipeline schedules. On Qwen3-Turbo training with 256K- and 1M-token workloads, Libra improves end-to-end throughput by up to 2.54x over Ulysses, with up to 3.14x worst-step straggler-attention speedup in microbenchmarks. Libra has run for hundreds of thousands of GPU-hours in production on jobs spanning 32K to 1M tokens while preserving training semantics.
展开完整摘要收起摘要↓
Long-context LLM training suffers from a load-balancing problem that sequence packing does not solve. Packing samples into fixed-token sequences balances memory and linear-cost operators, but the dominant attention cost scales with the sum of squared sequence lengths. Thus, equally sized packed sequences drawn from a long-tailed corpus can carry substantially different attention workloads, creating data-parallel stragglers and pipeline bubbles. Existing approaches either balance at the granularity of sequences or microbatches, where an outlier can dominate an assignment, or disaggregate attention over a global worker pool whose communication domain grows with the data-parallel (DP) degree. We present Libra, which operationalizes the law of large numbers (LLN) as a scaling principle for load balancing: the attention-balancing pool need not grow with the DP degree. Libra groups packed sequences and their CP groups into fixed-size sequence pools. As DP scales out, Libra adds pools rather than enlarging each one, bounding every attention exchange. Variance-Reduced Sequence Placement makes this effective for finite, long-tailed workloads by co-locating sequences with complementary attention workloads to reduce residual inter-pool skew. Within each pool, Tiled Attention Pooling dispatches sequence-head SH-Tiles across GPUs, while a pipelined runtime overlaps tile exchange with attention. Libra exposes a drop-in context-parallel attention operator and a pluggable data sampler, requiring no changes to model layers, optimizers, or pipeline schedules. On Qwen3-Turbo training with 256K- and 1M-token workloads, Libra improves end-to-end throughput by up to 2.54x over Ulysses, with up to 3.14x worst-step straggler-attention speedup in microbenchmarks. Libra has run for hundreds of thousands of GPU-hours in production on jobs spanning 32K to 1M tokens while preserving training semantics.
Conformalized selection has been widely applied to select high-quality candidates from large datasets with rigorous uncertainty quantification, such as reliable labeling, drug discovery, and the alignment of large language models. Nevertheless, existing methods assume clean responses on calibration data, an assumption that rarely holds in practice. In this paper, we formulate the above tasks as selecting candidates with true predicted labels or with responses exceeding certain values. We demonstrate that existing conformal selection methods fail to control the false discovery rate (FDR) or suffer from severe power loss under contaminated calibration data. To that end, we propose Robust Conformalized Selection (RCS), a unified framework for selective classification with valid FDR control under general label contamination. The key insight of RCS lies in a novel statistical reduction: by separately conditioning on different classes, we translate the intractable label noise into a localized covariate shift problem, which then enables a covariate-adjusted empirical-Bayes-type estimate of the number of false selections. Statistical properties such as the asymptotic FDR control, power optimality, and robustness of RCS are established. We further develop an instantiation of RCS under randomized response model, and also apply RCS to the task of selecting candidates with large response values. Extensive experiments on both simulated and real-world datasets demonstrate the effectiveness of RCS.
展开完整摘要收起摘要↓
Conformalized selection has been widely applied to select high-quality candidates from large datasets with rigorous uncertainty quantification, such as reliable labeling, drug discovery, and the alignment of large language models. Nevertheless, existing methods assume clean responses on calibration data, an assumption that rarely holds in practice. In this paper, we formulate the above tasks as selecting candidates with true predicted labels or with responses exceeding certain values. We demonstrate that existing conformal selection methods fail to control the false discovery rate (FDR) or suffer from severe power loss under contaminated calibration data. To that end, we propose Robust Conformalized Selection (RCS), a unified framework for selective classification with valid FDR control under general label contamination. The key insight of RCS lies in a novel statistical reduction: by separately conditioning on different classes, we translate the intractable label noise into a localized covariate shift problem, which then enables a covariate-adjusted empirical-Bayes-type estimate of the number of false selections. Statistical properties such as the asymptotic FDR control, power optimality, and robustness of RCS are established. We further develop an instantiation of RCS under randomized response model, and also apply RCS to the task of selecting candidates with large response values. Extensive experiments on both simulated and real-world datasets demonstrate the effectiveness of RCS.
Computational nutrition needs precise ingredient data, but current databases are incomplete, inconsistent, and built for human reference rather than automated reasoning. LLMs could help fill these gaps, but single-pass outputs are unreliable and can introduce silent errors into downstream computation. We present a quality-controlled LLM pipeline for ingredient data acquisition that combines robust statistical estimation, domain-specific invariant checks, and a web-fetch fallback. An illustrative Heap's Law fit to 233 recipes suggests that unique-ingredient growth is sub-linear and front-loaded: the projected ratio of unique ingredients to recipes falls from 1.74 at 100 recipes to 0.19 at 5,000. For each ingredient attribute, repeated LLM queries are treated as samples from a model-induced answer distribution, and we apply robust point estimators and normalised confidence scores across numerical, Boolean, multiple-choice, open categorical, and optional integer types. An invariant guard layer enforces nutritional and logical self-consistency within each ingredient record. Minor numeric inconsistencies are reconciled via a linear program that minimises worst-case percentage deviation while preserving semantic zeros, and major violations are escalated to web-evidence-grounded repair, then human review only if that fails. On a curated 30-ingredient reference set, the pipeline achieves 98.4% exact match on nutrient flags and cuts median absolute percentage error on nutrient ratios from 31.9% for the median-aggregated baseline to 10.1%, a reduction of 21.8 percentage points, at an API cost of about $1 per ingredient. This frames LLM-assisted database construction as a controlled data-engineering workflow that makes uncertainty operational rather than discarding it.
展开完整摘要收起摘要↓
Computational nutrition needs precise ingredient data, but current databases are incomplete, inconsistent, and built for human reference rather than automated reasoning. LLMs could help fill these gaps, but single-pass outputs are unreliable and can introduce silent errors into downstream computation. We present a quality-controlled LLM pipeline for ingredient data acquisition that combines robust statistical estimation, domain-specific invariant checks, and a web-fetch fallback. An illustrative Heap's Law fit to 233 recipes suggests that unique-ingredient growth is sub-linear and front-loaded: the projected ratio of unique ingredients to recipes falls from 1.74 at 100 recipes to 0.19 at 5,000. For each ingredient attribute, repeated LLM queries are treated as samples from a model-induced answer distribution, and we apply robust point estimators and normalised confidence scores across numerical, Boolean, multiple-choice, open categorical, and optional integer types. An invariant guard layer enforces nutritional and logical self-consistency within each ingredient record. Minor numeric inconsistencies are reconciled via a linear program that minimises worst-case percentage deviation while preserving semantic zeros, and major violations are escalated to web-evidence-grounded repair, then human review only if that fails. On a curated 30-ingredient reference set, the pipeline achieves 98.4% exact match on nutrient flags and cuts median absolute percentage error on nutrient ratios from 31.9% for the median-aggregated baseline to 10.1%, a reduction of 21.8 percentage points, at an API cost of about $1 per ingredient. This frames LLM-assisted database construction as a controlled data-engineering workflow that makes uncertainty operational rather than discarding it.
Multilingual reasoning evaluation overwhelmingly relies on translating English benchmarks, a practice that introduces linguistic artifacts and fails to test culturally-grounded reasoning. We introduce ADAGE (Analogical Difficulty-by-design Assessment for Grounded Evaluation), a language-agnostic pipeline that combines native-speaker curation with LLM-assisted generation to construct challenging, translation-free benchmarks for abstract analogical reasoning. We validate ADAGE by constructing benchmarks for Arabic, Amharic, and Japanese. Evaluating 14 open-weight models, we find a consistent cultural reasoning gap: models that perform well on English proverb reasoning struggle substantially on all three native benchmarks, with accuracy dropping by 12--52 percentage points relative to English. We release the pipeline, all three benchmarks, and the full evaluation suite.
展开完整摘要收起摘要↓
Multilingual reasoning evaluation overwhelmingly relies on translating English benchmarks, a practice that introduces linguistic artifacts and fails to test culturally-grounded reasoning. We introduce ADAGE (Analogical Difficulty-by-design Assessment for Grounded Evaluation), a language-agnostic pipeline that combines native-speaker curation with LLM-assisted generation to construct challenging, translation-free benchmarks for abstract analogical reasoning. We validate ADAGE by constructing benchmarks for Arabic, Amharic, and Japanese. Evaluating 14 open-weight models, we find a consistent cultural reasoning gap: models that perform well on English proverb reasoning struggle substantially on all three native benchmarks, with accuracy dropping by 12--52 percentage points relative to English. We release the pipeline, all three benchmarks, and the full evaluation suite.
Dynamic Product Ads (DPA) require retrieving relevant items from multi-million product catalogs, balancing two competing objectives: retargeting (re-surfacing known interests) and prospecting (discovering new categories). While Large Language Models (LLMs) capture semantic intent better than traditional embedding models, deploying them at scale introduces prohibitive inference costs and lexical mismatch issues. Through controlled experiments on millions of users, we demonstrate a critical retrieval decomposition: rule-generated queries excel at retargeting on a lexical BM25 index, while LLM-generated queries excel at prospecting on a dense ANN index. Building on this, we propose SMART (SeMantic-aware Adaptive ReTrieval). To manage costs, a lightweight quality gate identifies coverage gaps in initial keyword results, adaptively routing only the ~10% of users who benefit from semantic prospecting to the LLM path. Offline evaluation demonstrates that this gated approach captures the bulk of semantic prospecting gains in Relevance Score while maintaining competitive re-targeting performance at a 90% reduction in LLM costs. Finally, in a 2-week online A/B test at Snap, SMART improved the ad conversion rate by +27.6% over a strong embedding-based baseline.
展开完整摘要收起摘要↓
Dynamic Product Ads (DPA) require retrieving relevant items from multi-million product catalogs, balancing two competing objectives: retargeting (re-surfacing known interests) and prospecting (discovering new categories). While Large Language Models (LLMs) capture semantic intent better than traditional embedding models, deploying them at scale introduces prohibitive inference costs and lexical mismatch issues. Through controlled experiments on millions of users, we demonstrate a critical retrieval decomposition: rule-generated queries excel at retargeting on a lexical BM25 index, while LLM-generated queries excel at prospecting on a dense ANN index. Building on this, we propose SMART (SeMantic-aware Adaptive ReTrieval). To manage costs, a lightweight quality gate identifies coverage gaps in initial keyword results, adaptively routing only the ~10% of users who benefit from semantic prospecting to the LLM path. Offline evaluation demonstrates that this gated approach captures the bulk of semantic prospecting gains in Relevance Score while maintaining competitive re-targeting performance at a 90% reduction in LLM costs. Finally, in a 2-week online A/B test at Snap, SMART improved the ad conversion rate by +27.6% over a strong embedding-based baseline.
Probabilistic text generators supply conditional distributions over tokens and complete verbal continuations, whereas scientific use often requires a posterior over a finite state. Large language models are the leading example: phrase probabilities depend on prompt wording, and model-printed percentages are generated text rather than state posteriors. More generally, we ask when an observable language law can support a reproducible posterior over declared states. A semantic map groups meaning-equivalent continuations; held-out cases with reference posteriors identify a semiparametric inverse from grouped language probabilities to state probabilities. The language law remains nonparametric and no hidden model quantity is used. This is principally a theory and methods paper and makes several contributions. On the theoretical side, we derive conditions for existence, identification, stable recovery, and sequential updating; concentration, asymptotic, and nonparametric rates; identified sets under truncated probabilities; and a minimax boundary for uniform stability. On the empirical side, theorem- directed simulations verify recovery rates, compatible-set coverage, and stability gates, while two frozen language-model studies illustrate held-out recovery and conformal coverage. The results specify when observable language probabilities can provide an auditable state measurement without being interpreted as internal belief.
展开完整摘要收起摘要↓
Probabilistic text generators supply conditional distributions over tokens and complete verbal continuations, whereas scientific use often requires a posterior over a finite state. Large language models are the leading example: phrase probabilities depend on prompt wording, and model-printed percentages are generated text rather than state posteriors. More generally, we ask when an observable language law can support a reproducible posterior over declared states. A semantic map groups meaning-equivalent continuations; held-out cases with reference posteriors identify a semiparametric inverse from grouped language probabilities to state probabilities. The language law remains nonparametric and no hidden model quantity is used. This is principally a theory and methods paper and makes several contributions. On the theoretical side, we derive conditions for existence, identification, stable recovery, and sequential updating; concentration, asymptotic, and nonparametric rates; identified sets under truncated probabilities; and a minimax boundary for uniform stability. On the empirical side, theorem- directed simulations verify recovery rates, compatible-set coverage, and stability gates, while two frozen language-model studies illustrate held-out recovery and conformal coverage. The results specify when observable language probabilities can provide an auditable state measurement without being interpreted as internal belief.
Large language models (LLMs) are being increasingly integrated into immersive environments and design workflows, providing application prospects in areas such as rapid scene prototyping for non-expert users and scene understanding capabilities for accessibility design. While many workflows that incorporate LLMs in immersive spaces are proposed, such systems can exhibit errors, potentially resulting in frustration, loss of user trust, and compromised user safety. This paper studies the underexplored area of LLM confabulations in immersive 3D scene editing contexts. Through an exploratory study with 24 non-expert users, we construct a taxonomy of the different types of confabulation observed in LLM-assisted immersive 3D scene editing. We report their prevalence and disruptiveness, and define the construct perception-reality gap to help understand the gap between the actual and perceived occurrence of confabulations. We highlight the observed saturation of confabulation awareness under load and conclude by discussing design implications for confabulation mitigation in future LLM-assisted systems in immersive 3D scenes.
展开完整摘要收起摘要↓
Large language models (LLMs) are being increasingly integrated into immersive environments and design workflows, providing application prospects in areas such as rapid scene prototyping for non-expert users and scene understanding capabilities for accessibility design. While many workflows that incorporate LLMs in immersive spaces are proposed, such systems can exhibit errors, potentially resulting in frustration, loss of user trust, and compromised user safety. This paper studies the underexplored area of LLM confabulations in immersive 3D scene editing contexts. Through an exploratory study with 24 non-expert users, we construct a taxonomy of the different types of confabulation observed in LLM-assisted immersive 3D scene editing. We report their prevalence and disruptiveness, and define the construct perception-reality gap to help understand the gap between the actual and perceived occurrence of confabulations. We highlight the observed saturation of confabulation awareness under load and conclude by discussing design implications for confabulation mitigation in future LLM-assisted systems in immersive 3D scenes.
Automatic feature engineering (AutoFE) for tabular learning can be naturally formulated as a program synthesis problem, where the objective is to discover predictive feature transformations from an exponentially large search space. Recent advances in large language models (LLMs) have expanded the expressiveness of AutoFE by enabling feature program generation beyond predefined operator libraries. However, existing LLM-based approaches remain fundamentally limited by stateless generation and homogeneous search: feature proposals are produced from static prompts without accumulating search experience, while single-population exploration quickly converges to dominant transformation patterns and rarely discovers complementary feature compositions across transformation families. We propose TOPOFE, a topology-aware multi-island evolutionary framework for LLM-guided feature engineering. TOPOFE combines family-specialized exploration, adaptive prompt memory, and topology-guided knowledge transfer to efficiently discover diverse and compositional feature programs. Experiments on 29 public tabular datasets demonstrate consistent improvements over state-of-the-art AutoFE methods across classification and regression tasks. Beyond predictive performance, TOPOFE discovers more diverse and transferable feature programs that generalize across multiple downstream predictors and LLM backbones.
展开完整摘要收起摘要↓
Automatic feature engineering (AutoFE) for tabular learning can be naturally formulated as a program synthesis problem, where the objective is to discover predictive feature transformations from an exponentially large search space. Recent advances in large language models (LLMs) have expanded the expressiveness of AutoFE by enabling feature program generation beyond predefined operator libraries. However, existing LLM-based approaches remain fundamentally limited by stateless generation and homogeneous search: feature proposals are produced from static prompts without accumulating search experience, while single-population exploration quickly converges to dominant transformation patterns and rarely discovers complementary feature compositions across transformation families. We propose TOPOFE, a topology-aware multi-island evolutionary framework for LLM-guided feature engineering. TOPOFE combines family-specialized exploration, adaptive prompt memory, and topology-guided knowledge transfer to efficiently discover diverse and compositional feature programs. Experiments on 29 public tabular datasets demonstrate consistent improvements over state-of-the-art AutoFE methods across classification and regression tasks. Beyond predictive performance, TOPOFE discovers more diverse and transferable feature programs that generalize across multiple downstream predictors and LLM backbones.
Contrastive decoding methods such as DoLa improve the factuality of Large Language Models (LLMs) by contrasting the output distributions of mature and premature layers. However, DoLa's dynamic layer selection relies solely on divergences in output vocabulary distributions. In this work, we propose three attention-guided strategies: Attention-JSD, Attention-Entropy-Max, and Attention-Entropy-Min, which leverage structural information carried by internal self-attention mechanisms as a signal for layer selection. Experimental results on TruthfulQA demonstrate that our strategies, particularly Attention-JSD and Attention-Entropy-Min, consistently outperform the original DoLa. We observe significant gains on multi-answer metrics (MC2 and MC3), suggesting that attention distributions can provide a more sensitive signal for resolving factual knowledge than output vocabulary distributions.
展开完整摘要收起摘要↓
Contrastive decoding methods such as DoLa improve the factuality of Large Language Models (LLMs) by contrasting the output distributions of mature and premature layers. However, DoLa's dynamic layer selection relies solely on divergences in output vocabulary distributions. In this work, we propose three attention-guided strategies: Attention-JSD, Attention-Entropy-Max, and Attention-Entropy-Min, which leverage structural information carried by internal self-attention mechanisms as a signal for layer selection. Experimental results on TruthfulQA demonstrate that our strategies, particularly Attention-JSD and Attention-Entropy-Min, consistently outperform the original DoLa. We observe significant gains on multi-answer metrics (MC2 and MC3), suggesting that attention distributions can provide a more sensitive signal for resolving factual knowledge than output vocabulary distributions.
Modeling multi-entity temporal data requires capturing dependencies across entities, time, and their interactions. Transformer-based approaches perform well but often rely on deep stacks of layers to learn these heterogeneous dependencies implicitly, increasing computational cost. We revisit this problem from a structural perspective and decompose multi-entity temporal dynamics into three interaction types: spatial interactions among entities, temporal interactions across time, and cross interactions coupling the two domains. We propose a structured spatio-temporal transformer block that explicitly models all three within a single stage. It uses parallel spatial and temporal self-attention, followed by bidirectional cross-attention, and combines the outputs through learnable gated fusion. By directly encoding these complementary views, the model reduces the need for deep stacking. We evaluate the approach on video-based group activity recognition, skeleton-based human interaction analysis, and wearable sensor-based activity recognition. Despite its simplicity, the single structured Transformer block matches or outperforms deeper architectures with only 1.76M parameters. The results suggest that depth in prior models partly compensates for implicit and entangled interaction modeling, whereas explicit factorization offers a more efficient and transparent alternative. More broadly, this work supports a structure-first design principle: expressive multi-entity temporal reasoning can emerge by exposing interaction structure rather than relying on depth.
展开完整摘要收起摘要↓
Modeling multi-entity temporal data requires capturing dependencies across entities, time, and their interactions. Transformer-based approaches perform well but often rely on deep stacks of layers to learn these heterogeneous dependencies implicitly, increasing computational cost. We revisit this problem from a structural perspective and decompose multi-entity temporal dynamics into three interaction types: spatial interactions among entities, temporal interactions across time, and cross interactions coupling the two domains. We propose a structured spatio-temporal transformer block that explicitly models all three within a single stage. It uses parallel spatial and temporal self-attention, followed by bidirectional cross-attention, and combines the outputs through learnable gated fusion. By directly encoding these complementary views, the model reduces the need for deep stacking. We evaluate the approach on video-based group activity recognition, skeleton-based human interaction analysis, and wearable sensor-based activity recognition. Despite its simplicity, the single structured Transformer block matches or outperforms deeper architectures with only 1.76M parameters. The results suggest that depth in prior models partly compensates for implicit and entangled interaction modeling, whereas explicit factorization offers a more efficient and transparent alternative. More broadly, this work supports a structure-first design principle: expressive multi-entity temporal reasoning can emerge by exposing interaction structure rather than relying on depth.
Autoregressive (AR) large language models (LLMs) are inherently inefficient at inference time because each generated token requires accessing the full set of model parameters, leading to low operational intensity and high energy consumption. Masked diffusion language models (MDLMs) partially address this limitation for memory-bound settings by allowing multiple tokens to be generated per parameter access. In order to further enhance inference efficiency on modern platforms with extensive in-chip memory, this work proposes neuromorphic MDLMs (N-MDLMs), which integrate block diffusion with spike-based neuromorphic computation to jointly improve throughput and energy efficiency. While block diffusion increases token throughput by producing multiple tokens per parameter access, spike-induced sparsity reduces effective parameter traffic and computations by skipping inactive channels. To analyze the synergistic effect of sparsity and diffusion, we develop a token-level roofline-inspired model that captures the combined impact of block-parallel generation and spike sparsity on decoding efficiency. Experimental results on translation tasks show that, thanks to spike-induced sparsity, N-MDLMs achieve substantial improvements in energy efficiency and throughput even in compute-bound platforms for which MDLMs would fail to improve over AR-LLMs.
展开完整摘要收起摘要↓
Autoregressive (AR) large language models (LLMs) are inherently inefficient at inference time because each generated token requires accessing the full set of model parameters, leading to low operational intensity and high energy consumption. Masked diffusion language models (MDLMs) partially address this limitation for memory-bound settings by allowing multiple tokens to be generated per parameter access. In order to further enhance inference efficiency on modern platforms with extensive in-chip memory, this work proposes neuromorphic MDLMs (N-MDLMs), which integrate block diffusion with spike-based neuromorphic computation to jointly improve throughput and energy efficiency. While block diffusion increases token throughput by producing multiple tokens per parameter access, spike-induced sparsity reduces effective parameter traffic and computations by skipping inactive channels. To analyze the synergistic effect of sparsity and diffusion, we develop a token-level roofline-inspired model that captures the combined impact of block-parallel generation and spike sparsity on decoding efficiency. Experimental results on translation tasks show that, thanks to spike-induced sparsity, N-MDLMs achieve substantial improvements in energy efficiency and throughput even in compute-bound platforms for which MDLMs would fail to improve over AR-LLMs.
作者Yunting Song, Matthew Watson, Peter Grabowski, Jun Qin
The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality. As datasets scale, massive preference and instruction-tuning corpora inevitably accumulate hidden structural contradictions, safety risks, and systemic human annotation errors. Standard dataset auditing methods, such as semantic deduplication or LLM-as-a-judge, struggle to capture the actual predictive impact of individual records and often miss deep functional rule clashes. To address this, we introduce a scalable, inference-only data valuation pipeline that approximates the Shapley value without iterative model retraining. By mapping semantic k-NN neighborhoods into a directed graph, our framework evaluates data utility directly through a reference LLM's probability distribution using zero-shot and one-shot conditional log-likelihood shifts. Our pipeline then translates these predictive influence scores into localized advantage metrics to isolate gradient-conflicting records. We demonstrate the pipeline's efficacy in sanitizing two heavily vetted alignment datasets. First, applying our pipeline to the HelpSteer2 dataset reduced the manual audit search space by 99.1%, successfully uncovering falsely-labeled records across diverse failure modes. Second, applying our automated audit strategy to Anthropic's HH-RLHF training and evaluation splits identified thousands of hidden safety and factual preference inversions. Crucially, by extending this audit to the evaluation split, we expose severe vulnerabilities in current benchmark integrity: highly capable models frequently predict the safer or more helpful response, only to be penalized by objectively flawed human ground-truth labels. Overall, our work provides a mathematically grounded, highly efficient diagnostic tool to uncover human label failures, sanitize evaluation benchmarks, and ensure the integrity of LLM alignment data.
展开完整摘要收起摘要↓
The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality. As datasets scale, massive preference and instruction-tuning corpora inevitably accumulate hidden structural contradictions, safety risks, and systemic human annotation errors. Standard dataset auditing methods, such as semantic deduplication or LLM-as-a-judge, struggle to capture the actual predictive impact of individual records and often miss deep functional rule clashes. To address this, we introduce a scalable, inference-only data valuation pipeline that approximates the Shapley value without iterative model retraining. By mapping semantic k-NN neighborhoods into a directed graph, our framework evaluates data utility directly through a reference LLM's probability distribution using zero-shot and one-shot conditional log-likelihood shifts. Our pipeline then translates these predictive influence scores into localized advantage metrics to isolate gradient-conflicting records. We demonstrate the pipeline's efficacy in sanitizing two heavily vetted alignment datasets. First, applying our pipeline to the HelpSteer2 dataset reduced the manual audit search space by 99.1%, successfully uncovering falsely-labeled records across diverse failure modes. Second, applying our automated audit strategy to Anthropic's HH-RLHF training and evaluation splits identified thousands of hidden safety and factual preference inversions. Crucially, by extending this audit to the evaluation split, we expose severe vulnerabilities in current benchmark integrity: highly capable models frequently predict the safer or more helpful response, only to be penalized by objectively flawed human ground-truth labels. Overall, our work provides a mathematically grounded, highly efficient diagnostic tool to uncover human label failures, sanitize evaluation benchmarks, and ensure the integrity of LLM alignment data.
作者Patrick Rim, Tom Long, Ekta Prashnani, Ruth Rosenholtz, Ben Boudaoud, Peter Xenopoulos, Alex Wong, Joohwan Kim, Jae-Hyun Jung
Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably. Existing benchmarks evaluate these models as black boxes, limiting their ability to identify the underlying causes of lower performance: when a model fails a spatial reasoning task, it remains difficult to ascertain whether the hurdle is perceptual, such as recognizing object boundaries, or cognitive, such as reasoning about occlusion to infer hidden geometry. We introduce Spatial-IQ, a hierarchical diagnostic framework that decomposes object counting in stacked 3D structures into 9 perceptual and cognitive sub-tasks organized by the developmental stages of human spatial cognition, with mental rotation as an additional target probe. Using NVIDIA Isaac Sim, we procedurally generated a diverse dataset of roughly 80,000 stacked 3D structures with per-task ground truth. We evaluate models across three output formats (free-response text, multiple-choice images, and image editing) alongside a human baseline. The Spatial-IQ framework shows that top-performing models often succeed at the target task (object counting) without succeeding on the lower-level sub-tasks intended to support it, and that models differ in how much of these hierarchical chains they preserve, often revealing shortcut behavior that raw target-task accuracy alone would obscure. Finally, we demonstrate that training models with chain-of-thought (CoT) supervision over our hierarchical sub-tasks, combined with reinforcement learning with verifiable rewards, significantly improves both spatial consistency across sub-tasks and target-task accuracy, supporting the value of the proposed decomposition as both a diagnostic tool and a training signal.
展开完整摘要收起摘要↓
Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably. Existing benchmarks evaluate these models as black boxes, limiting their ability to identify the underlying causes of lower performance: when a model fails a spatial reasoning task, it remains difficult to ascertain whether the hurdle is perceptual, such as recognizing object boundaries, or cognitive, such as reasoning about occlusion to infer hidden geometry. We introduce Spatial-IQ, a hierarchical diagnostic framework that decomposes object counting in stacked 3D structures into 9 perceptual and cognitive sub-tasks organized by the developmental stages of human spatial cognition, with mental rotation as an additional target probe. Using NVIDIA Isaac Sim, we procedurally generated a diverse dataset of roughly 80,000 stacked 3D structures with per-task ground truth. We evaluate models across three output formats (free-response text, multiple-choice images, and image editing) alongside a human baseline. The Spatial-IQ framework shows that top-performing models often succeed at the target task (object counting) without succeeding on the lower-level sub-tasks intended to support it, and that models differ in how much of these hierarchical chains they preserve, often revealing shortcut behavior that raw target-task accuracy alone would obscure. Finally, we demonstrate that training models with chain-of-thought (CoT) supervision over our hierarchical sub-tasks, combined with reinforcement learning with verifiable rewards, significantly improves both spatial consistency across sub-tasks and target-task accuracy, supporting the value of the proposed decomposition as both a diagnostic tool and a training signal.
作者Naifu Xue, Zhaoyang Jia, Haosen Li, Zihan Zheng, Jiahao Li, Bin Li, Xiaoyi Zhang, Qi Meng, Yuan Zhang, Yan Lu
Diffusion models provide strong generative capabilities for video compression at ultra-low bitrates. Existing diffusion-based video codecs adapt base models originally developed for text-conditioned generation, whereas diffusion models designed and trained specifically for compression remain unexplored. To fill this gap, we introduce our Generative Video Codec (GenVC), built on a video diffusion model trained from scratch for compression. To our knowledge, this is the first compression-oriented video diffusion model. We realize this model directly in pixel space with a global-to-local hierarchy that recovers fine spatio-temporal details, enabling high-quality generative reconstruction from compressed representations. To accelerate inference, we distill the multi-step model into one step using distribution matching distillation (DMD). Applying DMD directly, however, drives the student toward motion-stalled reconstructions. We trace this to a teacher-side guidance failure: once student-induced perturbations leave the frozen teacher's training region, its guidance can become misleading, causing DMD updates to reinforce rather than correct the student drift. To break the resulting feedback loop, we propose Adaptive Score Distillation, which gates DMD updates according to their alignment with the ground-truth direction, enabling high-quality reconstruction with coherent motion. Experimental results show that GenVC achieves state-of-the-art perceptual quality at ultra-low bitrates, with average bitrate savings of 62.5% at matched LPIPS and 71.3% at matched FID over GLVC. Unlike prior codecs that inherit billion-scale pretrained backbones, our diffusion model has only 478.0M parameters and decodes 1080p video in a single step at 15.1 fps on an A100 GPU.
展开完整摘要收起摘要↓
Diffusion models provide strong generative capabilities for video compression at ultra-low bitrates. Existing diffusion-based video codecs adapt base models originally developed for text-conditioned generation, whereas diffusion models designed and trained specifically for compression remain unexplored. To fill this gap, we introduce our Generative Video Codec (GenVC), built on a video diffusion model trained from scratch for compression. To our knowledge, this is the first compression-oriented video diffusion model. We realize this model directly in pixel space with a global-to-local hierarchy that recovers fine spatio-temporal details, enabling high-quality generative reconstruction from compressed representations. To accelerate inference, we distill the multi-step model into one step using distribution matching distillation (DMD). Applying DMD directly, however, drives the student toward motion-stalled reconstructions. We trace this to a teacher-side guidance failure: once student-induced perturbations leave the frozen teacher's training region, its guidance can become misleading, causing DMD updates to reinforce rather than correct the student drift. To break the resulting feedback loop, we propose Adaptive Score Distillation, which gates DMD updates according to their alignment with the ground-truth direction, enabling high-quality reconstruction with coherent motion. Experimental results show that GenVC achieves state-of-the-art perceptual quality at ultra-low bitrates, with average bitrate savings of 62.5% at matched LPIPS and 71.3% at matched FID over GLVC. Unlike prior codecs that inherit billion-scale pretrained backbones, our diffusion model has only 478.0M parameters and decodes 1080p video in a single step at 15.1 fps on an A100 GPU.
作者Yuancheng Xu, Mingming He, Pablo Salamanca, Li Ma, Yash Kant, Emmett Steven, Paul Debevec, Ning Yu
In visual storytelling, human performances are central to creative intent and narrative meaning. However, preserving human identity and performance while enabling flexible visual edits remains challenging for generative video models. We formalize this challenge as identity-preserving video restylization, which propagates scene, lighting, and style changes specified by an edited keyframe across a source video, while preserving facial likeness and performance, including expressions, eye gaze, and lip synchronization. A key obstacle is the absence of paired training data, as identity-preserving restylized video pairs are rare in real-world settings. To address this, we propose a decoupling of source-grounded identity preservation and edit-driven video synthesis. Our key insight is that facial appearance and expression should remain invariant, with illumination being the primary permissible variation. We therefore cast identity preservation as a video relighting problem, while modeling visual edit propagation as controlled video synthesis guided by the edited keyframe. Building on this formulation, we introduce ID-V2V, a video-to-video generative framework integrating complementary control signals: relit facial regions and facial normal maps tightly constrain facial likeness and performance, while edited keyframes and depth sequences enable flexible and temporally coherent generation. This design enables constructing training pairs from a single video, eliminating the need for scarce paired data. Extensive experiments demonstrate that ID-V2V significantly outperforms existing methods in preserving facial likeness and fine-grained facial performance, supports both single- and multi-subject scenarios, and delivers high visual quality, highlighting its potential as a human-centric tool for real-world content production. The code is available at: https://github.com/Eyeline-Labs/ID-V2V.
展开完整摘要收起摘要↓
In visual storytelling, human performances are central to creative intent and narrative meaning. However, preserving human identity and performance while enabling flexible visual edits remains challenging for generative video models. We formalize this challenge as identity-preserving video restylization, which propagates scene, lighting, and style changes specified by an edited keyframe across a source video, while preserving facial likeness and performance, including expressions, eye gaze, and lip synchronization. A key obstacle is the absence of paired training data, as identity-preserving restylized video pairs are rare in real-world settings. To address this, we propose a decoupling of source-grounded identity preservation and edit-driven video synthesis. Our key insight is that facial appearance and expression should remain invariant, with illumination being the primary permissible variation. We therefore cast identity preservation as a video relighting problem, while modeling visual edit propagation as controlled video synthesis guided by the edited keyframe. Building on this formulation, we introduce ID-V2V, a video-to-video generative framework integrating complementary control signals: relit facial regions and facial normal maps tightly constrain facial likeness and performance, while edited keyframes and depth sequences enable flexible and temporally coherent generation. This design enables constructing training pairs from a single video, eliminating the need for scarce paired data. Extensive experiments demonstrate that ID-V2V significantly outperforms existing methods in preserving facial likeness and fine-grained facial performance, supports both single- and multi-subject scenarios, and delivers high visual quality, highlighting its potential as a human-centric tool for real-world content production. The code is available at: https://github.com/Eyeline-Labs/ID-V2V.
AC optimal power flow determines the minimum-cost generation dispatch under nonlinear power balance constraints and is solved thousands of times daily in electricity market operations. Learning a direct mapping from load conditions to OPF solutions can accelerate this computation, yet with deepening renewable penetration, a single optimal dispatch is no longer sufficient. Operators require a characterization of the distribution of feasible near-optimal solutions for risk quantification, sensitivity analysis, and multi-objective trade-off assessment. Supervised neural networks provide fast point predictions but cannot capture this conditional distribution. Diffusion-based generative models can sample diverse solutions in principle, yet existing methods operating in the raw state space exhibit degraded solution quality and fail to scale beyond medium-sized systems. We identify the root cause as the conflation of two distinct tasks within a single model. Compressing the high-dimensional OPF solution manifold is one task, and learning the conditional mapping from loads to that manifold is another. This paper presents FMOPF, a framework that resolves this conflation by decoupling compression from generation through latent flow matching and by explicitly modeling load-state coupling through a Constraint-Aware Interaction Prior Network. Experiments on four IEEE test systems demonstrate that FMOPF provides the most effective Newton-Raphson warm starts, achieves the lowest tail risk among generative methods, and is the first such method to scale to systems with several hundred buses while preserving full feasibility. Ablation studies confirm that the latent generation pipeline is a necessary condition for physical feasibility and that the interaction prior functions as a late-stage tail-risk controller.
展开完整摘要收起摘要↓
AC optimal power flow determines the minimum-cost generation dispatch under nonlinear power balance constraints and is solved thousands of times daily in electricity market operations. Learning a direct mapping from load conditions to OPF solutions can accelerate this computation, yet with deepening renewable penetration, a single optimal dispatch is no longer sufficient. Operators require a characterization of the distribution of feasible near-optimal solutions for risk quantification, sensitivity analysis, and multi-objective trade-off assessment. Supervised neural networks provide fast point predictions but cannot capture this conditional distribution. Diffusion-based generative models can sample diverse solutions in principle, yet existing methods operating in the raw state space exhibit degraded solution quality and fail to scale beyond medium-sized systems. We identify the root cause as the conflation of two distinct tasks within a single model. Compressing the high-dimensional OPF solution manifold is one task, and learning the conditional mapping from loads to that manifold is another. This paper presents FMOPF, a framework that resolves this conflation by decoupling compression from generation through latent flow matching and by explicitly modeling load-state coupling through a Constraint-Aware Interaction Prior Network. Experiments on four IEEE test systems demonstrate that FMOPF provides the most effective Newton-Raphson warm starts, achieves the lowest tail risk among generative methods, and is the first such method to scale to systems with several hundred buses while preserving full feasibility. Ablation studies confirm that the latent generation pipeline is a necessary condition for physical feasibility and that the interaction prior functions as a late-stage tail-risk controller.
Given a strongly convex function $u$, equip $R^d$ with a Riemannian metric given by the Hessian $\nabla^2 u$. This is a so-called Hessian manifold. Given a probability density $μ$ one may run a Langevin diffusion intrinsic to the manifold with stationary distribution $μ$. Such (Hessian) manifold-valued Langevin diffusions are called Mirror Langevin diffusions (MLD) which have recently become popular. One of the questions we explore is whether, given $μ$, one can choose $u$ to get an exponential convergence to equilibrium for the MLD, especially if $μ$ is not strongly log-concave. Our results are based on Lyapunov function methods and give sufficient conditions for a Poincaré or a log-Sobolev inequality to hold for the MLD. These, in turn, imply exponential convergence. We also introduce a Markov chain approximation to the MLD given by a two step Gibbs sampler with stationary distribution $μ$. This Markov chain is a variant of the Sinkhorn Markov chain introduced in arXiv:2307.16421 that is conjectured to converge to a time-inhomogeneous generalization of the MLD. Under suitable assumptions, we prove that the Markov chain has a guaranteed convergence rate in $χ^2$ that is consistent with the diffusion time scale. Our proofs are based on ideas from entropic optimal transport and strong data processing inequalities.
展开完整摘要收起摘要↓
Given a strongly convex function $u$, equip $R^d$ with a Riemannian metric given by the Hessian $\nabla^2 u$. This is a so-called Hessian manifold. Given a probability density $μ$ one may run a Langevin diffusion intrinsic to the manifold with stationary distribution $μ$. Such (Hessian) manifold-valued Langevin diffusions are called Mirror Langevin diffusions (MLD) which have recently become popular. One of the questions we explore is whether, given $μ$, one can choose $u$ to get an exponential convergence to equilibrium for the MLD, especially if $μ$ is not strongly log-concave. Our results are based on Lyapunov function methods and give sufficient conditions for a Poincaré or a log-Sobolev inequality to hold for the MLD. These, in turn, imply exponential convergence. We also introduce a Markov chain approximation to the MLD given by a two step Gibbs sampler with stationary distribution $μ$. This Markov chain is a variant of the Sinkhorn Markov chain introduced in arXiv:2307.16421 that is conjectured to converge to a time-inhomogeneous generalization of the MLD. Under suitable assumptions, we prove that the Markov chain has a guaranteed convergence rate in $χ^2$ that is consistent with the diffusion time scale. Our proofs are based on ideas from entropic optimal transport and strong data processing inequalities.
作者Jian Lu, Panyu Chen, Miriam Treggiari, Robert Blessing, Danyang Zhuo, Chunhua Weng, William W. Stead, Anru R. Zhang
Objective: To characterize the kinds of internal documentation inconsistencies a general-domain large language model (LLM) can surface from real-world discharge summaries, and to identify recurring failure modes that limit reliability at scale. Materials and Methods: We applied a two-stage LLM pipeline---open-ended candidate identification (Gemini 2.5 Pro) followed by context-grounded verification (Gemini 2.5 Flash)---to 3,000 randomly sampled MIMIC-IV-Note discharge summaries. A subset of the pipeline output was then reviewed manually by clinical experts. Results: Our pipeline surfaced 3,460 candidate inconsistencies, affecting 69.7% of admissions. Representative examples spanned demographics, allergies, procedures, diagnoses, laboratory, medications, and care-planning domains, with direct implications for clinical reasoning or patient safety. Expert review also revealed recurring failure modes that arise when verification requires temporal reasoning, evolving-diagnosis context, or knowledge of outpatient-prescribing conventions the model does not natively possess. Discussion: Detection is highly context-dependent: many flagged pairs require anchoring each statement to its source section and clinical domain, then assessing whether the conflict reflects a true contradiction or missing context. We propose a graded ontology spanning strict contradiction and ambiguity, with a schema characterizing each flagged case by category, section, domain, and inconsistency axis. Conclusion: This formative study establishes a methodological foundation and conceptual framework to guide subsequent validated, large-scale EHR-inconsistency analysis.
展开完整摘要收起摘要↓
Objective: To characterize the kinds of internal documentation inconsistencies a general-domain large language model (LLM) can surface from real-world discharge summaries, and to identify recurring failure modes that limit reliability at scale. Materials and Methods: We applied a two-stage LLM pipeline---open-ended candidate identification (Gemini 2.5 Pro) followed by context-grounded verification (Gemini 2.5 Flash)---to 3,000 randomly sampled MIMIC-IV-Note discharge summaries. A subset of the pipeline output was then reviewed manually by clinical experts. Results: Our pipeline surfaced 3,460 candidate inconsistencies, affecting 69.7% of admissions. Representative examples spanned demographics, allergies, procedures, diagnoses, laboratory, medications, and care-planning domains, with direct implications for clinical reasoning or patient safety. Expert review also revealed recurring failure modes that arise when verification requires temporal reasoning, evolving-diagnosis context, or knowledge of outpatient-prescribing conventions the model does not natively possess. Discussion: Detection is highly context-dependent: many flagged pairs require anchoring each statement to its source section and clinical domain, then assessing whether the conflict reflects a true contradiction or missing context. We propose a graded ontology spanning strict contradiction and ambiguity, with a schema characterizing each flagged case by category, section, domain, and inconsistency axis. Conclusion: This formative study establishes a methodological foundation and conceptual framework to guide subsequent validated, large-scale EHR-inconsistency analysis.
作者Bin Dong, Sukhada Gholba, Brooklin Gore, Shawn Kwang, David Mitchell, Samuel Oehlert, Garrett Stewart, Brendan White, Luke Baker, Ed Balas, Britt Gathright, Chin Guok, Jon-Paul Heron, John MacAuley, Scott Richmond, Chris Robb, Chris Tracy, Kesheng Wu
The ORBIT (Operations Responses and Business Intelligence Toolkit) project was initiated to assess agentic AI for the upcoming ESnet 7 initiative and to address persistent operational pain points in the Network Operations Center (NOC) workflow. ESnet operators experience slow retrieval from siloed data sources, incidents described in lengthy and difficult-to-parse tickets, and context loss across shift handoffs. These challenges increase cognitive load and prolong incident resolution times. ORBIT therefore targets routine automation, cross-source synthesis, and actionable insights delivered directly within operators' existing tooling. ORBIT is an agentic AI system integrated into ServiceNow, ESnet's primary incident management platform. The design uses a modular, layered architecture comprising a centralized reasoning hub, tool access via MCPs for ESnet data sources, a semantic search layer, and an operator-facing chat interface. To manage the complexity and stochasticity of the AI toolchain, ORBIT follows industry best practices by structuring task logic as versioned, tested "skills" that guide the system in performing bounded responsibilities. This improves reliability and predictability compared to fully unconstrained agent behavior. Key results show that ORBIT successfully delivered all six initial tasks, and the architecture enabled rapid development of two additional tasks proposed by NOC engineers. We observed strong organic adoption of general-purpose infrastructure components, especially the chat interface and LiteLLM model gateway, including high request volumes from outside the project. Experiments with skills indicate that this approach can reduce task completion steps while eliminating observed error modes.
展开完整摘要收起摘要↓
The ORBIT (Operations Responses and Business Intelligence Toolkit) project was initiated to assess agentic AI for the upcoming ESnet 7 initiative and to address persistent operational pain points in the Network Operations Center (NOC) workflow. ESnet operators experience slow retrieval from siloed data sources, incidents described in lengthy and difficult-to-parse tickets, and context loss across shift handoffs. These challenges increase cognitive load and prolong incident resolution times. ORBIT therefore targets routine automation, cross-source synthesis, and actionable insights delivered directly within operators' existing tooling. ORBIT is an agentic AI system integrated into ServiceNow, ESnet's primary incident management platform. The design uses a modular, layered architecture comprising a centralized reasoning hub, tool access via MCPs for ESnet data sources, a semantic search layer, and an operator-facing chat interface. To manage the complexity and stochasticity of the AI toolchain, ORBIT follows industry best practices by structuring task logic as versioned, tested "skills" that guide the system in performing bounded responsibilities. This improves reliability and predictability compared to fully unconstrained agent behavior. Key results show that ORBIT successfully delivered all six initial tasks, and the architecture enabled rapid development of two additional tasks proposed by NOC engineers. We observed strong organic adoption of general-purpose infrastructure components, especially the chat interface and LiteLLM model gateway, including high request volumes from outside the project. Experiments with skills indicate that this approach can reduce task completion steps while eliminating observed error modes.
A formal model enables verifying reachability, localizing an outage, or anticipating the blast radius of a change. Yet, virtually no production network has one, since writing a model by hand demands rare expertise and is hard to keep current as the network changes frequently. At its core, network modeling is a typographical exercise: it translates network artifacts (e.g., configurations, topology, and routing state) into rules in formal logic. Translation of this kind is what large language models (LLMs) nowadays do well. Unlike free-form AI reasoning, such translation can be formally verified. Once modeling is no longer the bottleneck, trusting AI to reason over large, complex networks no longer makes sense. Our position therefore cuts against the prevailing race to put autonomous AI agents in charge end-to-end. We instead confine AI to translation and rely on a solver for reliable long-horizon reasoning, building a reusable formal model of general network behavior that can then be specialized to specific tasks, e.g., root-cause analysis (RCA). We build TypoNet that constructs and validates a symbolic model of an emulated production-scale WAN from the network's own artifacts. Our preliminary evaluation shows TypoNet helps in two ways. On its own, TypoNet answers operational questions (e.g., reachability verification and change-impact analysis) faster, more cheaply, and more reliably than an LLM. As a tool for an AI agent, TypoNet boosts fault localization at lower cost. The result makes the case for AI that builds verifiable network models and relies on a solver for reliable long-horizon reasoning.
展开完整摘要收起摘要↓
A formal model enables verifying reachability, localizing an outage, or anticipating the blast radius of a change. Yet, virtually no production network has one, since writing a model by hand demands rare expertise and is hard to keep current as the network changes frequently. At its core, network modeling is a typographical exercise: it translates network artifacts (e.g., configurations, topology, and routing state) into rules in formal logic. Translation of this kind is what large language models (LLMs) nowadays do well. Unlike free-form AI reasoning, such translation can be formally verified. Once modeling is no longer the bottleneck, trusting AI to reason over large, complex networks no longer makes sense. Our position therefore cuts against the prevailing race to put autonomous AI agents in charge end-to-end. We instead confine AI to translation and rely on a solver for reliable long-horizon reasoning, building a reusable formal model of general network behavior that can then be specialized to specific tasks, e.g., root-cause analysis (RCA). We build TypoNet that constructs and validates a symbolic model of an emulated production-scale WAN from the network's own artifacts. Our preliminary evaluation shows TypoNet helps in two ways. On its own, TypoNet answers operational questions (e.g., reachability verification and change-impact analysis) faster, more cheaply, and more reliably than an LLM. As a tool for an AI agent, TypoNet boosts fault localization at lower cost. The result makes the case for AI that builds verifiable network models and relies on a solver for reliable long-horizon reasoning.
Computer-use agents are usually improved by strengthening perception: better models for reading a screenshot and choosing where to click. Yet a screenshot is only a lossy rendering of the underlying program state, e.g., the files, application backends, and DOM that hold the task data. Different states can produce the same pixels, while code can inspect and modify that state directly. StateAct is a code-first, multi-agent harness built around this distinction. Its main agent works directly with program state by using code, while a dedicated GUI subagent handles screenshot-and-click interaction on the few subgoals that need it, just 28 of 108 tasks and 1.1% of main-agent steps. The same direct access to program state also supports verification: an independent finish gate double-checks the saved result for structural failures, e.g., output that is missing, unsaved, or written to the wrong path. To stay on track over hundreds of steps, the main agent hands subgoals to fresh subagents, keeping its own context focused. On OSWorld 2.0, StateAct lifts Claude Opus 4.8 from 20.6% to 26.9% on binary success, and from 54.8% to 61.6% on partial success, at ~ 9x lower cost per task than the same model driven by screenshots alone; a code-only variant with no GUI subagent reaches only 45.9% partial, below that screenshot-based baseline's 54.8%. In general, grounding action, verification, and memory in state, what we call state-grounding, shifts the main bottleneck from perception toward reasoning: failures depend more on what the agent thinks than on what it sees.
展开完整摘要收起摘要↓
Computer-use agents are usually improved by strengthening perception: better models for reading a screenshot and choosing where to click. Yet a screenshot is only a lossy rendering of the underlying program state, e.g., the files, application backends, and DOM that hold the task data. Different states can produce the same pixels, while code can inspect and modify that state directly. StateAct is a code-first, multi-agent harness built around this distinction. Its main agent works directly with program state by using code, while a dedicated GUI subagent handles screenshot-and-click interaction on the few subgoals that need it, just 28 of 108 tasks and 1.1% of main-agent steps. The same direct access to program state also supports verification: an independent finish gate double-checks the saved result for structural failures, e.g., output that is missing, unsaved, or written to the wrong path. To stay on track over hundreds of steps, the main agent hands subgoals to fresh subagents, keeping its own context focused. On OSWorld 2.0, StateAct lifts Claude Opus 4.8 from 20.6% to 26.9% on binary success, and from 54.8% to 61.6% on partial success, at ~ 9x lower cost per task than the same model driven by screenshots alone; a code-only variant with no GUI subagent reaches only 45.9% partial, below that screenshot-based baseline's 54.8%. In general, grounding action, verification, and memory in state, what we call state-grounding, shifts the main bottleneck from perception toward reasoning: failures depend more on what the agent thinks than on what it sees.
Tracheostomy requires precise localization of the tracheal incision site; however, conventional manual palpation is subjective and often unreliable, while ultrasound utility remains operator-dependent. This work presents a learning-based framework for hierarchical tracheal anatomy understanding, designed specifically for ultrasound-guided robotic systems. We propose a two-stage perception pipeline integrating a YOLOv8n localization backbone with a sparse, prompt-optimized SAM2 decoder to achieve high-fidelity segmentation from sparse surgical annotations. Our hybrid training strategy, bridging curated laboratory data with unconstrained sequences, ensures clinical robustness. Experimental benchmarks demonstrate that this decoupled architecture effectively balances generalization, precision, and efficiency. The YOLOv8n and SAM2 framework achieves a consistent Mean Dice Similarity Coefficient (DSC) of 0.777 across both controlled and generalized domains. This significantly outperforms U-Net baselines, which often suffer from anatomical fragmentation and performance degradation (Generalization DSC $\le$ 0.494). By constraining mask decoding to targeted, sparse regions of interest, our model achieves a throughput of 6.92 FPS, which is vital for closed-loop robotic teleoperation. This study confirms that a robust hierarchical understanding of tracheal anatomy can be derived by coupling lightweight localization with foundation-scale visual models. Our framework establishes a scalable foundation for standardized, autonomous surgical assistance, effectively navigating the variability of real-world ultrasound to enhance the safety and precision of robotic-assisted tracheostomy.
展开完整摘要收起摘要↓
Tracheostomy requires precise localization of the tracheal incision site; however, conventional manual palpation is subjective and often unreliable, while ultrasound utility remains operator-dependent. This work presents a learning-based framework for hierarchical tracheal anatomy understanding, designed specifically for ultrasound-guided robotic systems. We propose a two-stage perception pipeline integrating a YOLOv8n localization backbone with a sparse, prompt-optimized SAM2 decoder to achieve high-fidelity segmentation from sparse surgical annotations. Our hybrid training strategy, bridging curated laboratory data with unconstrained sequences, ensures clinical robustness. Experimental benchmarks demonstrate that this decoupled architecture effectively balances generalization, precision, and efficiency. The YOLOv8n and SAM2 framework achieves a consistent Mean Dice Similarity Coefficient (DSC) of 0.777 across both controlled and generalized domains. This significantly outperforms U-Net baselines, which often suffer from anatomical fragmentation and performance degradation (Generalization DSC $\le$ 0.494). By constraining mask decoding to targeted, sparse regions of interest, our model achieves a throughput of 6.92 FPS, which is vital for closed-loop robotic teleoperation. This study confirms that a robust hierarchical understanding of tracheal anatomy can be derived by coupling lightweight localization with foundation-scale visual models. Our framework establishes a scalable foundation for standardized, autonomous surgical assistance, effectively navigating the variability of real-world ultrasound to enhance the safety and precision of robotic-assisted tracheostomy.
Hybrid mechanistic/data-driven models, which combine first-principles with learned components, are increasingly used in process engineering and scientific machine learning. Common hybrid modeling designs are specified primarily through their architectures and training losses, which offers a limited basis for a shared semantic interface to compare or verify them across domains, with comparatively little attention paid to epistemic uncertainty in the mechanistic part. We bridge hybrid modeling and neuro-symbolic (NeSy) AI by reconstructing these designs as instances of NeSy interface. The resulting translation, Hybrid-to-NeSy (H2N), places mechanistic knowledge on the language side, learned modules on the belief side, and validity domains together with constraints on the logic side. For each design, H2N then yields an explicit NeSy inference functional and a logic-belief decomposition. From this decomposition we derive two metrics: structural violation rate (SVR), measuring whether the learned belief respects the mechanistic structure; and belief dispersion (BD), measuring how concentrated the learned plausibility is, serving as a hybrid model's epistemic uncertainty in its mechanistic part. We instantiate H2N on a case study of a structured hybrid model for binary classification under label noise and show that models with higher SVR and BD exhibit greater variability in held-out accuracy. Under structural distribution shift, H2N further quantifies a model's uncertainty during extrapolations, whereas test accuracy reveals the same shift only post hoc.
展开完整摘要收起摘要↓
Hybrid mechanistic/data-driven models, which combine first-principles with learned components, are increasingly used in process engineering and scientific machine learning. Common hybrid modeling designs are specified primarily through their architectures and training losses, which offers a limited basis for a shared semantic interface to compare or verify them across domains, with comparatively little attention paid to epistemic uncertainty in the mechanistic part. We bridge hybrid modeling and neuro-symbolic (NeSy) AI by reconstructing these designs as instances of NeSy interface. The resulting translation, Hybrid-to-NeSy (H2N), places mechanistic knowledge on the language side, learned modules on the belief side, and validity domains together with constraints on the logic side. For each design, H2N then yields an explicit NeSy inference functional and a logic-belief decomposition. From this decomposition we derive two metrics: structural violation rate (SVR), measuring whether the learned belief respects the mechanistic structure; and belief dispersion (BD), measuring how concentrated the learned plausibility is, serving as a hybrid model's epistemic uncertainty in its mechanistic part. We instantiate H2N on a case study of a structured hybrid model for binary classification under label noise and show that models with higher SVR and BD exhibit greater variability in held-out accuracy. Under structural distribution shift, H2N further quantifies a model's uncertainty during extrapolations, whereas test accuracy reveals the same shift only post hoc.
作者Federico Del Pup, Elisa Tentori, Manfredo Atzori
Hand gesture recognition via surface electromyography (sEMG) is fundamental to prosthetic control. In this field, deep learning approaches have become the gold standard. However, current architectures struggle to scale; model performance typically decreases as the number of hand movements increases. Performance degradation is tied to the increased statistical complexity of decoding expanded gesture sets and compounded by the limitations of state-of-the-art methods, which primarily rely on low-latency unimodal convolutional architectures. Convolutions operate locally, limiting model's ability to capture long-range sequential patterns. Unimodal setups cannot leverage complementary information from coordinated signals characterizing movement execution, such as inertial and eye-tracking data. These limitations motivate architectures that integrate local and global features across multimodal physiological sequences. To bridge this gap, this study introduces EMG-CrossFormer, an end-to-end hybrid convolutional-transformer for seamless multimodal integration. EMG-CrossFormer combines representations from an arbitrary number of unimodal encoders through cascaded cross-attention fusion layers, and decodes the fused representations using learnable gesture queries. EMG-CrossFormer was evaluated on four NinaPro datasets (DB2, DB3, DB7, and DB10) and benchmarked against six state-of-the-art models using an increasing number of modalities. Using only sEMG, EMG-CrossFormer achieved mean accuracies of 72.33%, 52.48%, 79.16%, and 73.49% on DB2, DB3, DB7, and DB10, respectively. Incorporating inertial signals improved performance to 90.66%, 80.40%, 92.79%, and 92.06%. These results show that joint local-global feature modeling improves sEMG-only decoding and that multimodal fusion substantially amplifies this benefit, underscoring the value of both design principles for complex hand gesture recognition.
展开完整摘要收起摘要↓
Hand gesture recognition via surface electromyography (sEMG) is fundamental to prosthetic control. In this field, deep learning approaches have become the gold standard. However, current architectures struggle to scale; model performance typically decreases as the number of hand movements increases. Performance degradation is tied to the increased statistical complexity of decoding expanded gesture sets and compounded by the limitations of state-of-the-art methods, which primarily rely on low-latency unimodal convolutional architectures. Convolutions operate locally, limiting model's ability to capture long-range sequential patterns. Unimodal setups cannot leverage complementary information from coordinated signals characterizing movement execution, such as inertial and eye-tracking data. These limitations motivate architectures that integrate local and global features across multimodal physiological sequences. To bridge this gap, this study introduces EMG-CrossFormer, an end-to-end hybrid convolutional-transformer for seamless multimodal integration. EMG-CrossFormer combines representations from an arbitrary number of unimodal encoders through cascaded cross-attention fusion layers, and decodes the fused representations using learnable gesture queries. EMG-CrossFormer was evaluated on four NinaPro datasets (DB2, DB3, DB7, and DB10) and benchmarked against six state-of-the-art models using an increasing number of modalities. Using only sEMG, EMG-CrossFormer achieved mean accuracies of 72.33%, 52.48%, 79.16%, and 73.49% on DB2, DB3, DB7, and DB10, respectively. Incorporating inertial signals improved performance to 90.66%, 80.40%, 92.79%, and 92.06%. These results show that joint local-global feature modeling improves sEMG-only decoding and that multimodal fusion substantially amplifies this benefit, underscoring the value of both design principles for complex hand gesture recognition.
作者Wiebren Wijnstra, Sameed Sohail, Berend-Jan van der Zwaag, Sabih Gerez, Amirreza Yousefzadeh
Embedded RISC-V processors are increasingly deployed for on-device AI inference at the edge, where energy efficiency is a primary design constraint. Instruction fetching from SRAM-based memory is a dominant source of energy consumption in these cores, accounting for over 40% of total energy in our baseline measurements. This paper presents two loop cache architectures integrated into the datapath of a RISC-V processor: a dynamic loop cache that automatically detects and caches short backward-branch loops at runtime, and a static loop cache that functions as a software-managed hot-code instruction buffer, allowing preloading of arbitrary instruction blocks during the boot sequence. Both designs are implemented in the open-source NEORV32 RISC-V processor and evaluated on a LeNet-5 convolutional neural network inference workload, synthesized on GlobalFoundries 22nm FDX+ technology at 0.5\,V and 250\,MHz. The dynamic cache reduces instruction fetches by 48.3% and total energy by 21.5%, while the static cache achieves an 83.3% fetch reduction and 35.5% total energy savings. The area overhead of both designs remains below 0.2% of the full SoC area. The complete implementation is open source.
展开完整摘要收起摘要↓
Embedded RISC-V processors are increasingly deployed for on-device AI inference at the edge, where energy efficiency is a primary design constraint. Instruction fetching from SRAM-based memory is a dominant source of energy consumption in these cores, accounting for over 40% of total energy in our baseline measurements. This paper presents two loop cache architectures integrated into the datapath of a RISC-V processor: a dynamic loop cache that automatically detects and caches short backward-branch loops at runtime, and a static loop cache that functions as a software-managed hot-code instruction buffer, allowing preloading of arbitrary instruction blocks during the boot sequence. Both designs are implemented in the open-source NEORV32 RISC-V processor and evaluated on a LeNet-5 convolutional neural network inference workload, synthesized on GlobalFoundries 22nm FDX+ technology at 0.5\,V and 250\,MHz. The dynamic cache reduces instruction fetches by 48.3% and total energy by 21.5%, while the static cache achieves an 83.3% fetch reduction and 35.5% total energy savings. The area overhead of both designs remains below 0.2% of the full SoC area. The complete implementation is open source.
Apple-Silicon SoCs share CPU, GPU, and Neural Engine over one unified memory system, raising the question of whether transformer inference can be accelerated by splitting single operators across units. Prior attempts, including our own, failed or produced precision-confounded wins. We identify the cause: MLX's lazy-graph scheduler serializes cross-stream work whenever a CPU-stream operation consumes an unmaterialized GPU result inside one evaluation graph, so a row-split matmul that runs \x{1.38} faster with materialized inputs runs \x{0.66} slower than GPU-only inside a lazy graph; an eager materialization boundary restores concurrency (\x{1.34}). \sys{} implements a per-layer, contention-aware CPU+GPU row split for transformer prefill built on this fix. Evaluated across five chips and three Apple-Silicon generations, community-replicated, the split accelerates Llama-shaped decoder-block prefill by \x{1.15}--\x{1.38}, unchanged at full 32-block depth, and reaches \x{1.18}--\x{1.25} faster time-to-first-token on a real Qwen2.5-7B checkpoint served through stock MLX-LM, with token-identical outputs and unchanged decode throughput. We characterize the boundaries equally carefully: decode cannot benefit, bound by shared bandwidth co-execution does not add; precision-matched training loses \x{0.86}--\x{0.97} on all five chips; ANE dispatch overhead excludes it at layer granularity; and a no-regression runtime gate becomes self-defeating under memory pressure, where probing an alternative mode evicts the active mode's working set. Code, raw results, and generation transcripts are released.
展开完整摘要收起摘要↓
Apple-Silicon SoCs share CPU, GPU, and Neural Engine over one unified memory system, raising the question of whether transformer inference can be accelerated by splitting single operators across units. Prior attempts, including our own, failed or produced precision-confounded wins. We identify the cause: MLX's lazy-graph scheduler serializes cross-stream work whenever a CPU-stream operation consumes an unmaterialized GPU result inside one evaluation graph, so a row-split matmul that runs \x{1.38} faster with materialized inputs runs \x{0.66} slower than GPU-only inside a lazy graph; an eager materialization boundary restores concurrency (\x{1.34}). \sys{} implements a per-layer, contention-aware CPU+GPU row split for transformer prefill built on this fix. Evaluated across five chips and three Apple-Silicon generations, community-replicated, the split accelerates Llama-shaped decoder-block prefill by \x{1.15}--\x{1.38}, unchanged at full 32-block depth, and reaches \x{1.18}--\x{1.25} faster time-to-first-token on a real Qwen2.5-7B checkpoint served through stock MLX-LM, with token-identical outputs and unchanged decode throughput. We characterize the boundaries equally carefully: decode cannot benefit, bound by shared bandwidth co-execution does not add; precision-matched training loses \x{0.86}--\x{0.97} on all five chips; ANE dispatch overhead excludes it at layer granularity; and a no-regression runtime gate becomes self-defeating under memory pressure, where probing an alternative mode evicts the active mode's working set. Code, raw results, and generation transcripts are released.
作者Mattias Westerink, Sameed Sohail, Berend-Jan van der Zwaag, Sabih Gerez, Amirreza Yousefzadeh
Event-driven neuromorphic inference exploits activation sparsity by updating neuron state only on spikes. However, weight sparsity introduces irregular gather-style updates that undermine lockstep Single Instruction Multiple Data (SIMD) execution. We call the resulting overheads in control, metadata, and memory activity the sparsity tax. This paper quantifies that tax by comparing three closely related accelerators integrated into one neuromorphic core: (i) baseline lockstep SIMD, (ii) bitmap-gated Sparse-SIMD that selectively disables lanes without compressing weights, and (iii) a Single Instruction Multiple Threads (SIMT) style design with per-PE address generation and run-length coded sparse weights. Using an RTL-to-gates flow in GF22FDX+ and activity-driven energy estimation, we evaluate event-driven neural network inference across varying post-training pruning levels. Results show that total core area changes are insignificant because SRAM dominates area, while performance and energy strongly depend on how sparsity is handled: SIMD and Sparse-SIMD exhibit near-constant throughput, Sparse-SIMD achieves limited energy savings due to bitmap and dense-storage overheads, and SIMT provides the strongest energy scaling and substantial speedups at high sparsity, albeit with sublinear gains due to metadata reads, load imbalance, and sparsity-independent phases. The hardware code for the proposed architectures and experiments is publicly accessible for research purposes.
展开完整摘要收起摘要↓
Event-driven neuromorphic inference exploits activation sparsity by updating neuron state only on spikes. However, weight sparsity introduces irregular gather-style updates that undermine lockstep Single Instruction Multiple Data (SIMD) execution. We call the resulting overheads in control, metadata, and memory activity the sparsity tax. This paper quantifies that tax by comparing three closely related accelerators integrated into one neuromorphic core: (i) baseline lockstep SIMD, (ii) bitmap-gated Sparse-SIMD that selectively disables lanes without compressing weights, and (iii) a Single Instruction Multiple Threads (SIMT) style design with per-PE address generation and run-length coded sparse weights. Using an RTL-to-gates flow in GF22FDX+ and activity-driven energy estimation, we evaluate event-driven neural network inference across varying post-training pruning levels. Results show that total core area changes are insignificant because SRAM dominates area, while performance and energy strongly depend on how sparsity is handled: SIMD and Sparse-SIMD exhibit near-constant throughput, Sparse-SIMD achieves limited energy savings due to bitmap and dense-storage overheads, and SIMT provides the strongest energy scaling and substantial speedups at high sparsity, albeit with sublinear gains due to metadata reads, load imbalance, and sparsity-independent phases. The hardware code for the proposed architectures and experiments is publicly accessible for research purposes.
作者Kazi Kamruzzaman Rabbi, Md. Zami Al Zunaed Farabe, M. Sohel Rahman
Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices by compressing high-precision floating-point weights into low-precision representations without requiring retraining. Past research has demonstrated that quantization largely preserves classification accuracy; however, whether it also preserves the model's internal reasoning remains an open question. This study presents a systematic evaluation on how static PTQ affects the interpretability / explainability of five widely used CNN architectures: VGG19, ResNet18, EfficientNet-B0, DenseNet161, and MobileNetV2 at INT8 and INT4 precision. We employ a dual interpretability framework that combines Grad-CAM for spatial attention analysis with LIME for input-level feature attribution, and systematically compare full-precision and quantized models on two binary classification datasets. Interpretability is evaluated using three complementary metrics: the Pearson correlation coefficient, structural similarity index, and top-20% IoU to capture distributional and structural variations in model explanations, supplemented by deletion/insertion faithfulness analysis. The results show that classification accuracy is not a reliable indicator of interpretability stability under reduced precision. DenseNet161 maintains strong feature consistency across both precision levels, whereas EfficientNet-B0, despite achieving competitive spatial attention and classification accuracy at INT8 precision, exhibits a substantial degradation in input-level feature attribution. These findings have direct implications for the trustworthy deployment of quantized models in applications with high interpretability requirements, demonstrating that architecture selection is as important as the quantization strategy.
展开完整摘要收起摘要↓
Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices by compressing high-precision floating-point weights into low-precision representations without requiring retraining. Past research has demonstrated that quantization largely preserves classification accuracy; however, whether it also preserves the model's internal reasoning remains an open question. This study presents a systematic evaluation on how static PTQ affects the interpretability / explainability of five widely used CNN architectures: VGG19, ResNet18, EfficientNet-B0, DenseNet161, and MobileNetV2 at INT8 and INT4 precision. We employ a dual interpretability framework that combines Grad-CAM for spatial attention analysis with LIME for input-level feature attribution, and systematically compare full-precision and quantized models on two binary classification datasets. Interpretability is evaluated using three complementary metrics: the Pearson correlation coefficient, structural similarity index, and top-20% IoU to capture distributional and structural variations in model explanations, supplemented by deletion/insertion faithfulness analysis. The results show that classification accuracy is not a reliable indicator of interpretability stability under reduced precision. DenseNet161 maintains strong feature consistency across both precision levels, whereas EfficientNet-B0, despite achieving competitive spatial attention and classification accuracy at INT8 precision, exhibits a substantial degradation in input-level feature attribution. These findings have direct implications for the trustworthy deployment of quantized models in applications with high interpretability requirements, demonstrating that architecture selection is as important as the quantization strategy.
Creating sprint backlogs requires considerable effort, as items such as epics, user stories, and tasks can be missed or inconsistently specified. We propose a multimodal approach to support backlog generation from visual app mockups, an artifact available at early project stages. We evaluate three prompting strategies on GPT-4o: a zero-shot baseline, Compositional Chain-of-Thought (CCoT) for vision-language reasoning, and a persona-driven prompt. We study seven app development projects across two countries and interview developers about the results. Overall, we observed that the baseline prompt favours recall over precision, whereas CCoT is more balanced, achieving average F1 scores of 52-66% for epics and user stories. Tasks were more challenging to generate accurately. Precision gains were most consistent when adding architectural context, particularly for backend tasks (precision gains up to 35%). Interviews with developers revealed that up to 26% of false positives were still considered useful, reflecting the creative and open-ended nature of backlog creation. To capture this, we propose a new measure called Revised Recall, which complements ground-truth evaluation with developer assessments. Our findings suggest that hybrid prompting with architectural context can assist backlog generation from early mockups, though results vary by item type and developer oversight remains necessary.
展开完整摘要收起摘要↓
Creating sprint backlogs requires considerable effort, as items such as epics, user stories, and tasks can be missed or inconsistently specified. We propose a multimodal approach to support backlog generation from visual app mockups, an artifact available at early project stages. We evaluate three prompting strategies on GPT-4o: a zero-shot baseline, Compositional Chain-of-Thought (CCoT) for vision-language reasoning, and a persona-driven prompt. We study seven app development projects across two countries and interview developers about the results. Overall, we observed that the baseline prompt favours recall over precision, whereas CCoT is more balanced, achieving average F1 scores of 52-66% for epics and user stories. Tasks were more challenging to generate accurately. Precision gains were most consistent when adding architectural context, particularly for backend tasks (precision gains up to 35%). Interviews with developers revealed that up to 26% of false positives were still considered useful, reflecting the creative and open-ended nature of backlog creation. To capture this, we propose a new measure called Revised Recall, which complements ground-truth evaluation with developer assessments. Our findings suggest that hybrid prompting with architectural context can assist backlog generation from early mockups, though results vary by item type and developer oversight remains necessary.