跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 13:24 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 14:03 — 2026-11-09 14:03（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 13:24最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 3,653 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 13:22（北京时间）
版本更新 · v5arXiv:2512.07901

The Theory of Strategic Evolution: Three Principles of Strategic Replicators

Kevin Vallier

原文摘要

Strategic replicators combine evaluated choice and reproductive transmission. An agent chooses among alternatives; the consequences of those choices influence continuation or reproduction; and successors receive organization that shapes later choices. Artificial intelligence makes this combination salient when agents have authority to create, configure, or retire software instances. This paper organizes the general logic around three principles: situated choice, reproductive transmission, and institution-mediated coupling. The principles are constitutive rather than predictions of growth or improvement. A common representation distinguishes carriers, inherited records, decision owners, and the mechanisms that allocate consequences. Actual parent-descendant attribution yields a selection-transmission identity. Separate compatibility results characterize when utility-maximizing choices also maximize a reproductive criterion. Gode and Sunder's zero-intelligence traders reveal the role of institutions: enforced properties can hold across different decision procedures, while aggregate efficiency alone determines neither individual gains nor descent. A worked market-rent-entry model connects institutional profits to actual offspring, with its occurrence-level ancestry bridge checked in Lean. A direct-deployment example then shows evaluated preferences undergoing selection without presupposing that every chooser values reproduction. Formal appendices develop games with endogenous players, deployment-induced tipping, endogenous electorates, and the production of institutions, with models, proofs, and examples. The paper and its supporting formal artifacts are a prototype kernel with a generative function: an instrument for constructing models of strategic replication. The results are formal; their application to deployed populations and their empirical implications remain to be tested.

cs.GT · cs.AI · cs.CY · cs.MA · econ.TH

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36386

LoRA on a Budget: Function-Aware Post-Hoc Compression for Adapter Fleets

Shenghui Li, Thiemo voigt

原文摘要

Low-Rank Adaptation (LoRA) has become a key mechanism for efficiently specializing foundation models into many task- and user-specific variants. Serving many LoRA adapters under a shared resource budget turns post-hoc compression into a two-level allocation problem: rank must be distributed across layers within each adapter and across adapters within the fleet. Although trained LoRAs contain substantial spectral redundancy, spectral reconstruction alone does not determine how much compression an adapter can functionally tolerate. We formulate fleet compression through a functional rank-distortion frontier for each adapter, followed by fleet-level minimax allocation under a shared rank budget. Given exact frontiers, this decomposition is equivalent to joint optimization over all layer ranks. We introduce Functional Rank Allocation (FRA), an unlabeled method for constructing practical frontiers. FRA measures isolated module truncations end to end, uses these measurements as an additive search surrogate solved by dynamic programming, remeasures every complete candidate, and takes the lower-risk envelope with a complementary spectral proposal before exact minimax allocation over the constructed frontiers. Across 78 adapters from three public fleets, FRA improves worst-case and tail utility over uniform spectral compression in constrained-budget regimes. Fixed-budget probes show that isolated costs rank candidates well, but their calibration shifts across proposal shapes; end-to-end verification and the spectral proposal therefore limit functional-search error.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36384

SOMA: A Benchmark for Fine-Grained Egocentric Behavior and Body-Motion Understanding

Matea Tashkovska, Naël Ouerghemi, Haozhe Qi, Alexander Mathis

原文摘要

Perceiving human body motion is critical for multimodal systems that understand and assist people. Yet current evaluations of Multimodal Large Language Models (MLLMs) largely focus on objects, scenes, and coarse actions, leaving their ability to reason about the body itself poorly assessed. This is especially challenging from the egocentric perspective, in which the body is only partially visible and motion must be inferred from occluded and temporally distributed cues. We introduce SOMA, a benchmark for fine-grained body-motion understanding from egocentric video, comprising 1,632 human-verified questions across three capability axes: body configuration, motion dynamics, and temporal reasoning. We evaluate 37 leading closed-source, open-source, and specialized egocentric MLLMs, complemented by an extensive human evaluation. We find that humans also find this task difficult from video alone (68.5% accuracy), yet clearly outperform the strongest MLLM (Qwen3.6-27B), which reaches 50.0% zero-shot accuracy. Our error analysis shows that MLLMs often misread the wearer's own body, misjudge events in time, and are prone to biases such as favoring the right hand or under-counting repetitions. To narrow the gap to human performance and support further progress, we introduce a training dataset of aligned video, body motion, and language supervision, and a multimodal baseline that jointly learns from these modalities. By identifying common failure modes and missing capabilities in current MLLMs, we hope SOMA will inspire future research on body-motion understanding and multimodal reasoning. Full benchmark, training data, and code will be released at: https://cnai.epfl.ch/soma

cs.CV · cs.AI · cs.CL · q-bio.NC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.25147

TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems

Qingyun Liu, Bo Yan, Yang Liu, Yuji Roh, Ekansh Sharma, Likang Yin, Emma Olowo, Yuxuan Li 等 19 位作者

原文摘要

User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints due to fixed-dimensional vectors. As an emerging alternative for discrete user representation, LLM-generated natural-language user profiles often capture language semantics rather than sequential patterns in user behaviors. Meanwhile, Semantic ID (SID) is effective for item representation, yet existing discrete user representations remain largely confined to quantizing already-pooled user vectors, clustering historical watches, or predicting coarse topic clusters solely for candidate retrieval. We propose TokenMinds, an industrial system that extends the PLUM framework from SID-based item retrieval to generative sequential user modeling. Built on an encoder-decoder architecture adapted from pretrained LLMs, TokenMinds introduces a dual-output design: the encoder outputs a dense user embedding capturing a holistic user state, while the decoder generates discrete SID-based user tokens representing multi-faceted future interests. Grounded in item semantics, these tokens preserve distinct interests that a single pooled vector would average away. Additionally, a shared SID vocabulary across long- and short-form videos unifies cross-scenario behaviors into a single model, cutting upstream training and serving compute by 50% and 31%. Furthermore, leveraging the text vocabulary inherited from the pretrained LLM, TokenMinds interleaves textual search queries directly with watch histories to capture explicit user intent. We validate TokenMinds through offline evaluations and live A/B experiments across YouTube's primary ranking surfaces, serving billions of users asynchronously: SID-based user tokens are effective on their own, yield additive gains alongside dense embeddings, and together outperform the previous-generation, non-LLM user model in production.

cs.IR · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36374

HIDRA: Hierarchical Dual-Routing Attention for Replay-Free Lifelong Imitation Learning

Fanqi Yu, Matteo Tiezzi, Cigdem Beyan, Tommaso Apicella, Vittorio Murino

原文摘要

Robotic agents operating in real-world environments must adapt continuously from a stream of multimodal demonstrations, often under constraints that preclude storing or revisiting past data. In this replay-free, single-pass lifelong imitation learning setting, sequential updates can progressively distort the representation space, making expert-based approaches particularly sensitive to routing interference, causing expert selection to degrade over time. We propose HIDRA, a structured routing framework that mitigates this issue through a hierarchical dual-attention mechanism, which decouples instruction-level expert retrieval from context-dependent refinement. To further stabilize routing under representation drift, HIDRA introduces a key-level geometric regularization that enforces both alignment within tasks and separation across tasks. The resulting approach enables reliable expert selection while supporting an expandable set of experts for continual adaptation. We evaluate HIDRA on several LIBERO benchmark suites, including more challenging variants with heterogeneous task sequences and paraphrased language instructions. Our approach consistently outperforms both replay-free and replay-based baselines, improving AUC and forward transfer while maintaining low forgetting, with stronger gains under high interference and language variation. The code is available at: https://github.com/yfqi/HIDRA.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.17709

Where Small Mistakes Matter: Quantifying State Criticality for Imitation Learning

Yusuf Umut Ciftci, Joonwon Kang, Ajay Suresha Sathya, Somil Bansal

原文摘要

Imitation learning typically treats every demonstration state as equally important, optimizing a behavior-cloning objective uniformly across the dataset. Yet not all states are created equal: in a small number of critical states, even a slight deviation from the expert action can lead to a failure, while in many other states such errors are recoverable and inconsequential. We formalize state criticality in imitation learning as the worst-case degradation in downstream value induced by a bounded perturbation of the expert action at a given state. We then propose SCRIM, a practical State CRIticality Measure that estimates this quantity by training an adversarial disturbance policy and a value critic around a fixed imitation policy. SCRIM assigns each demonstration state a score reflecting how vulnerable the task outcome is to small, policy-relevant action errors. We show that these scores can be used to reweight behavior-cloning losses, improving imitation at consequential states and increasing overall task performance. We further show that SCRIM enables data curation by selecting compact, high-value subsets of demonstrations that preserve performance while substantially reducing the amount of training data. We evaluate SCRIM across various simulated and real-world robotic manipulation tasks, and demonstrate that SCRIM improves policy training, enables efficient data selection, and provides interpretable insights into which moments in a demonstration are most critical for task success. Project website: https://sia-lab-git.github.io/SCRIM/

cs.LG · cs.AI · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.31810

PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean

Jiyuan Tan, Jose Blanchet, Vasilis Syrgkanis

原文摘要

Even a carefully proofread paper can leave small gaps in its proofs or its stated assumptions. We introduce PaperFormalizer, a Lean-based agentic pipeline that helps authors find and close such gaps in their own papers and turn each paper into a Lean-verified version. Starting from the LaTeX source, PaperFormalizer transcribes the paper into a dependency graph of statements, audits each statement in natural language for faithfulness, ambiguity and correctness, and then formalizes and proves the statements in Lean against Mathlib, optional domain libraries and the author's personal toolkit. Only the author knows what a statement is meant to say and how a formalization gap in a result is best fixed. The pipeline therefore stops and asks the author whenever a statement admits more than one reading, presents every repair, in natural language and TeX symbols, as a proposal that the author can accept, decline or redirect, and leaves to the author every decision that could potentially change what the paper claims. The output is an annotated and revised version of the paper, a report of the changes, and Lean code in which each declaration is linked to the statement it formalizes. The author's toolkit grows as more papers are formalized, and authors can share their verified papers so that researchers who build on them can reuse their Lean code. By making verified papers practical to produce, PaperFormalizer aims to make research that rests on mathematical proofs more robust. PaperFormalizer runs inside a coding agent (Claude Code or Codex) and is available at https://github.com/Jiyuan-Tan/PaperFormalizer. Papers with Lean code shared by users are available at https://paperformalizer.org.

cs.AI · cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.02141

On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization

Kaixuan Ji, Qiwei Di, Heyang Zhao, Qingyue Zhao, Quanquan Gu

原文摘要

Kullback-Leibler (KL) regularization is widely used in offline decision-making and offers several benefits, motivating recent work on the sample complexity of offline learning with respect to KL-regularized performance metrics. Nevertheless, the exact sample complexity of KL-regularized offline learning remains largely from fully characterized. In this paper, we study this question in the setting of multi-armed bandits (MABs). We provide a sharp analysis of KL-PCB (Zhao et al., 2026), showing that it achieves a sample complexity of $\tilde{O}(ηSAC^{π^*}/ε)$ under large regularization $η= \tilde{O}(ε^{-1})$, and a sample complexity of $\tildeΩ(SAC^{π^*}/ε^2)$ under small regularization $η= \tildeΩ(ε^{-1})$, where $η$ is the regularization parameter, $S$ is the number of contexts, $A$ is the number of arms, $C^{π^*}$ policy coverage coefficient at the optimal policy $π^*$, $ε$ is the desired sub-optimality, and $\tilde{O}$ and $\tildeΩ$ hide all poly-logarithmic factors. We further provide a pair of sharper sample complexity lower bounds, which matches the upper bounds over the entire range of regularization strengths. Overall, our results provide a nearly complete characterization of offline multi-armed bandits with KL regularization.

cs.LG · cs.AI · math.ST · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36363

Reliability-Aware Short-Term Glycemic Risk Prediction Using an Anchor-Based Comparative Framework of Sequence, Multimodal, and State-Updating Digital-Twin Models

Pir Bakhsh Khokhar, Carmine Gravino, Fabio Palomba

原文摘要

Anticipating short-term hypoglycemic and hyperglycemic risk is essential for proactive diabetes management. However, existing machine learning approaches often use inconsistent evaluation protocols and emphasize predictive performance over reliability. This study introduces an anchor-based benchmarking framework integrating longitudinal glucose sequences and multimodal patient information. Using the T1DiabetesGranada dataset, 5,503,441 standardized prediction anchors were constructed from 736 individuals with type 1 diabetes to evaluate hypoglycemia and hyperglycemia prediction at 30-, 60-, and 120-minute horizons. Three neural architectures, a Hybrid LSTM-Transformer, a Multimodal Digital Twin, and a State-Updating Digital Twin with gap-aware longitudinal state progression, were compared under identical patient-level validation protocols. Beyond predictive performance, the evaluation examined calibration, classification thresholds, explanation reliability, cross-model disagreement, and robustness to controlled perturbations. No statistically significant predictive differences were observed after Holm correction, although the models exhibited complementary reliability characteristics. The Multimodal Digital Twin achieved the lowest mean Brier score, while the State-Updating Digital Twin demonstrated the lowest mean expected calibration error (ECE-10). The Hybrid LSTM-Transformer showed strong explanation faithfulness and stability under its temporal attribution protocol. These findings highlight the importance of evaluating digital-twin models beyond predictive accuracy and emphasize the need for reliability assessment and external validation before clinical deployment.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.14708

Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition

Yecheng Wu, Song Han, Han Cai

原文摘要

A core goal of efficient reasoning is to improve the accuracy-efficiency frontier. However, jointly improving reasoning accuracy and inference efficiency can be challenging, as the two objectives can favor different reasoning behaviors. Independently post-trained models already offer distinct strengths in accuracy and efficiency. We introduce Lightning Weave, a post-training framework that extracts and composes these independently learned capabilities in a single student through on-policy distillation. Each acquired capability is represented by the policy shift from the model before post-training to the resulting specialist. Lightning Weave combines aligned log-ratio shifts at shared student token states and uses Tilted-Target DOPD to convert the cached signals into a stable learning target. Each anchor pair scores the cached trajectories once, enabling subsequent student training without serving multiple live anchor models concurrently. Across diverse student models and benchmarks in mathematics and code, Lightning Weave substantially improves upon the base students and achieves a state-of-the-art accuracy-efficiency frontier. On Qwen3.5-4B, it raises HMMT 2025 accuracy from 59.2% to 64.0% with 10.7% fewer response tokens, and LiveCodeBench v5 accuracy from 41.7% to 54.2% with 9.6% fewer response tokens. Adjusting the relative strengths of the anchor signals yields a strong empirical accuracy-efficiency Pareto frontier. These results establish Lightning Weave as a new practical route to efficient reasoning through capability composition. Code is released at https://github.com/jet-ai-projects/Lightning-Weave.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36355

WAKMan: Workload Aware KVCache Manager

Suhas Kumar Morisetty, Vaibhavi Lokegaonkar, Sachin Mathew Varghese, Wesley Harris

原文摘要

Prefix caching enables a Large Language Model (LLM) servers to reuse the Key-Value (KV) states and accelerate prefill computation stage for requests that share a prefix with earlier prompts, thus reducing latency and serving cost. With limited memory resource, the KV cache eviction policy becomes a decisive factor in determining the overall benefits of prefix caching. Production traffic may have single-turn, multi-turn, agentic, or a mixture of any combination of these request types. Our findings indicate that agentic steps return within seconds and favor recency, while popular prompts and long conversations return after many other requests and favor frequency. Across 20 mixes, no single policy is always best: vLLM's default strategy LRU provides 12% higher cache hits as compared to the frequency-oriented S3FIFO on agentic-heavy mixes but trails it by up to 22% elsewhere, and even a single workload parameter can flip the winner even for any particular mix. We present WAKMan, a workload-aware KV cache manager that picks its eviction policy from live traffic without knowing request types or reading prompts. It improves hit rate over LRU by 5 percentage points on average, with the lowest mean and worst-case optimality gap of all policies.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.17700

MIDAS: Mosaic Input-Specific Differentiable Architecture Search

Konstanty Subbotko

原文摘要

Differentiable Neural Architecture Search (NAS) provides efficient, gradient-based methods for automatically designing neural networks, yet its adoption remains limited in practice. We present MIDAS, an approach that modernizes DARTS by replacing static architecture parameters with dynamic, input-specific parameters computed via self-attention. To improve robustness, MIDAS (i) localizes the architecture selection by computing it separately for each spatial patch of the activation map, and (ii) introduces a parameter-free, topology-aware search space that models the two-edge node topology during search. We evaluate MIDAS on the DARTS, NAS-Bench-201, and RDARTS search spaces. In DARTS, it reaches 97.42% top-1 on CIFAR-10 and 83.38% on CIFAR-100. In NAS-Bench-201, it discovers optimal or near-optimal architectures. In RDARTS, it achieves the best reported performance among the compared methods on two of four search spaces on CIFAR-10. We further analyze why MIDAS works, showing that patchwise attention improves discrimination among candidate operations and that the resulting input-specific parameter distributions are class-aware.

cs.LG · cs.AI · cs.NE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36344

Enhancing Clinical Classifier Robustness with Deep Representation Learning Based OOD Detection on DNA Methylation Data

Md Zahangir Alom, Quynh T. Tran, Breuer Alexandar, Brent A. Orr

原文摘要

DNA methylation (DNAM) array-based tumor classification is a powerful clinical diagnostic tool, but models trained on fixed reference cohorts can produce faulty predictions for tumor types not represented in the training distribution. We propose an end-to-end deep representation learning-based out-of-distribution (OOD) detection framework for DNAm array data. Deep neural network (DNN) classifiers were trained on public sarcoma (SARC) (GSE140686) and brain tumor (BT) (GSE90496) cohorts, and feature vectors were extracted from bottleneck layers. Five OOD methods, including 1dimension (1D)-Subspace Analysis (1D-SSA), K-Nearest Neighbors (KNN), Ridge Regression, Mahalanobis Distance (MD), and Sum of Squared Distances (SSD), were explored with 200 and 500-dimensional embeddings. Spectral discrepancy was used to discriminate in-distribution (IND) from OOD samples. Performance was measured via cross-validation, holdout samples, and an independent clinical dataset. 1D-SSA was the most effective approach. In the sarcoma-IND/brain tumor-OOD setting, the framework achieved an AUROC of 0.975 and True Negative Rate (TNR)@95TPR of 0.930, and an AUROC of 0.9569 and TNR@95TPR of 0.8660 for the brain tumor-IND/sarcoma-OOD setting. On the independent clinical test set, the method yielded a mean AUROC of 0.976, a DE of 0.032, an FPR@95TPR of 0.065, and a TNR@95TPR of 0.935. These results show deep representation-based OOD detection as a practical quality-control layer for clinical-grade methylation-based tumor classification systems.

q-bio.GN · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36341

Executable Archaeology of Programs That Model Programming: Reanimating the Heuristic Compiler (1961) and KBEmacs (1984)

Jeff Shrager, Kent M. Pitman, Mia Golec

原文摘要

Early AI programs were often also theories of how people think, and programs that wrote programs were, in part, theories of how people program. Here we report on the reanimation of two such programs that offer two seemingly different theories of programming and were developed for quite different purposes. The first, Herbert Simon's Heuristic Compiler (1961), was an experimental model of programming as problem-solving, applying the means-ends analysis methods of the General Problem Solver to investigate the nature of the programming task. The second, KBEmacs (1984), was a working prototype of an intelligent programming assistant developed by MIT's Programmer's Apprentice project, built on the view that expert programmers recognize and combine familiar patterns, or "cliches." It let a programmer build up programs by combining cliches through a stylized English command language. We approach both through the methodology of Executable Archaeology, the study of historical computational systems by running their original code, a process we call "reanimation." Our reanimation of the Heuristic Compiler reproduces the compiled code appearing in Simon's 1963 paper, and our reanimation of KBEmacs reproduces the SQRT sequence of its December 1984 self-test. Examined side by side, the two theories turn out to have much in common: the Heuristic Compiler also works by adapting existing routines, and Simon later argued that search alone requires a large body of programming knowledge. To highlight the reflexivity of this project, we deliberately used a modern AI-assisted programming tool, Anthropic's Claude Code (Opus 5.5), to carry out much of the detailed reanimation work, building on a significant base of existing software. The explicit, executable theories of programming that both systems embodied are largely absent from today's far more capable AI coding assistants.

cs.AI · cs.HC · cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36335

OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning

Hui Yang, Jiaoyan Chen, Yongsheng Gao

原文摘要

Large language models (LLMs) perform well across many real-world tasks but remain prone to hallucination, limiting their reliability in domains such as biomedicine and healthcare, where answers must be grounded in established knowledge. Retrieval-augmented generation (RAG) mitigates this problem by incorporating external information, but often overlooks logical relationships and relies heavily on the LLM's own reasoning, which can compromise answer faithfulness. We propose OA-RAG, an agent that integrates formal reasoning with LLM reasoning, drawing on both the logical structure and informal annotations of domain ontologies. For each answer, OA-RAG reports the ontology observations used as evidence and a model-assessed grounding level (entailed, supported, related, or unrelated) that characterises the strength of that evidence. Across benchmarks derived from three large-scale ontologies and six real-world medical question-answering tasks, OA-RAG achieves the best overall performance among the evaluated ontology-fine-tuned and popular RAG methods, with particularly strong results on reasoning-intensive tasks. The reported grounding levels also offer a useful indication of answer reliability, with stronger grounding generally associated with higher accuracy. Finally, our results demonstrate the value of ontologies as knowledge sources: OA-RAG is competitive with, and sometimes outperforms, domain-specific RAG systems that draw on sources such as textbooks.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36329

Plenty of Room in the Middle: Revealing Opportunities on a GPU Cluster via Fine-Grained Monitoring

Andrew Sheinberg, Samyak Gupta, Kai Li

原文摘要

GPU clusters have become essential computing resources for AI and scientific research in academia and industry. However, their high cost and growing demand often result in long queueing delays. While previous monitoring efforts have operated at second- or minute-level frequencies, they primarily informed job-level scheduling for clusters and lacked the detail needed to optimize GPU-level utilization. This paper presents an in-depth study of a university research GPU cluster, analyzing resource usage at 100 ms intervals. We have developed a lightweight monitoring tool that leverages Nvidia's DCGM library to capture fine-grained "compute utilization" metrics within GPUs. Deployed on a cluster with 89 nodes and 319 GPUs, our tool collected data over several months. This paper focuses on a 10-day period with 7,399 jobs submitted by 150 users from 12 departments. Our study reveals three key findings: (1) the GPU cluster exhibits significant underutilization, with over 70% of jobs using less than 20% of GPU memory and 50% averaging below 5% Streaming Multiprocessor (SM) utilization; (2) 80% of jobs have a drastic mismatch between their requested and actual durations, significantly limiting the scheduler's effectiveness; and (3) the multi-GPU jobs we examined show highly periodic communication patterns. These findings suggest there is plenty of room in the middle: substantial utilization gains are available through better job scheduling and GPU multitasking, independent of hardware or application improvements. Our monitoring solution is available as open-source software at https://github.com/als244/gpu_server_monitoring.

cs.AI · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36328

How Stable Are LLM-Generated Proofs Under Program Refactoring? A Stress Test for Verifiable Code Generation

Aravind Mandiga, Guoming Li

原文摘要

Benchmarks for verifiable code generation usually test a proof against one fixed implementation. We ask whether the same proof remains valid after a program refactoring that preserves behavior. We introduce RefactorProof, which derives 458 Lean-certified variants from the 185 VERINA tasks that compile in our pinned environment while holding the specification and evaluated proof fixed byte-for-byte. VERINA supplies reference proofs for 46 tasks, all from its basic split; the primary model-versus-reference comparisons further match on 21-25 short, non-recursive tasks. Structural refactorings expose substantial brittleness across proof sources: task-normalized structural PSR is 4.3% for the supplied references and 13.3-26.8% for the specialized provers. On the matched tasks, specialized prover proofs nevertheless have higher overall unchanged-proof survival than the supplied reference artifacts: +15.6 points for DeepSeek-Prover-V2-7B, +18.8 for Goedel-Prover-V2-32B, and +20.3 for Goedel-Prover-V2-8B; all three 95% CIs exclude zero. The ordering persists after excluding universally survived T1 variants, under family-balanced aggregation, and under alternative deployable valid-proof selection rules. However, unchanged-proof failure is not the same as high repair cost: predefined one-identifier edits repair 51/54 eligible reference structural failures and 58/85 eligible prover failures. RefactorProof therefore measures unchanged-proof stability under program refactoring, not the cost of maintaining a proof after it breaks.

cs.AI · cs.LO · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36325

Ontology-guided multi-agent reasoning for explainable differential diagnosis

Roxana Ramona Szomiu, George Ursu, Adrian Groza

原文摘要

Effective differential diagnosis depends on well structured and unambiguous patient case descriptions, since incomplete or ambiguous clinical information readily leads to diagnostic errors and inconsistent reasoning. Large Language Models (LLMs) have recently shown promising capabilities in medical question answering and clinical reasoning; however, even when achieving competitive performance on medical benchmarks, they often rely on pattern recognition learned from training data rather than grounded clinical evidence, and can generate plausible yet unsupported diagnostic conclusions. Their reasoning remains largely opaque, making it difficult for clinicians to assess the evidence and rationale behind a given recommendation. To address this gap, we propose an ontology-guided, multiagent differential diagnosis framework that replicates the iterative reasoning process of physicians. The framework grounds diagnostic inference in a structured, expert-curated medical knowledge base, enabling interpretation of symptoms, clinical findings, or disease relationships, while decomposing diagnosis into explicit, auditable reasoning steps. This ontology-based grounding constrains inference to evidence-backed associations, reducing hallucination and improving diagnostic transparency, traceability, and consistency. The system then identifies the most discriminative missing symptoms and generates targeted follow-up questions to reduce uncertainty through a process that mirrors to clinical inquiry. Together, these components improve the reliability, explainability, and diagnostic accuracy of AI-assisted differential diagnosis. The source code is publicly available.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.25687

From Deterministic to Generative Deep Learning for Urban Air Quality Reconstruction from Sparse Observations

Abhishek A. Sabnis, Mihai Mitrea, Lya Lugon, Karine Sartelet, Marc Bocquet, Xiaoyuan Cheng, Shupeng Zhu, Sibo Cheng

原文摘要

Full-field reconstruction of air pollution is essential for evaluating pollution exposure and supporting public health decision-making. However, the complex interactions among pollutants, hard-to-predict weather patterns, and limited monitoring station coverage make this a complex task. We apply deep learning techniques to provide fast and accurate reconstructions from sparse observations of four key pollutants: NO2, O3, PM2.5 and PM10. Models are trained on full-field simulation data and evaluated on real-world observations collected from 9 to 28 monitoring stations in the city of Paris. We introduce a diffusion-based generative framework for multi-pollutant reconstruction and benchmark its performance against deterministic deep learning models. Despite noisy observations and strong spatial variability, the models achieve high structural similarity on simulated validation data and produce realistic spatial patterns on real-world observations, as indicated by power-spectrum analysis. We introduce data augmentation methods that enable transfer to real-world observations without retraining, allowing the models to generalise beyond the training period. These findings highlight the potential of ML models for reliable real-world deployment in air pollution reconstruction tasks.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.27860

From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentation

Rit Gangopadhyay, Alex Wong

原文摘要

Vision foundation models are capable of generalizing across 3-dimensional (3D) scenes with high-fidelity estimates; their empirical success can be attributed to training on large-scale datasets of perspective images. However, when transferred to wide field-of-view (FoV) images, such as those captured by fisheye cameras, they return erroneous outputs due to a covariate shift stemming from the radial distortion on the image pixels. We propose a method to generalize vision foundation models to fisheye cameras. The crux of our method lies in a set of learnable parameters, termed Distortion Extenders (DEX), that model the fisheye distortion coefficients and the distributional shift between fisheye and perspective images encoded in the latent space. By minimizing a self-supervised alignment loss, DEX transforms the latent embeddings of fisheye images to resemble those of perspective images to recover high-fidelity estimates. DEX is architecture- and task-agnostic: We demonstrate DEX on monocular depth estimation and open-vocabulary segmentation for convolution- and Transformer-based architectures, where we consistently improve over baselines across indoor and outdoor fisheye datasets. As a byproduct, the activations of DEX can also be decoded to distortion coefficients to support camera calibration. Code available at: https://github.com/Suchisrit/DEX.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36308

When Retrieval Is Not Enough: Obsolete Facts in Agent Memory

Oleeviya Babu Poikarayil, Tony Basil Babu, Abdulrahman Nahhas, Het Darshan Mehta, Jawid Ahmad Baktash, Ernesto William De Luca, Klaus Turowski

原文摘要

Memory-agent benchmarks often collapse retrieval and answer generation into one score, making it hard to tell whether a failure comes from missing an update or from not using an update that was already retrieved. We examine this distinction on the single-hop FactConsolidation task of MemoryAgentBench. With Qwen2.5-7B-Instruct on 6K-history BM25 accuracy drops from 45% to 32% when the retrieved evidence budget grows from 64 to 512 tokens, even though a gold-assisted post-hoc audit finds the newest statement in every retrieved set. Most of the errors occur on questions that also contain an obsolete statement version. Under a frozen prompt and equal four-statement evidence size, replacing one unrelated statement with the obsolete competing statement reduces accuracy from 100% to 44.6% for Qwen2.5 and from 100% to 87.8% for Qwen3-14B, with all 50 harmful paired flips classified as stale. A 32K-history replication likewise favors BM25-64 over BM25-512 (69% versus 58%). These results suggest that retrieving the correct fact is not enough. An obsolete competing statement can be more harmful than an unrelated piece of evidence of the same size.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36298

Spiking Neural Networks Are Harder to Steal: A Benchmark Study of Model Stealing Attacks

Ayana Moshruba, Maryam Parsa

原文摘要

Machine learning models deployed behind query interfaces expose more than their predictions, because an adversary can use those predictions to rebuild the model itself. Model stealing attacks (MSAs) exploit this exposure by training a surrogate model that replicates the decision behavior of a target through black-box queries alone, without access to its parameters or training data. These attacks are well characterized for conventional artificial neural networks (ANNs), yet spiking neural networks (SNNs) process information in a fundamentally different way. SNNs communicate through sparse, discrete spikes, and their outputs depend on membrane potentials that evolve over time rather than on a static mapping from input to output. This temporal mode of computation suggests that the decision behavior of an SNN may be harder to reconstruct from its responses. This work tests that possibility by benchmarking four representative MSAs, namely the Papernot, Tramèr, T-RND, and color perturbation attacks, against SNNs and their ANN counterparts on MNIST, Fashion-MNIST, and CIFAR-10. Across every attack and dataset, SNNs prove consistently more difficult to steal. Surrogates of SNNs achieve 10% to 20% lower agreement with the target model and 15% to 25% lower adversarial transferability than surrogates of ANNs. We attribute this resistance to the way SNNs compute, as their spike-based and time-dependent dynamics yield decision boundaries that ANN-based surrogates struggle to approximate, even under large query budgets. These findings extend the known resilience of SNNs beyond attacks on training data to the replication of model functionality, strengthening the case for neuromorphic architectures in security-sensitive applications.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36295

Detecting and Mitigating Query-Based System Prompt Leakage Attacks

Tushar Nayan, Pratik Poudel, Qian Lou, Yuede Ji, Jason Liu, Ruimin Sun

原文摘要

Large Language Models (LLMs) rely on proprietary system prompts to enforce task directives, safety policies, and access controls. These prompts are vulnerable to query-based leakage attacks, where black-box adversaries extract confidential instructions through adaptive, multi-turn interactions. Existing defenses often assess queries independently, missing malicious behavior that emerges across interactions. We present AdvGuard, a model-agnostic framework for detecting and mitigating system prompt leakage. AdvGuard models cross-query relationships using a bounded semantic interaction graph, statistically filters candidate components, and converts them into line graphs for graph convolutional network (GCN) classification. This approach captures multi-hop patterns in query similarity that distinguish coordinated extraction from benign workflows. A lightweight prompt-level detector provides protection before sufficient interaction history accumulates, and the framework supports black-box LLM deployments. In mixed-query evaluations, AdvGuard improves recall by up to 36% over the strongest baseline while maintaining a false positive rate of at most 3.4%. In multi-turn workloads, it achieves 97.23%-99.1% F1 with 100% recall. Leave-one-attack-family-out tests yield 99.98% mean recall and 99.99% mean F1, with no observed false positives. Integrated into the adaptive PLeak and LeakAgent attack loops, AdvGuard limits exact-match leakage to 0.00-0.01 and substring-match leakage to 0.01-0.09 across evaluated victim models. These results demonstrate robust detection of unseen attack families and substantially reduced prompt reconstruction.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.07063

Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training

Pingbang Hu, Xueshen Liu, Z. Morley Mao, Jiaqi W. Ma

原文摘要

Data selection methods address a critical challenge in LLM post-training: effectively leveraging scarce, high-fidelity target data alongside abundant but imperfectly aligned general training data. In this work, we move beyond the data-selection framing and introduce Dr. Post-Training (Data-Regularized Post-Training), a novel framework that reconceptualizes general training data as a data-induced regularizer that prevents overfitting to the scarce target objective, rather than serving as a pool for selection. Specifically, our framework proposes that, at each training step, we construct a feasible set of model update directions using the general training data, and project the model update direction specified by the scarce target data onto that feasible set. Standard training and existing data selection methods arise as special cases with different choices of the data-induced regularizer, and these methods correspond to different points on a bias-variance spectrum with different regularization strengths. Building on this view, we propose a family of methods offering a richer design space and more flexible bias-variance tradeoffs. For practical LLM-scale use, we introduce careful system optimizations that realize these methods with minimal overhead. Extensive experiments across SFT, RLHF, and RLVR show that our methods outperform standard training and state-of-the-art data selection baselines, with the largest gains where the general and target data are most misaligned, and system benchmarks confirm their efficiency.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36288

BUSTA: Teaching Small Language Models to Reason About Binary Execution

Ritika Poddar, Aidan Fennelly, Deirdre Murphy, Eric Wolos, Corre L. Steele, Michael Doyle

原文摘要

Large Language Models (LLM) are increasingly applied to Reverse Engineering (RE) workflows. RE, however, differs from common LLM coding tasks as it requires models to reason about low-level program behavior. Furthermore, the deployment of tooling in resource-constrained sandboxed RE environments limits the ability to use frontier-scale solutions. We examine whether a targeted LLM training approach can transfer distinct RE skills to open models via inverse basic-block execution: given an x86-64 basic block and a desired output register state, the model predicts the input register values that produce it. Fine-tuning \texttt{Qwen3-1.7B} and \texttt{Nemotron-3-Nano} with Group Relative Policy Optimization (GRPO) raises knowable-register prediction accuracy from 73.2\% to 85.3\% and from 63.3\% to 95.2\%, respectively. Frontier models still score highest (up to 99.2\%), but our fine-tuned \texttt{Nemotron-3-Nano} comes within four points at a fraction of the parameter count. We release both fine-tuned models and the training dataset.

cs.CR · cs.AI · cs.LG · cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36287

A Smart Instant Book Filter Model based on Dual-Objective Optimization

Yi Hou, Li Fan, Huizhong Duan

原文摘要

Hospitality service in online marketplaces has become increasingly popular over the past few years, not only because it helps people easily rent short-term lodging but also because it empowers travelers to connect with locals and feel belonging. A typical pattern of these industries is a central platform mediating the economic interactions between guests and hosts, where a successful booking experience is the key to user satisfaction. However, one of the biggest challenges is the possible delay of response and chance of rejection when guests try to book a request-to-book listing. Previously, we enabled the instant book feature to allow hosts to instantly accept qualified guests and guests to confirm bookings immediately. Yet the symptom has not been alleviated given mixed request-to-book and instant book listing supply in search results. One possible solution is to promote all instant book listings in search results; however, booking rate will be damaged due to some improperly promoted low quality listings. In this paper, we present a novel smart instant book filter system that applies the instant book filter intelligently and shifts request-to-book to instant book without hurting booking rate. Compared with traditional two-sided markets research that targets finding strategies to maximize a single overall social welfare goal, our proposed system aims to maximize the instant book rate with the constraint that booking rate should not decrease, forming a dual-objective optimization problem. We show A/B testing results for our system exposed to global users, demonstrating that our model performs better than previous human-expert-tuned models in terms of both instant book rate and overall booking rate. We also achieved improved metrics such as the host instant book adoption rate. The proposed system has been deployed to production and is serving millions of users every day.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.38829

Diversity Combining for Multi-Path LLM Reasoning

Guangsheng Yu, Litianyi Zhang, Qin Wang, Xu Wang, Mingyuan Li, Shaoxiong Ji, Ren Ping Liu, Massimo Piccardi

原文摘要

Multi-path reasoning methods such as self-consistency (SC) sample $K$ reasoning paths and choose the most frequent answer. However, their gains quickly plateau as $K$ increases, and locating this saturation point currently requires fitting a scaling model to accuracies measured at several values of $K$ or stopping online per query. We formalize multi-path LLM reasoning as a diversity combining problem from wireless communications: each path is a noisy channel observation, and the pairwise correlation of path correctness caps the design-effect effective sample size of the vote at a finite ceiling. Generalized least squares (GLS) analysis shows that, for paths with equal gains, the optimal linear combiner of latent embeddings is uniform exactly when every row of the path covariance has the same sum, as under exchangeability, supporting majority vote as the natural default in standard SC while leaving room for weighting or pruning under heterogeneous prompt-template branches. Across 5 models and 12 benchmarks, prompt-template diversity reduces path correlation in $55$ of $60$ model-benchmark cells, with a mean relative reduction of $16\%$ and reductions in every task domain. We derive an Adaptive-K rule that uses a four-path pilot to select $K^*$, retaining $96$--$103\%$ of MV@$K{=}32$ accuracy across Math, QA, and NLU.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.19818

Semantic World Models

Jacob Berg, Chuning Zhu, Yanda Bao, Ishan Durugkar, Abhishek Gupta

原文摘要

Planning with world models offers a powerful paradigm for robotic control. Conventional approaches train a model to predict future frames conditioned on current frames and actions, which can then be used for planning. However, the objective of predicting future pixels is often at odds with the actual planning objective; strong pixel reconstruction does not always correlate with good planning decisions. This paper posits that instead of reconstructing future frames as pixels, world models only need to predict task-relevant semantic information about the future. For such prediction the paper poses world modeling as a visual question answering problem about semantic information in future frames. This perspective allows world modeling to be approached with the same tools underlying vision language models. Thus, vision-language models can be trained as "semantic" world models through a supervised finetuning process on image-action-text data, enabling planning for decision-making while inheriting many of the generalization and robustness properties from the pretrained vision-language models. In this paper, we introduce this new method and validate it on simulated robotic tasks leading to improvements over typical paradigms of reconstruction-based action-conditional world modeling. Website available at https://weirdlabuw.github.io/swm.

cs.LG · cs.AI · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.28891

Fig: Automated Multiagent Behavior Elicitor

Anrui Gu, Zhichao Wang, Nicolai Ouporov

原文摘要

Many social evaluations for multiagent systems study behaviors as they emerge from environments instead of systematically intervening in the environment to elicit such behaviors. We introduce Fig (Finding Interactions in Games), an agentic system that performs targeted elicitation interventions on game environments. It takes a natural language behavior description, decomposes it into sub-behaviors, generates new social games or selects existing ones, and executes single or combined interventions to the games' engine, opponents, instructions, and context. To evaluate model behavior, it combines built-in mechanical checks and synthetic rubric judgments. We validate the interventions, generated games, and evaluation mechanisms via human review. Models attempt the target behavior in 45.2% of episodes on average for valid scenarios generated by Fig for six test behaviors -- cooperation, exploitation, deception, covert coordination, betrayal, and sabotage. For game-behavior pairs with available controls, Fig's interventions increase attempt rates by 10.9% on average compared to matched control games. Fig shows that multiagent environments can serve as programmable test beds for intentional, controllable, and reproducible behavior evaluation. Code is available at https://github.com/fleet-ai/fig.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.19298

Scoring-Rule Sensitivity in LLM Evaluation: Evidence from Indian Financial Regulatory Text

Rajveer Singh Pall

原文摘要

A benchmark leaderboard reports one accuracy number, but that number is a joint product of a model and a scoring rule. We ask what changes when only the rule changes, and find that model ordering is highly sensitive to it. IndiaFinBench is a 406-item expert-annotated benchmark over SEBI and RBI regulatory text covering regulatory interpretation, numerical reasoning, contradiction detection, and temporal reasoning. We score twelve LLMs zero-shot under two primary regimes over the same predictions - strict four-stage string matching, and the verdicts of a cross-model judge sharing no model family with any evaluated system - plus one operational composite regime. The two primary regimes show no positive rank correspondence (Spearman rho = -0.273, p = 0.39, not significant), and no model holds its rank across all three regimes. Strict accuracy spans 75.12-89.66%; judge-only accuracy spans 87.19-94.83% with a different leader and trailer; the composite compresses the field to 94.1-98.0%, under which DeepSeek-R1-Distill-Llama-70B ties for first despite ranking last under strict scoring, because the judge reclassifies 93.9% of its strict errors as correct. Output verbosity does not explain the reclassification once task and model composition are adjusted for, a negative result we report as such. Item-level analysis compounds the finding: 148 of 406 items (36.5%) are answered identically by all twelve models and separate no pair of systems, while a predefined higher-discrimination band captures 134 items. We also anchor the scale against one non-specialist evaluator, who scored 80.0% (48/60; 95% Wilson CI [68.2, 88.2]) on a 60-item medium/hard subset; paired bootstrap tests find no significant difference against any model after multiplicity correction. Data, harness, judge verdicts, predictions: https://github.com/Rajveer-code/IndiaFinBench

cs.CL · cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗