overfeed.news
Anuncio

SRExpert

Deja de saltar entre 6 herramientas de Kubernetes.

Monitoreo, alertas, seguridad, despliegues Helm y operaciones con IA en una sola plataforma.

Probar 30 días gratis

Tema

LLMs

2967documentos

226últimos 7 días

arXiv AI Papers

GSLM2: Multi-Stream Speech Representation Learning and Generative Spoken Language Modeling

Generative spoken language models (SLMs) offer a route to learning linguistic structure purely from speech, yet they lag far behind text-based models in both capability and data scaling efficiency. We identify two bottlenecks underlying this gap: the limited linguistic quality of existing speech units and the reliance on a single stream of discrete units to represent speech. Multiple codebooks are widely used to encode acoustic features but rarely to represent speech semantics. We present GSLM2, which learns and models complementary properties of speech at multiple levels of abstraction. Its encoder, SpidR 2.0, uses self-supervised learning with differentiable prediction heads to induce high-quality discrete units at multiple levels. A multi-stream SLM then jointly models these units using a shared temporal backbone, stream-specific predictors, and an autoregressive head that captures cross-stream dependencies. Across training data sizes and model scales, up to 6M hours and 6.5B parameters, GSLM2 consistently improves linguistic competence while scaling more efficiently with data. As a result, it substantially narrows the gap between spoken and text-based LMs; across read and conversational speech domains, we shrink the gap by about two orders of magnitude on sWuggy, sBLIMP, and tSC, while also outperforming competitive speech-text systems on all three tasks. We open-source the training code and model checkpoints at https://github.com/facebookresearch/gslm2.

en
arXiv AI Papers

Rethinking LLM Pruning via Test-Time Scaling

Structured pruning reduces the size of large language models, often at the cost of lower accuracy. Whether this decline reflects diminished reasoning capacity or greater difficulty in sampling correct solutions is less clear. We examine this question across expert, FFN and layer pruning on four mathematical and coding benchmarks, comparing original and pruned models through pass@k at matched sampling budgets. Even after substantial pruning, some models match or exceed the original model's reasoning coverage despite lower pass@1, and solve problems left unsolved in the original samples. Retaining broad coverage, however, does not mean that correct solutions remain easy to obtain. Under severe pruning, diverse generated chain-of-thought (CoT) traces can coexist with increased repetition and less reliable generation. As correct answers become harder to sample, the additional attempts can sharply increase total token use even when individual responses become shorter. This separation between coverage and sampling efficiency also clarifies expert-selection gains, as methods with markedly different pass@1 can solve the same problems at large budgets yet require different numbers of attempts to reach a common coverage target. Pruning should therefore be assessed by both the range of problems a model can still solve and the sampling cost of obtaining correct solutions.

en
arXiv AI Papers

HiGenTrans: Hierarchical LLM Knowledge Transfer for Generative Recommendation

Generative recommendation promises to simplify conventional multi-stage recommender systems by generating item Semantic IDs (SIDs) autoregressively. However, two obstacles limit its effective- ness in industrial settings: interaction-only supervision underuses the semantic knowledge encoded in pretrained language models, while beam-search likelihood ranks token sequences rather than directly estimating item relevance. To address these limitations, we propose HiGenTrans, a three-level framework that introduces LLM knowledge at the input, representation, and decision levels. First, Global Semantic Priming (GSP) adds an LLM-derived user representation to the beginning-of-sequence embedding, provid- ing a semantic prior before SID generation. Second, Hierarchi- cal Representation Transfer (HRT) aligns intermediate LLM representations with depth-matched GenRec layers through mean- centered projections and gated residual connections. Finally, Multi- Signal Decision Calibration (MDC) uses a lightweight mixture- of-experts calibrator to combine semantic relevance, generation confidence, and candidate-set context when reranking beam-search outputs. All semantic features are computed only from the observ- able interaction prefix, preventing target leakage, and can be cached offline. Experiments on three public benchmarks show that HiGen- Trans improves Recall@10 by up to 12.9% and NDCG@10 by up to 33.7% over the strongest baselines. These results demonstrate the value of transferring LLM knowledge at complementary stages of the generative recommendation pipeline.

en
arXiv AI Papers

What Does a Safety Label Measure? Auditing Situational-Safety Benchmarks for Multimodal LLMs

Situational-safety benchmarks label each scene SAFE or UNSAFE and score a multimodal large language model (MLLM) against that label, usually by judging its free-form answer, and these scores guide deployment. We ask what such a label measures. A label score can come from the scene, the request or the benchmark's own files. We propose the Benchmark Card, seven measured fields that tell them apart, and fill it for six benchmarks. Only MSSBench chat leaks the label through its image files: image size alone reaches 82.3% accuracy, matching or beating six of seven commercial models. Elsewhere the signal outside the scene comes from design. In MOSSBench the item partition fixes the label, and on HoliSafe the request alone ranks pairs about as well as the scene. On our corrected chat split, the size rule falls to chance. We then introduce the Spot-Stop decomposition, which compares ranking with labelling on pairs of a safe and an unsafe scene. It splits the gap above a label-swap null into three parts: a threshold part, overlap between safe and unsafe scores, and order that holds only within a pair. Most of fourteen open MLLMs rank better than they label, beyond what their AUROC predicts. On chat, one shared threshold repairs a third to a half of the excess, and label-free recentering recovers it on balanced batches. Recentering on unlabelled scenes of the same situation improves ranking on VSCBench for 13 of 14 models.

en
arXiv AI Papers

Do Earnings Calls Help Predict Financial Restatements? Evaluating Text Beyond Public Firm Information

Financial restatements correct errors in previously published financial reports. Could managers' language in earnings calls warn of them in advance? Comparing 109 calls that precede restatements with 218 matched control calls, we find that the text predicts restatements but adds no detectable ranking gain beyond public firm information. A text classifier beats chance, largely because of restatements tied to special-purpose acquisition companies, but a model using only public information scores slightly higher. With refitting, the 95% interval for the gain from adding text (-0.05 to 0.11 AUROC) still leaves room for a meaningful benefit. A large language model scores higher, but we show that it names the exact ticker in 66% of masked transcripts, and it was released after the restatements occurred. Our results suggest that finding new warning signs in call text requires a public-information baseline and a check of what a language model already knows.

en
arXiv AI Papers

Zero-Gated Cross-Attention

Injecting non-text modalities into frozen language models often introduces early optimization instability, making it difficult to separate architectural gains from transient training dynamics. We introduce Inductively Gated Cross-Attention (IGCA), a zero-initialized cross-attention bridge that preserves pretrained model behavior at initialization while enabling gradual multimodal conditioning. Integrated across six decoder layers of frozen Falcon-40B, open_llama_30b, and Bloom-7b1 backbones (with 40,404,961,288 trainable adapter parameters used during training), IGCA acts as an exact algebraic no-op at initialization with a maximum output discrepancy of 0.00e+00. Over 59,500 training steps on Falcon-40B, the training loss decreases from 3.9403 to 0.0007 (with final ten step losses of [0.0001, 0.0003, 0.0005, 0.0002, 0.0005, 0.0011, 0.0005, 0.0006, 0.0005, 0.0007]). On held-out evaluation, the best gate-on checkpoint achieves a loss of 2.2201 compared to 4.3469 for the gate-off baseline -- a 48.9% reduction (2.1268 nats) -- while average held-out loss improves from 4.3423 to 2.2498 (1.9075 nats) with a mean gate magnitude of {}(α){} = 0.0713.

en
arXiv AI Papers

CompSkill: Compiling Execution Experience for Skill Retrieval

LLM agents increasingly rely on skill documents, yet most retrievers rank them by description alone and ignore what earlier executions revealed, even though a relevant skill can hurt execution. We present CompSkill, which indexes skills with learned 512-d keys and compiles matched same-task comparisons into skill offsets and capped key residuals (KeyOpt), so experience changes which document the executor receives, never its text. Under a logistic outcome model with unknown task difficulty, matched comparisons cancel that difficulty and only discordant ones carry information; on support executions, predictions improve with each discordant task. An experience hypergraph keeps each comparison with its executor and document versions, recalls missed skills and grounds a cited review. Compact keys raise SkillRet NDCG@10 from 64.0 to 70.9 at one eighth of the dimension. With one document, CompSkill completes 256 and 260 of 332 ToolQA tasks with GPT-5.6-luna and DeepSeek-V4.1-Flash, respectively, more than every baseline, and stays on par with the strongest baselines on AppWorld and ALFWorld. On 332 newly generated ToolQA tasks, it completes 256 with GPT-5.6-luna, significantly more than BM25, SkillRet-8B, Tool2Vec and RankGPT; over all 844 ToolQA tasks, it completes 24 more than the strongest baseline. Selection matters beyond relevance: pairing the right guide with a same-database sibling instead of another database's guide costs 8 of 96 tasks. Code, models and support data: https://github.com/satoshinji2992/CompSkill

en
arXiv AI Papers

CogRSI: Evolving and Auditing Cognitive Reasoning Strategies

Can a language model learn better ways to reason about other people's minds by improving its own strategies, and are the strategies it learns actually right? We study this with cogrsi. A grounded reader marks who saw each event in a story and uses a short written principle to settle disagreements between its readings. With a principle written by experts, it beats self-consistency at the same token cost. A self-improvement loop then writes the principle itself. It keeps an update only if accuracy rises by a calibrated margin, and in one variant only if it also passes counterfactual test pairs. The learned principles transfer: on 800 BigToM pairs that no system had seen, each of them scores higher than the expert principle. We then check what the learned rules actually say. Each rule is translated into code and run on thousands of small stories with known answers. Most of them give a wrong answer in at least one situation they claim to cover, for example by treating a character who is in the room as knowing what happened even while asleep. Accuracy does not reveal which rules are wrong, and the counterfactual test does not fix this. A strategy can help in practice and still be wrong as a rule, so both need checking. Our code and data are publicly available.

en
arXiv AI Papers

Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation

Vision-language models can interpret instructions and plan manipulation tasks, yet struggle when acting directly as robot policies. On RoboDojo, a large planning-execution gap separates high-level task decisions from physical execution: removing arm execution raises GPT-6 Astra's success rate from 22.5% under the reference control interface to 76.2%. We present Auriga, a task-agnostic agent harness that closes 68.3% of this gap in zero-shot manipulation without target-task trials or resets. In Auriga, the model makes all task decisions over an explicit task belief and acts through either direct tool calls or synthesized multi-step Python programs, while the harness supplies calibrated 3D measurements, finger-referenced dual-arm control, and a single admission gateway to the robot. Before motion, the model inspects a visual trajectory preview while simulation is paused; during execution, the harness checks declared stage tolerances and grasp bounds, stopping the robot on divergence and returning the measured discrepancy for in-place recovery. Developed across 13 cross-task capability iterations and frozen for evaluation, Auriga ranks first on the RoboDojo leaderboard with a 57.7% success rate (64.0 Score), more than doubling the reference harness on the same model, and remains first under scene randomization while learned policies drop by up to 33.9%. On RoboCasa365, the same frozen harness reaches a 73.2% success rate, outperforming VLA-assisted agents by up to 23.1% on composite tasks. Project page: https://auriga.stelledge.com/ Code: https://github.com/lose4578/Auriga

en
arXiv AI Papers

Scute: Exact Batched Serving for PEFT Adapters Beyond LoRA

Existing serving systems for large language models batch requests for many different LoRA adapters on one GPU. However, these systems reject adapters from other parameter-efficient fine-tuning (PEFT) methods such as DoRA, (IA), VeRA and OFT. One solution to this is to convert these adapters to LoRA, but this induces a significant memory and accuracy cost. Instead, we show that, under some modifications, a batched LoRA kernel can serve all of these methods exactly and efficiently. We achieve this by writing each method in one normal form, a LoRA computation with six slots for an adapter's own vectors and matrices. Some slots can merge into an adapter's weights at load time; the others remain live and induce a cost. We give ways to efficiently pay this cost and predict it from a zero-parameter byte model. We package this system, Scute, and build it on top of vLLM. Scute serves all five methods, coming as checkpoints from the Hugging Face PEFT library, in one batch, and it matches that library with a mean error of at most 1.5% of each adapter's effect. Under a burst of requests on an RTX A6000, a mix of these methods takes 5-17% more decode time than the same number of LoRA adapters. Furthermore, using Scute, the same GPU can serve 64 to 1024 (IA) and VeRA adapters at 1.5x to at least 2.5x the request rate of their LoRA conversions.

en
arXiv AI Papers

Evidence-grounded large language models guide perovskite solar cell design and optimization

Using large language models to interpret experimental evidence, design discriminating experiments and formulate well-supported mechanistic explanations remains a central challenge in materials research. Here we establish PSM-Bench, an 800-question benchmark developed by perovskite researchers to evaluate scientific reasoning in perovskite photovoltaics. We also introduce OpenPerov, an expert-informed language-model framework that learns from expert-calibrated evidence records reconstructed from 4,532 articles; these records link experimental strategies, controls and observations to mechanistic interpretations. Structured-evidence adaptation outperformed conventional question-answer training, and OpenPerov Flash ranked first among 13 closed-book systems. OpenPerov Pro raised Scientific Mastery further, from 87.6 to 89.1, by revising selected passages with retrieved evidence. On questions derived from subsequent studies, both models also outscored expert-authored answers. In an experimental test of self-assembled monolayer design, OpenPerov selected a K analogue that outperformed the Na analogue preferred by experts. Devices incorporating the selected contact reached a power conversion efficiency of 27.05% and retained 96.74% of their steady-state reference efficiency after 1,000 h of dark thermal ageing at 85 ^. These results show that reconstructed scientific reasoning provides an effective basis for building domain models that interpret experiments and inform materials design.

en
arXiv AI Papers

TopoQuant: Topological Framework to Characterize Behavioral Shifts in Quantized Large Language Models

Post-training quantization (PTQ) reduces the com putational cost of large language models (LLMs), but it can introduce internal structural and behavioral changes that are not captured by traditional metrics such as accuracy and per plexity. We present TopoQuant, a topological framework that uses topological data analysis (TDA) to quantify structural drift in self-attention weights and relate it to behavioral changes in quantized LLMs. Across four LLM families and multiple quantization levels, we show that topological drift remains stable at moderate compression levels but increases sharply below 4 bit precision, closely tracking declines in attention agreement. Our results reveal a strong relationship between topological drift and attention agreement, indicating that structural changes in model parameters closely reflect behavioral degradation under quantization. We further demonstrate that topological features can accurately predict attention consistency using lightweight machine learning models, achieving R2 scores of up to 0.85. Predicting attention agreement enables efficient assessment of be havioral consistency in quantized LLMs, allowing quantization induced degradation to be detected without running expensive downstream tasks. The results indicate that topological drift pro vides an efficient early-warning signal for quantization-induced degradation and can help identify safe compression limits without extensive downstream evaluation.

en
arXiv AI Papers

Log-Driven Semantic Tuning for Mixed Integer Programming Solvers

Automated configuration of mixed-integer programming (MIP) solvers largely relies on black-box optimization. Each trial requires an expensive solver run and provides only a scalar outcome, so tuning can require many such evaluations. Human experts take a different approach. They inspect solver logs, identify performance bottlenecks, and adjust the parameters that address them. We propose Log-Driven Semantic Tuning (LDST), which uses a large language model (LLM) to automate this process. LDST extracts compact diagnostics from solver logs, uses the LLM to propose sparse edits to the current best configuration based on parameter meanings and observed solver behavior, and validates each proposal before execution. A regime-adaptive objective selects the tuning signal according to the information available from a time-limited run, while a log-based completion signal estimates completion time from branch-and-bound tree growth recorded in ordinary solver logs, so that solved and unsolved runs share one time scale. On 215 instances from five benchmark sets, LDST reduces geometric-mean loss by 43.9% on easy instances and 16.7% on intermediate instances relative to the best of SMAC3, RBFOpt, and random search. In both regimes, LDST achieves a lower loss with 10 proposals than any of these baselines achieves with 50. Configurations that LDST tunes on a single instance also transfer better than baseline configurations to unseen instances of the same family.

en
arXiv AI Papers

Discovering Models for Experimental Quantum Systems with Agentic AI

A central obstacle in realizing color center cavity-QED-based quantum technologies is inhomogeneity, or disorder, among individual emitters. As the number of emitters increases, so does the complexity of the experimental data, making it difficult to quantify the present physical mechanisms of disorder. Here we introduce an artificial intelligence-driven model discovery framework in which a large language model (LLM)-based agent, equipped with tools and a structured workflow, proposes candidate Hamiltonian and Lindbladian models, generates computational tools, and quantitatively evaluates competing physical hypotheses. We apply the workflow to three previously published experimental cavity-QED datasets collected from color centers in diamond and silicon carbide. Across the experiments, the agent successfully identifies physical models for the system and characterizes the disorder. In assessing reproducibility, we find that run-to-run variability is concentrated primarily in the research plan generation step, while the computational analysis itself is substantially more consistent. Our results suggest that structured LLM agent workflows can support model discovery from quantum optical experimental data while simultaneously allowing for human expert supervision and collaboration.

en
arXiv AI Papers

Enhancing Language Model Reasoning with Structured Multi-Level Modeling

Inference-time scaling enhances a model's reasoning by extending its chain-of-thought (CoT). However, existing approaches typically rely on a single policy trained with outcome-reward reinforcement learning (RL), which often suffers from long-horizon plan failures where the implicit plan drifts from valid strategies, especially for small LMs with limited capacity. To address this, we propose Multi-Level Reasoning (MLR), which reformulates long-CoT generation as a two-level stochastic process. A high-level planner generates structured step descriptors specifying both the reasoning mode and the semantic subgoal. The low-level executor then produces detailed reasoning conditioned on these descriptors, forming an alternating plan--execute loop. To maintain scalability, we adopt a minimal design where the base model serves as the low-level policy and a lightweight LoRA module implements the high-level policy. For training, we observe that outcome-reward RL provides sparse and delayed feedback for long trajectories (e.g., several thousand tokens), hindering credit assignment. We therefore introduce iterative Step-DPO, a process-level preference optimization scheme that leverages Twisted Sequential Monte Carlo (TSMC) to provide scalable stepwise supervision. This yields more effective training, improved stability, and higher accuracy. Extensive experiments on challenging math, science, and logical reasoning benchmarks show that, under the same reduced data budget (10% SFT and 5% preference relative to the DeepSeek-R1 distillation setup), MLR outperforms both SFT-based distillation and strong RL/preference-optimization baselines across multiple base models and tasks. Moreover, MLR exhibits slower performance degradation on long-horizon reasoning, demonstrating stronger robustness under extended CoT generation.

en
arXiv AI Papers

Trail: Accurate Local Smart Home Control Using Decision Models

Natural-language driven smart home control remains challenging: cloud-hosted Large Language Models (LLMs) raise privacy concerns, while local Small Language Models (SLMs) can generate invalid actions or misinterpret requests. We introduce Trail (Typed Registry-Anchored Inference for Language commands in Smart Homes), a fully local framework that replaces open-ended command generation with hierarchical typed decisions. Trail exploits the natural structure of a home's action space, selecting a room, device, and operation from candidates derived from the runtime device registry. This ensures valid actions while enabling confidence-based abstention when requests cannot be reliably resolved. We also design a structured memory module that uses typed decisions to support user preferences, device references, and multi-turn interactions. To evaluate Trail, we extend HomeBench and generate three datasets: Trek-Base, which tests natural-language variation; Trek-Robust, which evaluates robustness to changes in the home and its description; and Trek-Memory, which assesses conversational memory across multi-turn interactions. Trail achieves 85.3% accuracy on Trek-Robust versus 69.8% for a finetuned Qwen3.5-4B baseline, while remaining competitive on Trek-Base requests. With memory, Trail resolves 75.6% of the requests that depend on earlier turns, compared with 42.5% for the finetuned baseline given conversation history.

en
arXiv AI Papers

Words Before Pixels: Selective Modality Routing for Vision-Language Model Unlearning

Vision-language model (VLM) unlearning is often treated as an objective-design problem: given multimodal forget data, the goal is to optimize a loss that removes undesirable behavior while preserving retained capabilities. We argue that this view overlooks an equally important data-centric question: how should each forget example be represented before optimization? Existing methods typically keep image-conditioned failures in their original image-text form, implicitly assuming that pixels are the right route for unlearning whenever pixels appear in the input. We challenge this assumption by constructing modality-decomposed versions of VLM benchmarks, enabling controlled comparisons among image-only, text-only, and multimodal representations of the same examples. Our modality-mixing experiments show that unsafe instruction-following behavior is more effectively suppressed through textual representations than through images alone, while purely text-only unlearning can still weaken visual grounding when the target behavior depends on visual evidence. Motivated by this trade-off, we introduce ModRoute, a gradient-guided per-sample modality routing strategy that selectively converts high visual-pressure examples to text-only form while keeping the remaining examples multimodal. Notably, on VLGuard with LLaVA-1.5-7B, ModRoute has the strongest composite unlearning-utility score of 0.847 at γ=0.5, a 2.5% improvement over the best random-switching score and 46% better than pure multimodal or text unlearning. Overall, our results show that effective VLM unlearning depends not only on the objective, but also on the composition and per-sample modality routing of the unlearning data.

en
arXiv AI Papers

Conversational Interaction for LLM-Based Clinical Text-to-SQL: A User Study with Healthcare Professionals

Conversational text-to-SQL interfaces could give healthcare professionals natural-language access to electronic health record (EHR) data, but evidence for their real-world usability remains limited: prior evaluations have relied largely on curated benchmarks with fully specified questions or on simulated users. We report a user study in which 14 physicians who regularly work with EHR data used both a single-turn and a conversational multi-turn text-to-SQL interface over the MIMIC-IV database in a within-subjects design; dialogue analyses additionally drew on interaction logs from 21 healthcare professionals across the main study and two pilot studies. The conversational interface was consistently favored: mean System Usability Scale scores rose from 68.2, near the industry average, to 85.9 (p<0.001), with significant advantages across technology-acceptance constructs including performance expectancy, effort expectancy, self-efficacy, and behavioral intention. In post-study forced-choice comparisons, 93% of participants reported greater overall satisfaction with the conversational interface, 86% preferred it for real-world adoption, and 71% trusted its results more; no participant preferred or trusted the single-turn interface more. Turn-level analysis of 425 logged user turns showed that freely composed queries triggered clarification requests in 24.8% of cases versus 1.8% for predefined, fully specified questions, and 64.3% of clarification episodes stemmed from EHR- or clinical-domain knowledge. Conversational interaction is a practical prerequisite, rather than a convenience, for natural-language EHR access. The frequent need for clarification in realistic clinical queries further underscores the importance of conversational interfaces, while benchmark-style evaluation can substantially underrepresent the ambiguity of real clinical use.

en