每天知道
你的领域
出了什么

Hierarchical vision-language-action (VLA) systems consist of a high-level vision-language planner and a low-level action expert that generates continuous actions. This hierarchical design has practical value only if the planner can generate plans fast enough to meet real-time control requirements, and the resulting plans actually contribute to the generation of action. We study one such system, a waypoint hierarchy pipeline adapted from $π_{0.5}$, and find that neither requirement is satisfied. This baseline relies on token-level autoregressive decoding (Token-AR) to generate a waypoint plan, requiring 57 very expensive vision-language model (VLM) forward passes. However, we find that erasing the waypoint endpoints has little effect on task success. Two findings reveal the misalignment of planner-executor: the planner generates outputs at an excessively fine granularity, and the executor underuses plans as a control condition. We address the latency issue with waypoint-aligned block-autoregressive decoding (Block-AR), and plan underuse issue with normalized goal modulation (NGM), a layer-wise goal path constrained by phase gating and anti-shortcut training so that the waypoint influences action generation maintaining other signals. Our method reduces the maximum number of VLM forward passes from 57 to 8 on LIBERO, including one prefix prefill, and achieves an $8.7\times$ reduction in planning latency on a Rokae dual-arm robot. With normalized goal modulation and anti-shortcut training, Block-AR's success rate on LIBERO-Long increases from 91.0% to 96.2%, while its average success rate across the four suites increases from 95.85% to 98.45%. On three bimanual tasks with this robot, success rates remain comparable across methods.

Large language models (LLMs) have demonstrated promising performance in log anomaly detection, yet how their adaptation strategies, architectures, and deployment configurations affect detection effectiveness remains insufficiently understood. To investigate these factors, we conduct a systematic empirical analysis across three public log datasets, examining different adaptation strategies, model architectures, parameter scales, and quantization settings. Our results reveal substantial performance differences across adaptation strategies, while model scaling yields varying detection gains across datasets. We further observe that models with comparable detection accuracy can exhibit markedly different computational costs, and that low-bit quantization largely preserves detection performance in the evaluated configurations. Finally, we examine detection robustness under structural, semantic, and label noise at different perturbation levels. These findings provide empirical insights into the performance, efficiency, and robustness of LLM-based log anomaly detection, highlighting practical considerations beyond conventional accuracy-oriented evaluation.

Reliable voice interaction is essential in environments with limited internet connectivity and strong privacy. However, most existing voice assistants depend on cloud-based services, which leads to latency issues, dependency on internet access, and privacy vulnerabilities. This research presents LUMO (Lightweight Unified Multilingual Orchestrator), a privacy preserving offline voice assistant designed for edge computing environments. This system integrates local Automatic Speech Recognition (ASR), locally deployed quantized Large Language Model (LLM), and Text-to-Speech (TTS) synthesis into a fully offline pipeline running on a Raspberry Pi 5 with 8 GB RAM. To enable efficient operation on resource constrained hardware, the language model is compressed using 4-bit GGUF quantization, which reduces memory usage while preserving practical conversational capability. Existing edge based voice assistants Mycroft provides partial offline functionality without a generative LLM, with an approximate latency of ~5 s and power consumption of ~12 W, while Rhasspy supports full offline operation but lacks generative capabilities, with ~3 s latency and ~11 W power usage. In contrast, LUMO achieves a Word Error Rate (WER) of 6.8% for short English utterances in low noise conditions, an end-to-end response latency of 2.0-4.0 s, and a lower peak power consumption of approximately 9.0 W. The system also achieves effective offline recognition for Bangla speech, supporting multilingual accessibility in low resource settings. By operating entirely offline, LUMO provides strong data privacy, reduced need for cloud connectivity, and suitability for privacy sensitive edge execution such as rural healthcare, education, and disaster response scenarios.

Hybrid language models maintain fixed-size recurrent states, but existing quantizers typically use eight bits or more. Quantization errors persist according to channel decay rates. We derive distortion weights from the observability Gramian and combine them with normalized state ranges for mixed-precision bit allocation, without calibration data, rotation, or training. We also quantize decay rates logarithmically. With per-token state quantization, a four-bit mean payload reduces excess negative log-likelihood by factors of 3.3--27.9 relative to the best of seven baselines across three hybrid models; metadata costs vary. At six bits, negative log-likelihood differs from the FP32-state baseline by less than 0.005 nats. Ablations separate gains from variable bit widths, decay weighting, and range normalization. With less frequent write-backs, gains diminish and depend on the model and budget.

Tool observations dominate the context of software-engineering agents, making long interaction histories costly to maintain. Existing context compression methods can discard information needed by later actions, while adapting agents to soft-token representations can compromise their original behavior. To reduce context while preserving action-critical information and agent behavior, we combine Latent Observations, Hard Actions (LOHA), a context layout that separates compressed history from text needed for exact reference, with Anchored Context Distillation (ACD), a training method that enables latent reading while constraining behavioral drift. LOHA compresses older tool observations into soft tokens while retaining the agent's own turns and the last K observations in text, providing compact access to historical information and exact access to recent content. To enable the agent to use this representation, ACD distills the base model's full-text predictions into the latent view while anchoring its behavior on plain-text inputs to the same base model. On SWE-bench Verified, K=3 reduces context per call by 43% for Qwen3-4B and 57% for SWE-Master-4B-RL, with resolve rates of 12.1% and 21.8% versus 14.5% and 27.5% for their uncompressed bases. A single-run recency sweep reaches 14.4% and 23.0% at K=8, with larger windows generally favoring task performance over compression. Under a 32K-token limit, Qwen3 with K=3 resolves 21.1% of a 199-instance subset versus 11.1% for the same adapted agent using full text. In concurrent single-GPU serving, it achieves 1.9 times that full-text agent's instance throughput.

Whether an information extraction pipeline should process page images or parsed text depends on the document, and the answer flips across the layout spectrum. We study this trade-off under a constraint that rules out (closed) cloud services: privacy-sensitive documents processed on-premise by small ($\le 8\mathrm{B}$ parameter) text-only and vision--language models, evaluated on both accuracy and energy over a design space spanning input representation, model family, and inference configuration. Benchmarking on the near-plain-text Kleister-NDA contracts and the layout-rich VRDU forms, we find that batching is the dominant energy lever, cutting energy per page by 38-85% at no cost in accuracy, while FP8 quantization saves 27-32% when requests are served one at a time but less than 1mWh per page (9-19%) once batching is applied. Preprocessing dominates what remains: neural OCR costs $17\times$ more energy per page than classical OCR and never reaches the Pareto frontier. Which representation wins flips with the type of document: vision--language models on layout-rich documents and small text-only models with a cheap parser on near-plain text, where they are both more accurate and cheaper than any vision--language configuration. Our work yields concrete guidelines for energy-efficient, privacy-compliant local information extraction.

Cross-domain few-shot learning requires adapting a classifier to a new visual domain from very few labelled examples without target-time parameter updates. We isolate one question: under a fixed global representation, what does joint query-support adaptation contribute to prototype construction? The Within-Instance Prototypical Transformer (WIPT) implements single-query test-time prototype adaptation by jointly transforming one unlabelled query and the labelled support embeddings, then forming query-specific class means. Using a shared frozen ViT-S/16 encoder, miniImageNet source training, and CUB, EuroSAT and ISIC targets, we replicate the key comparisons across five independent training seeds. In 1-shot evaluation, WIPT improves frozen ProtoNet in every run on CUB (+0.21 percentage points) and EuroSAT (+2.07), but decreases ISIC (-0.22). In 5-shot evaluation, ProtoNet remains strongest overall, while WIPT consistently improves a capacity-matched support-only Transformer on ISIC (+0.99). Joint processing of up to five queries yields no reliable accuracy gain; in a head-only 5-shot benchmark, g = 5 reduces analytical attention-token pairs by 73% and peak allocated memory by 29% relative to g = 1, although latency is non-monotonic. Across all target/shot conditions, WIPT changes uncertain ProtoNet decisions far more than confident ones, and rescue/break decomposition accounts for the observed gains and losses. Source-shift and scorer controls further show that the benefit is not universal. Overall, WIPT provides a streaming-compatible form of test-time prototype adaptation that can improve difficult low-shot cross-domain decisions without target-time optimization.

Large vocabularies make output heads a substantial inference cost in small language models. We introduce softmax reparameterization, a post-training method that searches over functionally equivalent output heads before quantization. The method subtracts a scalar multiple of the vocabulary-row mean from every output row and selects the coefficient by validation KL. For linear-softmax heads, these shifts preserve full-precision predictions exactly and require no decoder retraining; a rank-one correction extends the construction to nonlinear logit paths. Across seven output heads and three quantizers, W4 gains are largest where baseline quantization substantially distorts predictions: test KL falls by 93% on XGLM under RTN and by 73--77% on Phi, BLOOM, and BLOOMZ under activation-weighted MSE. Heads with low baseline error change little; at W2, used as a compression stress test, benefits extend more broadly. On Phi, the gains persist under stronger GPTQ calibration; a separate untouched holdout reproduces the improvements on Phi and BLOOM. Frozen WikiText-selected coefficients also transfer without retuning to C4 and OpenWebMath. Residual analysis on Phi shows how fidelity can improve despite greater total logit error: the selected representative reduces error on likely outputs and lowers its Fisher-weighted cost. For shift-compatible heads, the shift adds no inference operation. With the decoder held in BF16, a packed W4 Phi output head reduces batch-one generation latency by 10.8%, and reparameterization preserves this speedup.

Full-duplex speech language models continuously accumulate acoustic key-value (KV) states, making long-running interactions memory-intensive. During listening, the model can finish processing an audio unit before the next arrives; we term the remaining interval listening-time slack. We propose acoustic-to-text KV compression, which introduces a transcription side channel to convert incoming speech into compact textual memory within this interval. When the cache exceeds a target budget during inference, older acoustic states are evicted while transcripts and recent acoustic context remain. We train the side channel with LoRA using cross-entropy on transcription segments. To preserve listening and speaking behavior, we apply knowledge distillation to the original model's token-level output distributions at native prediction positions. On ten-minute LongSpeech sessions, our MiniCPM-o 4.5 implementation reduces peak streaming KV-cache size by 64.6% compared with the same model without eviction. The proposed method also improves transcription, temporal question answering, and summarization over the baseline. Full-Duplex-Bench evaluations further show comparable pause-handling, turn-taking, and interruption performance.

Tabular in-context learners such as TabPFN, Mitra, or ConTextTab rely on alternating row and column attention over 2D sequences of latent embeddings. These attention patterns differ markedly from the one-dimensional case in language models: row attention involves longer sequences while column attention operates on much shorter ones, and the strided memory layout of tabular data makes producing contiguous tensors costly. Moreover, the hidden dimensions used in current models are small compared to recent language models. Yet efficient attention has been studied mostly for one-dimensional sequences, leaving the two-dimensional tabular setting unexplored. To this end, we create a reproducible benchmarking setup and study the unique characteristics of tabular attention across several backends — Torch SDPA (efficient and cuDNN), FlashAttention-2/3/4, and the inference-only backends vLLM and SageAttention — measuring forward and backward throughput across realistic tabular shapes on three GPU generations (A100, H100, B200). We find that the optimal backend choice differs between column and row attention and varies across hardware as well as model specifics: While the FlashAttention implementations tailored for each GPU generation perform overall best, they are at times outperformed by CuDNN in the case of column attention at longer sequences with cross-over points depending on the head dimension. Among inference-only backends, SageAttention performs well for row attention and large sequences beyond 16\,k rows. Our reproducible benchmark lays the foundation for future improvements to table-native attention. The self-contained benchmarking and evaluation code is openly available at: https://github.com/SAP-samples/tabular-attention-benchmark

Agentic LLM workflows decide their execution paths at runtime. Downstream computation may be predictable, or may have run before, yet it cannot begin until the model or the user resolves the branch. We call this serialization the branch-resolution barrier. Caching alone does not hide it: the key that identifies a reusable result is not known until then. In this paper, we propose DynBranch, which makes an unresolved branch addressable before it resolves. Its stable coordinate lets candidate subgraphs run during resolution and completed subgraph results be reused across later requests. A two-level controller admits this work when its expected benefit exceeds the load price. DynBranch sits at the model-API boundary and requires no changes to agent harnesses or model execution engines. Across four agentic workloads with Qwen3-32B on 4x H200 GPUs, DynBranch reduces mean latency by up to 32% over each workload's strongest prior system and by 46-66% against a no-reuse floor, while preserving workflow results. The benefit persists across backbone families and on a commodity Qwen3-8B/RTX 4090 deployment.

Looped transformers reuse weights across recurrence steps, making low-bit quantization especially attractive. We identify two distinct failure modes of standard post-training quantization. On Huginn-3.5B, per-channel INT4 fails primarily at the non-residual loop-entry adapter, while quantizing the residual core is much less damaging. We call this feedback exposure: a quantized layer perturbs the recurrent state without an identity path, and the resulting error is fed back at later steps. Controlled experiments on linear filters and Mamba state-space models show that feedback exposure also occurs outside transformers. Grouped INT4 reveals a separate failure, calibration blindness: our one-step GPTQ baseline builds its Hessian from step-0 activations, leaving input directions used later in the recurrence nearly unweighted. Across nine checkpoints from seven looped architectures, one-step GPTQ is worse than round-to-nearest (RTN) on the primary task metric for five checkpoints. Accumulating the GPTQ Hessian across recurrence steps outperforms both one-step GPTQ and RTN on all nine checkpoints and recovers bf16-level accuracy on Huginn. These results separate two questions for PTQ on looped models: where quantization error enters the recurrence, and which states calibration sees.

Disaggregating the two stages, Prefill and Decode, onto separate GPU pools is now a standard optimization for (text-only) LLM serving. However, multimodal LLMs (MLLMs), which add a third phase, Encode, pose new challenges for resource allocation. Encode turns images, video, or audio into embeddings that the language model can consume, yielding a three-stage Encode-Prefill-Decode (EPD) pipeline. Existing frameworks offer only partial answers: text-only PD systems lack Encode, while EPD frameworks expose it as a separate service without regulating downstream request flow. The pipeline also carries a structural resource imbalance: every request enters through Encode before downstream work can begin, yet per-request execution leaves the encode GPU severely underutilized even at high loads, starving the downstream Prefill and Decode workers. Addressing this, we reposition Encode as the control point of the EPD pipeline, exposing three tightly coupled dimensions: when work enters downstream, where prefill executes, and how the GPU is shared. We instantiate this in EAServe across two co-designed layers. Its runtime manages load-adaptive micro-batching, rate-controlled partial offload to a co-resident prefill worker, and dynamic SM partitioning for predictable co-location. The configuration layer, Hybrid Auto Selection (HAS), navigates the joint space of GPU allocation, encode batch size, and offload ratio by pruning unbalanced allocations with per-stage capacity profiling and refining the remainder through TPE-based Bayesian optimization. Evaluated on three MLLM architectures spanning image, video, and audio, EAServe delivers up to 4.3x and 1.7x higher goodput than NVIDIA Dynamo and vLLM, respectively, under identical SLO constraints, sustains more balanced and higher GPU utilization across the EPD pipeline, and reaches near-optimal configurations faster than baseline search methods.

Agentic LLM inference accumulates long KV caches across iterative observation-reasoning-action loops, imposing substantial memory overhead and limiting serving throughput. Existing compression methods emphasize overall output quality, overlooking the asymmetric importance of actions in driving task progress. Our key idea is to establish a compression criterion that values KV entries by their contribution to action generation and prioritizes action quality. However, iterative execution, dynamic memory demands, and scattered action-critical entries pose challenges to eviction policies, budget allocation, and paged memory integration. To this end, we propose ActKV, the first KV cache compression framework tailored for agentic LLM inference. (i) Action-oriented KV cache eviction exploits stable action access patterns to retain entries critical to future actions, supporting reliable task progress under compression. (ii) Confidence-driven adaptive budget allocation uses LLM's intrinsic confidence to adapt the budget to evolving action-critical memory demands. (iii) Page-aware compression management standardizes compression into three primitives with customized kernels, realizing practical throughput gains. On long-trace tasks, ActKV retains an average of 98.53% of FullKV's accuracy with only 25.98% of its peak KV cache memory. It also achieves 3.97 times and 3.58 times FullKV's token and task throughput, delivering state-of-the-art performance.

Autoregressive LLM inference at long context is bounded by memory bandwidth, not arithmetic throughput, and the binding resource shifts from model weights to the Key-Value (KV) cache as sequence length grows. For Llama-3-70B in BF16, the 140 GB weight footprint exceeds the 80 GB HBM of a single accelerator, and one 128k-token sequence adds 42 GB of KV cache. Techniques that compress, evict, page, share, or offload KV state have proliferated, but reported gains use inconsistent workloads, hardware, and quality metrics, preventing cross-paper comparison. This SoK paper unifies the field analytically, with a protocol that strictly separates derived and reported claims. We derive closed-form arithmetic intensity as a decaying function of context length, parameterized by hardware topology for NVIDIA H100, NVIDIA B200, and AMD MI300X, including per-die bandwidth partitioning and the crossover lengths where KV traffic overtakes weight traffic. We classify the literature into five domains, quantization, token eviction, KV paging, prefix caching, and heterogeneous tiering, evaluating one method per domain at 128k context under a single protocol. The central finding is a three-regime structure: below a hardware-specific crossover, weight traffic dominates and KV compression yields negligible speedup; beyond it, KV traffic dominates and each domain trades quality for bandwidth savings approaching the roofline bound. Paging and prefix sharing are lossless but address capacity, not bandwidth. Quantization and eviction cut bandwidth directly, with degradation that accelerates below 4-bit precision and turns discontinuous for eviction on position-sensitive tasks. Tiering converts the bandwidth wall into an interconnect problem bounded by PCIe or NVLink rather than HBM. We close with design rules for selecting a compression domain given hardware, context length, and quality budget.

AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Cloud assistants such as ChatGPT route sensitive student data to foreign servers---violating data-sovereignty laws such as Vietnam's Decree 53---and, pre-trained on Western-centric corpora, are not organized around the national textbook curriculum, so their knowledge of local content is unsystematic and frequently hallucinated. Self-hosting an open model keeps data on-premise but hits a two-fold wall: post-training quantization (AWQ, GPTQ) tames the static weight footprint, yet the dynamic KV cache and prefill latency of long tutoring contexts still cause out-of-memory failures and slow responses on consumer GPUs, while the model keeps hallucinating on region-specific material. We present DeepEdu-v1, an AI-tutoring system for Vietnamese education built on SCALE (Self-improving Context-Aware Learning Engine), a framework with two innovations. First, a long-context inference engine amortizes token selection from per-sub-chunk to per-cluster granularity; on long-context retrieval it issues x7.7 fewer retrieval calls than a state-of-the-art selective-attention baseline, cutting prefill latency (TTFT) by roughly 35% while matching or improving task accuracy. Second, a self-improving agentic layer continuously curates a verified playbook from past interactions instead of fine-tuning, a design intended to progressively reduce reliance on dominant-language priors as trustworthy local knowledge accumulates. In its deployed configuration, DeepEdu achieves a nearly x2 TTFT speedup over standard vLLM serving and lifts agentic accuracy from 70.0% to 79.5% on complex tasks, with the strongest per-track gains across financial-reasoning and interactive-agent benchmarks.

A punch is a ballistic, full-body action driven by a kinetic chain running from the legs through the trunk to the arm, where a small sequencing error separates a scoring strike from a miss. Wearable sensors can capture this movement in the gym, but most deployable systems only classify which punch was thrown rather than assess how well it was thrown. We present Skill Profiling with Attributable Reasoning (SPAR), an eight-IMU garment and pressure-insole system that classifies each punch as expert or novice and treats an explanation of that prediction as feedback. Feedback is only useful if the person receiving it can act on it, so SPAR explains the prediction at three tiers, a per-joint attribution for the analyst, a counterfactual over kinetic-chain layers for the coach, and a plain-language narrative of the two for the athlete. Across 17 participants and 4,713 punches, SPAR reaches a leave-one-participant-out AUC of 0.842 (95% CI [0.769, 0.907] over participants). A frozen time-series foundation model encodes the joint-angle and plantar-force series, and a small transformer trained on the cohort classifies the encoding. We audit the two quantitative tiers and report six themes from a thematic analysis of interviews with six practicing boxing coaches.

Large language models rely on KV caching to reduce repeated prefill computation in long context and interactive applications. As lightweight adapters evolve, cached states reflect earlier versions, so stale reuse distorts current model outputs, while complete affected suffix recomputation restores fidelity at substantial cost. We seek minimal recomputation that recovers current adapter behavior. Existing systems track token, context, or stable adapter identity, but neither represent caches from earlier adapter versions nor distinguish update propagation from the recomputation required for behavioral recovery. To address these gaps, we introduce CacheReforge, which represents stale KV caches as layerwise mixed-version objects. It combines per-layer adapter anchors, calibrated sensitivity, accumulated drift, and executable restart boundaries to select direct reuse, bounded recomputation, or complete affected-suffix recovery. We distinguish dependency depth from the functional recomputation horizon and use cumulative tail influence to characterize when bounded recovery preserves current-model behavior. We evaluate CacheReforge on Qwen2.5-1.5B and Qwen2.5-7B with continual LoRA updates, including 16K HotpotQA and 2WikiMQA workloads. CacheReforge reduces mean KL divergence by 92.4% relative to stale reuse, while recomputing only 5.44% of layers and reducing cache-maintenance time by 93.2% relative to fresh full prefill. These results show that version-aware recovery preserves model fidelity and most KV caching gains.

We introduce Acacia, a graph foundation model, trained on the web graph. Acacia (i) supports arbitrary feature dimensionalities and semantics without additional training, (ii) supports a wide range of tasks, including node classification, link prediction, node clustering, and graph generation, without additional training, (iii) has in-context learning capabilities, and (iv) does not rely on pretrained LLMs. In particular, existing graph foundation models often require training additional classification heads or feature projectors to accommodate new graphs or new labels, whereas Acacia does not. Moreover, existing graph foundation models often gain their capabilities by being stitched together with pretrained LLMs, whereas Acacia is trained from scratch using only the Common Crawl web graph. This is also an important result because it provides evidence that graph models can acquire emergent capabilities from scratch like LLMs.

Activation steering is a powerful training-free paradigm for controlling large language models at inference time. However, standard approaches estimate a per-layer steering direction from contrastive data and apply it on the layer's entire representation space, which may couple the intervention to off-target properties present in the contrastive data and degrade unrelated capabilities. To mitigate this issue, we introduce LocUS (Localized Unembedding Steering), a method which grounds activation steering to the model's own output vocabulary subspace. By identifying a property-specific linear subspace within the unembedding matrix, LocUS enforces a geometric constraint that restricts the steering transformation to a specific subspace and at the same time localizes its application to a sparse subset of attention heads. Extensive evaluations across three model families on toxicity mitigation, sentiment redirection and sycophancy suppression show that LocUS matches or outperforms state-of-the-art baselines while intervening on under 6% of parameters and better preserving general capability.

Scaling language models to long contexts is limited by the quadratic cost of self-attention. Block sparse attention offers an efficient alternative, but selecting the retained blocks remains a bottleneck. Conventional block selection requires scoring all query-block pairs and therefore remains quadratic in sequence length. To address this issue, we propose PISA, a block-sparse attention mechanism that employs a pyramid Top-$K$ selection strategy. The main idea is to gradually narrow down the candidates across different levels, making it more efficient to find the most relevant keys. Specifically, we construct a coarse-to-fine hierarchy of keys and perform selection from the coarsest level. At each level, LogSumExp scoring is applied to a bounded candidate set to select candidates for the next finer level, continuing until the finest level is reached. Through pooling, we construct $O(\log N)$ levels of keys, yielding an overall complexity of $O(N\log N)$, where $N$ denotes the sequence length. We develop hardware-aware Triton kernels for both training and inference, fusing hierarchical routing and LogSumExp scoring without materializing the query-key score matrix. We further evaluate our method on language modeling tasks. Compared with the baseline, our method achieves comparable performance on benchmarks such as commonsense reasoning while delivering better results on retrieval tasks.

Large language models (LLMs) have become fixtures of academic work even as their users describe them as degrading their writing, thinking, and skills. Dominant adoption frameworks read continued use as evidence of satisfaction, and cannot explain continued use of a distrusted tool. We interviewed 36 graduate student workers, balanced between English-as-a-foreign-language (EFL) and non-EFL speakers, and introduce the Active Negotiation framework: a model of sustained LLM use as a recurring cycle of risk, mitigation, and justification. A failure surfaces a risk, mitigation labor addresses it, and a justification renders the residual risk tolerable until the next failure reopens the cycle. The cycle runs across three dimensions: practical, auditing output; internal, auditing one's own cognition and identity; and social, managing how peers and institutions perceive use. EFL participants invoke linguistic parity as a further justification. We reframe continued adoption as compliance sustained by invisible labor.

This paper proposes an architecture for equipping large language models (LLMs) with audio-understanding capabilities without fine-tuning their weights. The proposed symbiotic architecture employs an injector module that writes audio-conditioned vectors directly into the target LLM's short-term memory, i.e., the key-value (KV) cache, enabling the LLM to behave as an audio language model (ALM). The architectural advantages are twofold. First, it improves the scalability of ALMs: because the proposed method bypasses the LLM during audio injection, the injection cost is governed by the injector width rather than the backbone width, and can therefore scale more slowly than the cost of full-backbone prefilling. Second, since the training scheme does not update the LLM weights, the original capabilities of the LLM are preserved without the risk of degradation from fine-tuning. The effectiveness of the proposed method is evaluated on both audio-understanding tasks (automatic speech recognition, audio question answering, and acoustic scene classification) and text-only tasks. We confirm that, while activating fewer parameters during audio prefilling, our architecture outperforms the conventional method with a frozen LLM and approaches the performance of a fine-tuned ALM, all while preserving the backbone LLM's original text-only task performance by construction.

Large language models operating in multilingual contexts must resolve target response languages early in generation, yet the causal circuitry governing first-token language identity decisions remains poorly mapped. We present an end-to-end structural circuit analysis across six model architectures spanning four families: GPT-2, BLOOM-560M, Pythia-1B/2.8B, and Qwen2.5-1.5B Base/Instruct. Using Edge Attribution Patching (EAP) with FP16 active clamping, followed by exact activation patching verification with a 2,000-candidate-edge search ceiling, we extract directed acyclic graphs driving first-token language broadcasting. Across the standalone models, we observe deep or mid-to-deep broadcasting hubs, though the evidence is strongest for Pythia-2.8B and BLOOM-560M because GPT-2 and Pythia-1B leave few out-of-graph heads for comparison, while both Qwen2.5-1.5B variants invert the necessity check. Scaling from Pythia-1B to 2.8B expands node participation while maintaining a similar verified edge budget, producing sparser topology. The Qwen2.5-1.5B base and instruct circuits retain 84.7% Jaccard similarity, including the Layer 27 hub, indicating that first-token routing is largely established during pretraining and preserved by instruction tuning. Finally, EAP scores correlate weakly with exact patching deltas across most models, showing that linear gradient approximations can diverge from causal interventions in FP16 and motivating exact-patching verification for reliable circuit discovery.

Contemporary large language model (LLM) chat systems treat conversation history as an immutable sequence of turns that defines the model's working context. However, user intent in real interactions is not static: it evolves through correction, refinement, and shifting constraints. This mismatch between dynamic intent and static transcripts can result in context pollution, where outdated or irrelevant information persists and continues to influence subsequent responses. We introduce mutable transcripts, a new interaction paradigm that enables users to revise prior turns through natural language edit requests, allowing the conversation history itself to be updated rather than appended. This reframes the transcript from a passive record into an editable representation of conversational state. We present a working prototype that integrates transcript-level revision into a standard chat interface and evaluate its feasibility through a controlled user study (n=17) and an illustrative transcript analysis of representative interaction scenarios. Participants significantly preferred mutable transcripts over standard chat across measures of clarity, confidence, and ease of use, with reduced intent to restart conversations. Transcript analysis of representative user study conversations shows that mutable transcripts can reduce conversation length and eliminate obsolete retained context. These findings provide initial evidence that user-driven revision of conversational history can improve interaction quality and help maintain a more current representation of user intent. The source code and prototype can be accessed at https://github.com/QxLabIreland/ReChat

The empirical success of pretraining large language models has inspired a deeper investigation into the underlying loss landscapes and the optimization dynamics. Recent empirical and theoretical study suggest that the training loss landscape often exhibits a "river-valley" structure, which features a low-loss manifold (river) flanked by sharp orthogonal directions with higher loss (mountains). In the long term, the optimization progress is determined primarily by the progress along the river. Within such a landscape, gradient descent with large learning rates can move faster along the river despite high apparent loss due to vertical oscillations, while a subsequent sharp decay in the learning rate suppresses these oscillations, revealing genuine optimization progress. This explains the recent success of warmup-stable-decay (WSD) learning rate scheduler which, unlike cosine scheduling, keeps stable high learning rate and decays before producing intermediate checkpoints. Building on this foundation, in this work we take a step further and study the role of momentum within such a loss landscape. We establish theoretical analysis that characterizes how momentum accelerates optimization by stabilizing large learning rates that can not be tolerated by vanilla GD without deviating significantly from the river. The enabled large learning rate in-turn gives greater speed along the river and makes faster essential progress in the long run. Another intriguing observation from theory is that for a river-valley landscape with very flat and slow-spinning river, the momentum itself does not contribute directly to acceleration in terms of the speed of tracking the river, while the main acceleration comes from the admissible larger learning rate.

Most work on improving large language models treats accuracy as the sole objective. We argue that the harness, the Python code surrounding the model that constructs prompts, routes calls, and parses outputs, is a first-class design surface whose quality is inherently multi-objective: an accurate harness that refuses no unsafe request, or that consumes an order of magnitude more tokens, is not a good harness. We present Meta-Harness, a system that casts harness design as search over three per-domain objectives (accuracy, behavioural safety, and token cost) solved by an agentic proposer (Claude Code) with full filesystem access to prior harness source, execution traces, and scoring artifacts. Our central finding is that a singlephase joint-reward proposer (MoMHa) outperforms every alternative, including a two-phase "accuracy then tokens" ablation, scalar-only feedback, and an accuracy-only baseline. We evaluate on seventeen domains: seven synthetic capability suites, seven real-world public benchmarks (HumanEval, MBPP, Spider, FEVER, MMLU-Pro, LawBench, NuminaMath), and three U-SafeBench-derived user-specific safety domains, using a 12-model fleet spanning four families. On the synthetic track MoMHa achieves a joint mean of 0.482 versus 0.198-0.422 for ten baselines, winning $7 / 10$ per-domain columns; on the real-world track it scores 0.461 versus 0.377 for the strongest baseline (DSPy), winning 5/7 columns, demonstrating that harness strategies transfer to unseen benchmarks without retraining on 8 of 12 target models. MoMHa attains the highest measured behavioral safety composite (U-SafeBench, 0.781) and uses 95 fewer tokens per example than the two-phase alternative. We will release all harness code, evaluation infrastructure, and crossmodel logs.

Researchers increasingly use generative large language models (LLMs) to convert corporate text into empirical variables. We examine the extent to which LLM-based textual measures are invariant to model choice using thirteen measures, including sentiment, management clarity, uncertainty, answer specificity, and climate and political risk. Seven LLMs from different providers score earnings call transcripts of S&P 500 companies on these constructs. Cross-model rank correlations average only 0.52, and transcript-level differences common across providers account for only 34% of total score variation. Cross-model disagreement does not predict subsequent analyst or market disagreement, consistent with a substantial model-specific component rather than common ambiguity in the underlying disclosure. Model choice significantly affects downstream inference, with coefficient magnitudes, signs, and statistical significance varying substantially across models. Averaging across providers makes transcript rankings more stable for most constructs, but score levels remain sensitive to the models included in the ensemble. LLM-generated variables should therefore be treated as model-contingent measurements and validated across providers.

Corr2Cause asks whether a causal claim holds in every DAG compatible with observed correlations and conditional independencies. We frame this as latent-object reasoning: the label is defined by a CPDAG query, but free-form chain-of-thought often collapses the Markov-equivalence-class problem into local pattern matching. We propose Structured Thinking, a two-turn pipeline that first externalizes a typed, schema-constrained CPDAG summary and then answers against that graph state. On the Corr2Cause full test, Structured Thinking raises Qwen3.5-27B from $73.0$ to $86.4$ $F_1$(Yes) over a strong PC-instruction baseline in the primary paired run ($+13.4$ pp; McNemar $p=2.4\times 10^{-6}$; bootstrap $95%$ CI [$+8.4$, $+18.6$]); across three full-ID seeds, the mean gain is $+8.1 \pm 5.3$ pp. A PC-scaffolded two-turn prose control reaches only $67.6$ $F_1$, indicating that a detailed PC scaffold plus a schema-free prose intermediate is not sufficient. The same pattern holds on Qwen3.6-27B, Paraphrase-OOD, and GPT-5.4-mini. Scrambling the emitted CPDAG costs $12.0$ pp $F_1$, and a full-split audit shows close agreement with the reference CPDAG (ID skeleton $F_1$ $0.960$; exact match $75.9%$). These results support a bounded design principle: externalize the latent object that defines the label, constrain its form, and test whether downstream answers use it.

We introduce Kaggle Game Arena, an open and ever-expanding platform to evaluate large language models (LLMs) through competitive games. Different from static benchmarks, game arena enables models to play head-to-head matchups in structured environments where the gameplay strength naturally increases as models evolve, preventing performance saturation. This technical report details the infrastructure behind Game Arena and describes the three pilot game environments: Chess, Poker, and Werewolf. These environments span perfect information, imperfect information, and multiplayer game settings, enabling a systematic study of models' strategic planning, adaptation, and robustness under uncertainty. For each game, we provide a detailed description of the environment, evaluation metrics, and results from running full competitions across models. Through robust infrastructure and large-scale ground-truth based evaluation, Game Arena ensures reproducibility, transparency and generalizability to new games and variants over time.