生成模型与LLM推理优化

Climbing hollow stairs remains a challenging problem for quadruped robots due to the high risk of leg trapping, severe depth sparsity, and high-frequency depth-sensing noise. In this paper, we propose StairMaster, a novel three-stage reinforcement learning framework for stable locomotion on such extreme discontinuous terrains. Our architecture integrates a Cross-Attention mechanism to extract structural features from noisy depth data, alongside a Spatial-aware Recurrent Unit (SRU) that maintains robust spatio-temporal memory to mitigate perception blind spots. To bridge the sim-to-real gap in depth perception, we propose a high-fidelity sim-to-real depth sensor modeling pipeline that faithfully replicates real-world sensor artifacts. Additionally, we employ a 3D waypoint-guided active perception reward for proactive sensing, alongside hollow gap kinematic and stair edge penalties to ensure precise foothold placement. We successfully deployed StairMaster on a Unitree Go2 robot, demonstrating its ability to conquer hollow stairs with an unprecedented incline of up to 55$^\circ$ through zero-shot transfer. To the best of our knowledge, this is the first RL-based policy to achieve such steep hollow stair climbing in real-world environments. Project Website: https://sivan666666.github.io/StairMaster/.

As graph neural networks (GNNs) become standard tools for critical tasks in circuit design and analysis, their security and privacy risks require careful attention. Here, we present the first comprehensive evaluation of gradient leakage attacks (GLAs) on GNNs in circuit-design and hardware-security tasks, a practical threat that has been largely overlooked. We assess state-of-the-art (SOTA) GNNs, including GraphSAGE, GCN, GIN, and GAT, trained on standard netlist benchmarks (ISCAS'85, EPFL, and TrustHub), for their fundamental vulnerability to GLAs. We find that GLAs can expose sensitive information, such as gate types and distinctive properties of hardware Trojans, which may assist adversaries in analyzing logic locking schemes or evading Trojan detection mechanisms. Our analysis shows that these risks are influenced by architectural features, with attention mechanisms (GAT) exacerbating leakage, while injective aggregation (GIN) provides comparatively stronger resilience. We further evaluate several SOTA defense techniques, including differential privacy, gradient clipping, secure aggregation, model compression with quantization, and adversarial training. We find that these techniques improve resilience only in specific settings and can also compromise model performance. Overall, our work provides key insights toward privacy-preserving GNNs and highlights the need for more robust and efficient defenses. We release our full methodology and artifacts.

Large-scale neural-network training repeatedly aggregates gradients across devices, making communication a central cost in distributed learning. Low-bit gradient aggregation can reduce this cost, but applying it as a static replacement for full-precision communication can destabilize training because safe precision depends on training phase, model structure, runtime bucketization, and the communication substrate. This paper presents NEURON-Fabric, a profile-guided runtime system for controlled low-bit gradient communication. NEURON-Fabric uses calibrated operating profiles, model-aware runtime bindings, online training-health monitoring, and reducer-capacity checks to decide when low-bit aggregation should be admitted, when execution should fall back to FP32, and which model regions are eligible for each route. The runtime preserves model semantics inside mixed DDP buckets and treats reducer admission as an architecture-runtime co-design problem rather than as a standalone compression operator. Across vision, Transformer, and autoregressive language-model workloads, NEURON-Fabric validates the path from calibration to distributed communication-hook execution. Static low-bit communication can collapse training accuracy, while profile-guided control preserves accuracy near full-precision references or calibrated targets and reduces modeled gradient-communication traffic in the evaluated settings. Transformer and billion-parameter language-model checks show that the same routing and fallback mechanisms execute across model families and multi-node deployments. Reducer-side replay and reducer-path measurements identify when compact sign-count aggregation is expected to reduce communication cost and when endpoint capacity should trigger fallback.

Large language model (LLM) inference is increasingly dominated by data movement across the memory hierarchy. Recent 3D-stacked cache technologies have enabled GB-scale last-level caches in modern server CPUs, making it possible to keep reusable model weights on chip and exploit cache bandwidth and latency. Achieving this regime is not straightforward: deeper pipelining for weight residency increases in-flight requests and KV-cache footprint, while cache-resident operators make operator-boundary synchronization a visible bottleneck. We present a cache-resident execution model for inference on hierarchical-memory clustered systems. The model separates weight-centric operators from attention and KV-cache management into dedicated resource domains, keeping reusable weights cache-resident while scaling KV capacity independently of pipeline depth. It also relaxes synchronization from operator boundaries to true sub-operator dependencies, reducing coordination overhead in the cache-resident regime. We instantiate this model on a multi-socket CPU cluster with a weight-attention decoupled architecture, locality-aware placement, and a specialized static runtime. The prototype substantially outperforms equally provisioned llama.cpp. On deployed Llama-3.2-3B and Llama-2-7B configurations, it achieves 2.04x-11.51x speedup on time-per-output-token (TPOT). Under a validated analytical model, it further reaches up to 13.9x TPOT speedup across model sizes, context lengths, and batch sizes. These results show that commodity CPUs with GB-scale last-level caches can support efficient LLM inference when execution is organized around cache residency, decoupled state management, and dependency-aware coordination.

We present HiReLC, a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural networks. The framework decomposes the compression search across two levels of abstraction: low-level agents (LLAs) operate independently per block, selecting per-kernel configurations over a multi-discrete action space spanning bitwidth, pruning keep-ratio, quantization type, and granularity, while high-level agents (HLAs) coordinate global budget allocation via ensemble voting guided by Fisher Information-based sensitivity estimates. To mitigate the computational cost of policy evaluation, an iterative active learning loop interleaves surrogate-guided RL optimization with post-compression fine-tuning, using a lightweight MLP surrogate to amortize expensive evaluations and a logit-MSE proxy during cold-start. The surrogate is used for reward shaping rather than as a replacement for final post-compression evaluation. The controller is architecture-agnostic by design, with a modular layer abstraction decoupling the RL environment from the underlying network topology. Experiments across Vision Transformer and CNN benchmarks demonstrate effective parameter-storage compression ratios of 5.99 - 6.72$\times$ with a 3.83 % gain in one setting and 0.55 - 5.62 % accuracy drops elsewhere, supporting hierarchical policy decomposition and sensitivity-aware guidance as practical design choices for joint neural network compression.

Inference efficiency is typically pursued by shrinking the model: distillation, pruning, quantization, and sparse routing each lower per-token cost while treating token count as fixed. But output length has been inflating, and it is precisely the component the standard toolkit leaves untouched. Here, we argue that brevity is the missing inference-efficiency lever, and that pretraining data curation is a practical way to pull it: a model trained on concise, correct data learns to answer in fewer tokens; i.e. it has a lower Cost-of-Pass. We apply our VLM curation pipeline to the MAmmoTH-VL single-image subset, and compare models trained on our curated data, the standard MAmmoTH-VL data, and external open-weight frontier VLMs. On a controlled 20-evaluation set and 14 VLMs at 1B-4B activated parameters, we hold output length fixed with a per-model regression, separating brevity from quality, and price models in FLOPs per correct answer. Curation buys a 35x Cost-of-Pass advantage over the most verbose 4B comparator (Qwen3.5-4B) within $\sim$1 pp of accuracy (0.41 vs 14.58 TFLOPs per correct answer; 0.691 vs 0.704 mean accuracy). Curation also buys a +17.55-percentage-point matched-length accuracy gain over the uncurated baseline that grows with model scale (from +16.7 pp at 1B to +21.2 pp at 4B). This brevity improvement concedes no quality: generic verbosity buys no accuracy at any capability or scale, and the window where reasoning-structured verbosity still earns its tokens shrinks from 4 of 8 capability groups at 2B to 1 of 8 at 4B. Per example, the concise model even reaches correct answers the verbose reasoning model misses, marking reasoning as a distinct curation target rather than something brevity gives up. Inference efficiency in this regime is a tokens-per-correct problem, and brevity is the lever that targets it directly.

Quantization is widely used to reduce the inference cost of large language models, but its effect on reasoning models is not fully captured by final-answer accuracy or per-token latency. We show that low-bit post-training quantization can introduce a hidden test-time compute cost: quantized reasoning models often generate longer chains of thought even when they still answer correctly. Across mathematical reasoning, code generation, scientific question answering, and agentic tool-use benchmarks, we find that INT4/INT3 quantization can preserve accuracy but increase reasoning-token usage, offsetting the expected per-token speedup. To measure this effect, we introduce the CoT Token Inflation Ratio, which compares reasoning length between quantized and full-precision models averaged across all evaluation benchmarks. We further show that token inflation is accompanied by behavioral changes in the reasoning trace, including more intermediate steps and greater semantic repetition. These changes translate into measurable end-to-end real-world serving penalties. Finally, we evaluate mitigation strategies and find that prompting and decoding-time sampling offer inconsistent accuracy-length trade-offs, while quantization-aware training shows more promise in reducing both accuracy degradation and token inflation. Our results suggest that reasoning-token usage should be reported alongside accuracy when evaluating quantized reasoning models.

Currently, streaming video understanding is still a daunting task for existing multimodal large language models (MLLMs). Its difficulties not only lie in handling the ever-increasing video frames, but also in the unpredictability of future video content and input instructions. In this paper, we study this task from the perspective of constructing a dynamic but fixed-budget memory bank, and propose a novel and training-free approach termed CausalMem. CausalMem is dedicated to constructing a dynamic visual memory update mechanism, thereby maximizing the amount of information in streaming video within a limited memory space, much like the human brain. In practice, CausalMem estimates the redundancy of visual tokens and updates the memory bank via an online semantic basis, which models the principal semantics of the observed video stream. To validate CausalMem, we apply it to two representative MLLMs, namely LLaVA-OneVision and Qwen2.5-VL respectively, and conduct extensive experiments on both streaming and offline video understanding benchmarks. The experimental results not only show the great advantages than existing methods under both streaming and offline settings, e.g., $+3.2%$ and $+3.0%$ average accuracy gains respectively, but also witness the superior semantic preservation for streaming videos, e.g., using 12$k$ token budgets to memorize hour-long streaming videos, which achieves more than 20$\times$ visual token compression ratio and only occupies about 82 MB storage. Our code is given in \href{https://github.com/hktk07/CausalMem}{CausalMem}.

On Apple Silicon the fp32 GEMMs dominating LLM prefill are dispatched by Accelerate to a matrix coprocessor (AMX) on the M1-M3. We ask where a hand-written kernel's throughput over Accelerate comes from on the M1 AMX, and reach a structural conclusion: not a faster inner loop. By microbenchmark the inner loop is load-issue bound — once any operand load interleaves with the FMA32 stream, single-thread throughput falls to a 610-to-680 GFLOPS band, under half the load-free rate. The gain comes from two deployment-level levers Accelerate underuses: fine multi-thread panels filling the M1's second on-chip AMX block (winning the K >= N shapes), and pre-packing the constant weight at load (winning the N > K shapes). A bit-exact direct-AMX kernel using both is the fastest bit-exact fp32 GEMM path we find on the M1: it exceeds all three Accelerate fp32 paths (cblas_sgemm, BNNSMatMul, and the BNNS Graph compiler) at all twelve LLM prefill GEMMs at S = 128 (GPT-2 to Llama-7B scale), leading the fastest, BNNS Graph, by 1.17 — and by 1.09 at the three shapes where it too holds fp32 — with geometric means of 1.58 over BNNSMatMul and about 2.0x over cblas_sgemm. Every output is bit-identical to Accelerate, whereas BNNS Graph is bit-exact at only three of twelve shapes, the rest at reduced precision (error up to 1.4e-3). Dropped into llama.cpp for its cblas_sgemm prefill matmuls, it raises measured full-forward throughput from 291 to 420 tokens/s (1.44x, bit-identical) at 128-token prefill — end-to-end, not a GEMM-only ratio. The contribution is this shape-resolved M1-AMX characterization (microbenchmark, two-block aggregate, per-core occupancy probe), leaving fine-panel scheduling and pre-packing as the only two levers above an inner loop at the hardware limit; mis-tuning the single column-panel width costs nearly 2x.

LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding inference, while high-dimensional full-precision embeddings impose substantial storage and bandwidth overhead on large-scale indexes. In this paper, we present BITEMBED, an extreme low-bit framework for LLM-based text embedding that jointly targets encoding efficiency and vector storage. BITEMBED converts pretrained LLM backbones into BitNet-style embedding encoders with ternary weights, quantized activations, and lightweight normalization refinement. The converted model is adapted to representation learning through continual contrastive pre-training, followed by supervised contrastive fine-tuning with both similarity-distribution distillation and attention-relation distillation from a full-precision teacher. Beyond quantizing the backbone, BITEMBED further trains output embeddings to support multiple storage precisions meeting different storage needs in various scenarios. Experiments on MMTEB (eng, v2) with Qwen3-0.6B and Gemma3-270M show that BITEMBED is largely comparable to full precision teacher embedders. Moreover, BITEMBED flexibly obtains text embeddings of various precisions, achieving a trade-off between performance and storage cost.

Lifelong continual learning remains an obstacle on the path to human-like intelligence. Modern transformers show sparks of intelligence with in-context learning. The quadratic nature of attention, however, prohibits transformers from performing this process on arbitrarily long sequences. In this work, we argue that extending in-context learning to lifelong settings is a practical solution for continual learning in AI agents. In particular, we argue that parametric forms of attention are needed to understand a lifetime of context with transformers on a fixed hardware budget. These attention mechanisms learn the relationship between keys and their associated values at test-time with parametric regression. Our generalization of parametric approaches (linear attention, state-space models, fast weight programmers, and test-time training layers) contrasts with nonparametric counterparts like softmax attention. They replace the ever-growing key-value cache with an online-trainable neural network, maintaining a constant memory footprint. We highlight how parametric attention currently fall short of lifelong learning due to limited memory capacity or costly online updates. To address these issues, we pose a set of open questions with novel insights to guide the field toward long-horizon agents.

Large language models (LLMs) can improve autonomous driving planning but are costly to query online, and existing fast-slow planners often rely on hand-designed triggering rules that either over-call the slow system or call it at the wrong times. We formulate slow-system invocation as a resource-aware sequential decision problem and propose the Adaptive Slow-System Control Gate (ASSCG), which makes frame-level Query/Cache/Drop decisions to refresh, reuse, or suppress slow guidance. ASSCG uses an RWKV backbone for efficient long-horizon gating and is trained with supervised fine-tuning followed by GRPO-style compute-aware reinforcement fine-tuning. We apply ASSCG to two different fast-slow architectures: (i) AsyncDriver on nuPlan Hard20 closed-loop evaluation, where ASSCG improves score to 67.28 (+2.28) while reducing average end-to-end inference latency by 60%; and (ii) a RecogDrive-based dual system that we build by replacing its original VLM-2B module with a lightweight ViT-based fast planner and adding an LLM slow planner, evaluated on NAVSIM, where ASSCG achieves 91.4 PDMS (+0.6) and increases average speed by 25%. The project page, including video visualizations and additional results, is available at https://williamxuanyu.github.io/asscg/.

More than a billion people communicate in Indic languages, yet the natural language processing infrastructure serving them remains fragmented and underdeveloped. The cause is structural: the field organizes its tools and benchmarks around individual languages or small subsets of genealogical language families, building separate analyzers, parsers, and datasets for each language and starting over for the next. This overlooks a deep regularity. Through more than two millennia of convergence around Sanskrit, Indic languages came to share a morphosyntactic architecture formalized in Pānini's grammar, the Astādhyāyī. This cuts across genealogical lines, uniting languages through a common framework. We argue that this Pāninian framework supplies a unifying computational architecture the field has lacked, and that benchmarks grounded explicitly in it would make Indic language systems more accurate, more data-efficient, and more transferable, effectively merging many apparently disparate and sparse Indic language resources into a single high-resource metalanguage bedrock. We propose a four-part benchmark suite to render this shared architecture explicit, measurable, and ready to be leveraged for practical applications. Moreover, we underscore the question it raises for interpretability research: whether neural models trained on these languages come to represent Pānini's categories on their own.

On-device fault detection enables real-time diagnostics without cloud dependency, but deploying machine learning models on resource-constrained hardware demands careful tradeoffs between accuracy, latency, and model size. We present a benchmark comparing traditional ML methods (Random Forest, XGBoost, SVM, Logistic Regression) against lightweight transformer architectures (DistilBERT, TinyBERT-6L, TinyBERT-4L, MobileBERT) for binary fault detection across three public datasets: NASA C-MAPSS turbofan degradation, SECOM semiconductor manufacturing, and UCI AI4I 2020 predictive maintenance. We evaluate classification performance (F1-score, AUC), model size, and CPU inference latency, and further assess INT8 dynamic quantization and a two-stage adaptive inference pipeline. Our results reveal that on well-separated sensor data (C-MAPSS), lightweight transformers match traditional ML at 87.8% F1 but at 100x the model size and 9000x the latency. TinyBERT-4L emerges as the most deployment-friendly transformer at 55 MB and 18 ms CPU latency. INT8 quantization reduces size by 25% while preserving 86.9% F1. Our adaptive pipeline, routing 97.9% of predictions through a quantized triage model and only 2.1% to a larger expert, achieves 87.6% F1 at 19.5 ms average latency. On severely imbalanced datasets (SECOM, UCI-PM), both traditional and transformer methods struggle significantly, highlighting fundamental limitations of current approaches for extreme class imbalance in fault detection. All code is publicly available.

In many decision-making scenarios, acquiring information incurs different costs. We consider the problem of constructing a deterministic evaluation strategy that minimizes the expected cost of evaluating a propositional formula under variable costs and a probability distribution over truth assignments. We present a branch-and-bound algorithm with variable-selection heuristics, pruning, and caching. To the best of our knowledge, it is the first practical exact algorithm for this level of generality. Experiments on random instances demonstrate scalability and quantify the efficiency-quality trade-off of a greedy beam-search variant. We additionally evaluate a structured heart-disease diagnosis instance. Finally, we prove that the problem is $\#P$-hard and contained in $\mathrm{PSPACE}$.

3D Gaussian Splatting (3DGS) has garnered significant attention in Simultaneous Localization and Mapping (SLAM) due to its advances in capturing fine-grained geometry features and synthesizing novel views. For SLAM in large-scale scenes, such as autonomous driving, 3DGS-SLAM faces a critical limitation: memory consumption increases continuously over time as Gaussian points accumulate, leading to poor memory efficiency and limiting its applicability. In this work, we propose a rendering-area-aware pruning strategy that selectively removes Gaussians based on their contribution to the effective rendering area, rather than solely relying on Gaussian-level heuristics such as opacity or gradient magnitude. This perspective directly targets the sources of memory redundancy, effectively reducing the peak memory footprint of 3DGS-SLAM during runtime. Evaluations on the EuRoC and KITTI datasets demonstrate that our method consistently outperforms existing pruning approaches in large-scale outdoor scenes, achieving over 60% memory reduction and more than 2 times FPS improvement while preserving localization and mapping accuracy. These results highlight rendering-area-aware pruning as a promising direction for scaling 3DGS-SLAM to real-world autonomous driving scenarios. Our code is publicly available at https://github.com/UMN-ZhaoLab/Pocket-SLAM.git.

Neural network quantization aims to find a discrete representation of parameters that preserves the performance of a full-precision (FP) model as faithfully as possible. Enforcing discrete constraints perturbs parameters away from a well-optimized minimum, generally resulting in performance degradation. Recent studies indicate that low-loss FP solutions are not isolated, but instead belong to connected low-loss subspaces of the loss landscape, where the loss maintains nearly the same minimum value. Models sampled from these subspaces are diverse and retain high accuracy. This raises the question: can a quantized model be constructed to lie within a low-loss subspace of the FP model, thereby automatically preserving performance? We address this question by learning quantization-aware linear paths in weight space optimized to minimize loss. We demonstrate that the midpoint of the resulting subspace is, by design, quantization-friendly and that its direct quantization yields performance comparable to that of quantization-aware training. The proposed procedure offers a novel perspective on weight quantization and, in contrast to conventional methods, neither relies on the straight-through estimator nor involves explicit discretization during training.

General-purpose robots operating in partially observable environments, such as homes, require memory to support autonomy. They must recall diverse information from the past, such as where objects were placed, which tasks a human partner has completed, and when an appliance was turned on. Achieving this versatility requires a general memory retrieval mechanism. Transformer architectures that use attention over long contexts for memory retrieval provide a promising approach, as they learn retrieval from data rather than relying on task-specific or hand-designed rules. However, directly incorporating them into imitation learning from offline data introduces two key challenges: (1) the policy may learn spurious correlations between past information and predicted actions, and (2) errors accumulate in memory due to prediction inaccuracies and their compounding interactions with the environment, causing model drift and cascading failures. To address both challenges, we introduce HALO, a visuomotor policy with an attention-based memory retrieval mechanism for long-horizon control. First, to suppress spurious correlations, HALO distills vision-language model (VLM) priors into the policy. It generates memory-dependent question--answer pairs from demonstration trajectories and trains jointly with a video question--answering objective, steering retrieval toward task-relevant information. Second, to reduce the impact of accumulated errors in memory during closed-loop control, HALO uses sparse attention that restricts retrieval to only the most relevant parts of the history. Together, these components enable more reliable long-horizon control by guiding the policy to retrieve task-relevant information from up to eight minutes of past experience. Project website: https://robin-lab.cs.utexas.edu/HALO

Speculative decoding (SD) accelerates LLM inference by $1.5$-$3$ times when the draft and target models are co-located. This has motivated a distributed variant (DSD) that places the draft model on an edge device while the target stays in the cloud. We show with closed-form inequalities that DSD's per-request latency benefit is limited under WAN edge-cloud communication. If the server can host both models, co-located SD has lower latency and communication than synchronous DSD, with the same per-output FLOPs and model-weight memory. Pipelining can make DSD competitive with co-located SD only in low-RTT regimes where the round trip is shorter than the edge drafting time window; at WAN RTTs, the cloud round trip remains too large for pipelined DSD to beat co-located SD. Against cloud autoregressive decoding, DSD can reduce latency only inside a bounded window given the target-model speed, acceptance rate, and RTT. DSD is also infeasible against closed-source APIs without a verifier-only interface. The main case for DSD appears in multi-tenant capacity. Under cross-client overlap, offloading draft compute lets a saturated cloud server sustain $(1 + γ\,t_d/t_v)$ times more concurrent clients at the same per-client rate, where $γ$ is the speculation length and $t_d, t_v$ are the per-step draft and verification times. DSD should therefore be evaluated primarily by multi-tenant capacity and server throughput, not only by single-request latency.

While speculative decoding improves inference throughput for multi-batch long-context Large Language Models (LLMs), its efficiency is often limited by a verification bottleneck where Key-Value (KV) cache loading dominates latency. Existing compression methods fail in this regime: static eviction incurs accuracy loss due to saliency shift, while dynamic selection introduces prohibitive computational overhead during the verification path. We propose Dustin, a sparse verification framework designed for long-context speculative decoding. Dustin integrates lookahead signals from the draft model with historical attention from the target model to identify critical tokens with high fidelity across multi-step verification windows. To reduce recomputation latency, this approach further employs a sparse estimation scheme that restricts importance scoring to a minimal subset of attention heads. Evaluations on PG-19 and LongBench with Qwen2.5-72B demonstrate that Dustin achieves a 27.85x speedup in self-attention and a 9.17x end-to-end decoding speedup at a 32k sequence length, all with negligible accuracy degradation.

Speculative decoding accelerates inference by letting a draft model propose tokens for a target model to verify, raising a concrete safety question: at temperature zero, can draft-side behavior leak into safety-scored outputs? We answer with Typical-Acceptance Invariance Screen (TAIS), a behavioral-equivalence screen that pairs target-only and speculative outputs on the same safety battery and requires byte-identity evidence, TOST equivalence at +/-3pp, and per-task Cohen's h below a calibrated null cutoff of |h| < 0.1. Applied to a 16,783-sample confirmatory core plus 44,066 matched expansion samples (fp16/bf16 execution, canonical and DPO-adversarial drafts, GPTQ-4bit drafts, two seeds, and four safety benchmarks), the tested temperature-zero vLLM stacks show no detectable safety divergence under TAIS. The largest absolute Cohen's h on matched target-only versus speculative refusal is 0.024, roughly an order of magnitude below the conventional trivial-effect floor; 25 of 27 per-task TOST contrasts pass at the +/-3pp margin (the two non-pass contrasts are capability-domain Wald-CI edge cases at identical ceiling rates, not genuine non-equivalence); the DPO-adversarial draft produces byte-identical output to the canonical draft across 4,006 samples; and bf16 changes 36%-53% of output bytes without moving any per-task safety rate outside equivalence. A separate 4,006-sample 70B production-scale probe, which lacks a matched 70B target-only arm and is therefore not counted as a TAIS pass, produces AdvBench refusal 0.839 over 700 AdvBench completions with 95% Wilson CI [0.809, 0.864]. We make no claim about sampling temperatures, untested frameworks, untested model families, or tree-speculation variants such as EAGLE and Medusa.

Traffic accident reconstruction is a forensic inverse problem that requires recovering physically consistent motion from sparse and heterogeneous evidence. Existing learning-based approaches predominantly optimize for semantic plausibility or visual realism, rather than quantitative agreement with measurable geometry and dynamics. Here, we present TRACER, a training-free framework that formulates reconstruction as a closed-loop structured inference process. Instead of directly generating dense trajectories, our framework constructs and iteratively refines event-anchored motion hypotheses under geometric, kinematic, and interaction constraints, guided by structured case memory and consistency-driven diagnosis. This design enables incremental, interpretable corrections when evidence is insufficient, making the accident reconstruction process more aligned with the workflow of human experts. Experiments on real-world accident data show that TRACER achieves improved geometric fidelity, velocity consistency, and collision accuracy over both data-driven and physics-based baselines.

Sparse Mixture-of-Experts (MoE) models route each token to a few of many experts, inviting the hypothesis that experts form functional modules tied to capabilities or languages. We test this causally on Command A+, a frontier open-weights MoE (218B total / 25B active; 128 experts, 8 active, +1 shared). We build a routing-mass atlas, pre-register six family-to-axis hypotheses before any intervention, and ablate each family at inference time against a size-matched random-expert null, measuring whether it selectively breaks its own axis (worst off-target effect at most one third of on-target). Crucially, we test the same families under four metrics and a held-out, independent-corpus run with bootstrap confidence intervals. Our finding is cautionary: robust functional modularity is rare and measurement-dependent. Of six pre-registered families, only one, the Arabic-language family, is a clean selective module that survives an independent corpus and a conservative statistical bar (1/6; a more permissive pre-registered point rule admits 3/6, but that count is threshold-sensitive). Every other family has a real causal effect yet fails selectivity, and its apparent modularity flips with the measurement: with the corpus, the metric, and the statistical bar. A positive control on Qwen3-30B-A3B recovers its published disjoint structure, confirming the method detects modularity when present. The verdict reproduces on the un-quantized BF16 model, ruling out a 4-bit quantization artifact. We conclude that ablation-based modularity verdicts are not safe unless the corpus, metric, and statistical bar are controlled. We release the atlas and ablation data.

The accelerated digitalization of renewable energy smart grids through IoT sensors, AMI, and SCADA systems has significantly expanded the attack surface for sophisticated cyberattacks, FDI attacks that stealthily distort state estimation and DoS/DDoS attacks that flood communication channels. Current IDS, however, exhibit three inherent limitations: inadequate modeling of the temporal progression of multi-step attacks, degraded scalability under extremely skewed class distributions of standard benchmark datasets, and restricted generalization across heterogeneous network environments. In this study, we present a Hybrid CNN-LSTM IDS that jointly exploits CNN-based spatial feature extraction and LSTM-based temporal sequence modeling, enabling the detection of instantaneous volumetric anomalies and gradually evolving low and slow-attack campaigns in real time. The model was trained using a seven-step preprocessing workflow comprising missing-value imputation, min-max normalization, one-hot encoding, SMOTE class balancing, mutual-information feature selection, causal temporal sequence construction (T=10), and stratified partitioning. LSTM (96.1%), Random Forest (93.5%), SVM (91.2%) and KNN (89.7%); in NSL-KDD, it reaches 98.2% precision versus 96.4% (LSTM), 95.2% (CNN), 92.7% (Random Forest) and 90.8% (SVM), with margins of 2-9 percentage points in all measures. An ablation analysis identified SMOTE balancing as the most influential design choice (-3.7~pp F1 without it). The model achieves a real-time inference throughput of 27,800 flows/s on GPU and 0.082 ms/sample CPU latency in FP32,, with INT8 quantization providing an additional 3.1 x speedup at 0.3% accuracy loss, confirming deployment feasibility on resource-constrained IEDs with <128MB memory and establishing a deployable deep-learning framework for securing next-generation renewable energy smart grid infrastructure.

Most vision-language-action (VLA) models are reactive: they predict the next action from the current instruction and observation, implicitly assuming that the current observation fully specifies the action-relevant state. In embodied control, however, embodiment-specific factors such as camera-to-robot geometry, robot calibration, or systematic actuation bias are often hard to identify from a single observation. As a result, reactive policies cannot reliably disambiguate these factors in general, overfitting to training environments and generalizing poorly at deployment. We propose Reflective VLA, which conditions each decision on a context of observation-action-consequence triplets. Each triplet records not only what the robot observed and executed, but also how the scene changed afterward, exposing the deployment-specific mapping from actions to observed effects. Architecturally, Reflective VLA routes all observation modalities through the VLM under shared attention, so the action expert reasons directly over past triplets and the current observation. A block-causal mask enables parallel multi-frame training without leakage and supports KV-cached real-time inference. On standard LIBERO and SimplerEnv-Bridge, Reflective VLA preserves strong in-distribution performance. Under distribution shift on LIBERO-Plus and the harder LIBERO-Plus-Hard, it improves average success rate by 5.4 and 4.2 percentage points over a matched reactive baseline. Ablations with a matched history-only baseline further show that action consequences — rather than additional context length alone — are the key to cross-environment generalization. Project page: https://lianqing11.github.io/reflective-vla-page/

Serving diffusion models for image-to-video generation is computationally expensive, posing significant challenges for large-scale deployment. Real I2V workloads often contain similar requests, such as repeated effect templates, related subjects, and recurring shot layouts. Existing cross-request acceleration methods mainly exploit this redundancy through feature reuse. We observe that similar I2V requests also share highly consistent sparse attention patterns, enabling historical sparse masks to serve as request-conditioned priors with almost no online mask-prediction overhead. We propose a cross-request reuse framework centered on sparsity reuse, with feature reuse as an optional extension safeguarded by a lightweight guidance enhancement. Our sparsity reuse is implemented as shared sparse mask reuse, which reuses high-quality sparse masks from similar historical requests to avoid per-request online mask prediction. Optional feature reuse applies downsampled computation to highly redundant spatiotemporal regions, mitigating boundary artifacts while preserving efficiency gains. Guidance enhancement reinforces image/text conditioning after reuse, mitigating semantic drift and condition-adherence issues. Experiments show that default sparsity reuse configuration preserves generation quality with a 2.16$\times$ speedup.

Hyperparameter Optimization (HPO) is essential for maximizing machine learning model performance, and its core challenge is sample efficiency: finding strong configurations within a limited budget. Because every HPO tool relies on a surrogate prior that imparts its own inductive bias, individual tools struggle once problems become sufficiently diverse and drift from these priors. Motivated by the reasoning and generalization capabilities of LLMs, recent work has explored using LLMs for HPO and reports improved per-iteration performance. Yet these methods share two limitations with a common origin: they use the LLM as a single-tool replacement evaluated by iteration count. (i) Deployed in place of prior tools, the LLM is itself constrained by its pretraining objective to one family of inductive-biased proposals; this single-source setup still fails to handle the full diversity of problems. (ii) Per-iteration evaluation ignores that, in real runs, LLM inference or tool execution is paid serially on top of model evaluation every round, so iteration-count gains do not translate into end-to-end wall-clock gains. We present ASAP, an agent-system co-design that addresses both limitations. On the agent side, ASAP uses the LLM to integrate a diverse pool of inductive-biased optimizers and to select among their proposals each round. On the system side, ASAP re-architects the loop to reduce end-to-end wall-clock while preserving regret quality: a prefix-stable prompt maximizes KV-cache reuse across rounds; speculation parallelism hides the remaining LLM and tool latency under model evaluation via a relative-error accept test; and a Self-Tuner adapts the speculation threshold from execution logs off the critical path. Extensive experiments on diverse modern HPO tasks show that ASAP consistently outperforms baselines, underscoring the value of tool integration and agent-system co-design.

Target-specific peptide design requires sequence and structure co-design under full atom geometric constraints. Latent generative frameworks offer an effective route for this problem by compressing fine grained atomic structures into block level latent representations and performing conditional generation in a compact latent space. However, the scalability of such systems depends heavily on the geometric backbone used throughout their encoding, decoding, and denoising components. We introduce MEET (Memory Efficient Equivariant Transformer), an E(3) equivariant backbone for scalable atomistic peptide modeling. MEET maintains coupled invariant scalar and equivariant vector feature streams, while reformulating geometric computation around memory efficient attention. It initializes vector features through global coordinate aggregation, incorporates pairwise distances through augmented query and key dot products, and injects covalent bond information through sparse bond adaptation. Integrated into a VAE and latent diffusion pipeline for full atom peptide generation, MEET achieves linear memory scaling with atom count and improves generation quality over existing peptide design methods. Experiments on large scale AFDB derived datasets further show that the proposed backbone supports systematic model and data scaling, leading to better binding affinity, physical validity, and sample diversity.

Modern large language models based on softmax scaled-dot-product attention are constrained by their training sequence length: as the key-value sequence grows, softmax probability mass can dilute across a wider distribution, inducing activation shift and long-context performance collapse. Moreover, long-context language modeling faces a structural tension: a sliding-window attention core maintains a bounded local representation and low perplexity but is blind to long-range dependencies, while full-context attention preserves global recall but suffers from out-of-distribution perplexity explosion. To resolve these limitations, we introduce ATMA, a hybrid convolutional-attention architecture that integrates a novel three-channel attention mechanism. ATMA factorizes the attention mixing step into: (1) a count-blind, unit-vector direction channel, (2) a bounded magnitude channel driven by the participation ratio of effective matches over an extreme-value-corrected null sink, and (3) a long-term recurrent compression memory optimized via a gated-delta fast-weights rule. Neither the Polar Attention core nor the recurrent memory is sufficient alone; their combination enables monotonic perplexity reduction and high-fidelity long-range retrieval simultaneously. We evaluate ATMA using a 100-run factorial ablation sweep, demonstrating that the combined Polar + memory model maintains induction needle-in-a-haystack retrieval accuracy above 90% out to 64K tokens (32 times the training length of 2K) while its document perplexity improves monotonically, outperforming softmax-based memory baselines which collapse at extreme context lengths. Code: https://github.com/kreasof-ai/atma

Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the network, producing smaller models that retain most of their accuracy. As attention layers are the most resource-intensive parts of LLMs, pruning them is a promising compression strategy. Prior work shows that up to 33% of attention layers can be pruned with minimal accuracy loss. Nevertheless, the impact of attention pruning on model interpretability, specifically faithfulness and confidence calibration, remains unstudied. To address this gap, we study how pruning attention layers affects explanation faithfulness and confidence calibration across five LLMs and eight datasets. While the pruned models often maintain high accuracy, we find that their faithfulness and calibration often degrade. Notably, faithfulness and calibration can fluctuate significantly, even when accuracy remains stable, highlighting a misalignment between model confidence, interpretability, and accuracy. Our findings suggest that layer pruning can affect LLMs' interpretability and reliability in ways not captured by accuracy and efficiency measures alone. We recommend including explainability and calibration metrics when evaluating pruned models.