跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 01:55 — 2026-11-19 01:55(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:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

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。

26,870 已收录论文22,374 AI 相关8,156 有修订112 HF 社区发现

论文修订列表

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 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2611.05557

支持向量机直接最小化KL散度

Support Vector Machines Directly Minimise KL Divergence

Ivan Silajev

AI 速读 基于摘要

作者证明支持向量分类与回归的对偶目标等价于两个高斯测度间带约束的KL散度最小化,并据此将核岭回归纳入同一信息论框架。

cs.LG · stat.ML

查看原文摘要

Support vector machines (SVMs) are fundamentally grounded in geometric margin maximisation and currently lack a mainstream probabilistic interpretation. This keeps them theoretically isolated from probabilistic machine learning models that are naturally comparable and combinable. In this paper, we bridge this gap by proving that the dual objectives of both support vector classification and support vector regression are exact, constrained Kullback-Leibler (KL) divergence minimisation tasks between two Gaussian measures. We further show that this same divergence formulation recovers the exact objective function for kernel ridge regression when domain constraints are removed and $L^2$ regularisation is applied. By demonstrating that SVM duals directly minimise relative entropy, our results provide a unified information-theoretic model for standard kernel machines and lay the foundation for unifying broader kernel-based algorithms under probability theory.

版本更新 · v2arXiv:2609.00313

MUSES: A Benchmark for Prospective Intellectual-Roots Retrieval

Rohan Pandey, Sunjae Kwon, Hong Yu

原文摘要

Scientific discovery depends on finding prior literature that shapes what comes next. Existing retrieval systems optimize for relevance and popularity, often favoring central papers over less familiar works that later prove generative. We introduce \textbf{MUSES}, a million-instance benchmark for prospective intellectual-roots retrieval over a fixed 2.33M-paper corpus, with roughly 140K test instances per familiarity tier. To our knowledge, it is the first prospective benchmark at this scale with a shared retrieval task and author-confirmed paper-level root labels. Alongside it, \textbf{CiteRoots} pairs a scalable rhetorical layer over local citation text (LLM judge $κ= 0.896$ versus human gold) with a paper-level author-endorsed layer ($n = 1{,}518$ generative-inspiration pairs from 753 focal papers). MUSES organizes difficulty along two axes: a \emph{familiarity} axis spanning CiteNext, CiteNew, and CiteNew-Isolated, and a \emph{functional} axis spanning broad citations, rhetorical roots, and author-endorsed roots. Across 9 method classes, a lean multi-centroid retriever built on SPECTER2 is strongest. Hit@100 falls from 0.534 on CiteNext to 0.424 on CiteNew, 0.205 on rhetorical CiteNew, and 0.171 on author-endorsed CiteNew, a $3.1\times$ decline. In a registered eight-lens full-test audit, roughly half of broad-tier test instances remain unsolved at K=1{,}000. Rhetorical role and author endorsement are distinct: the same judge agrees with endorsement at $κ= 0.037$. We release MUSES, both CiteRoots layers, and a distilled open companion judge for future work on prospective retrieval and intellectual roots.

cs.IR

版本更新 · v3arXiv:2606.15950

Spectral Similarity Weights for Adaptive Conformal Prediction: A Bias-Variance Account and a Benchmark

Jeffery Opoku, David Banahene

原文摘要

Conformal prediction intervals lose their guarantee when a series is not exchangeable. We study weighting calibration residuals by the similarity of local Fourier power features, combined with the adaptive level update of ACI. A two-term account of the coverage error, mismatch that falls and sampling error that rises as the bandwidth shrinks, holds with exogenous features and conditionally independent residuals, but not for features computed from the series itself, which is how the method is used. In four simulations, spectral weighting lowered the mean regime-level deviation of coverage by 17% to 19% when the features came from the response and by 75% when they were exogenous, and not clearly under gradual drift. In each recurring-regime design a scaled-error baseline or Conformal PID control calibrated better. On nine public series with 36 forecast origins, spectral weighting with the plain weighted quantile did not differ from projected ACI in coverage error, and Conformal PID and scaled ACI were the best calibrated methods. The features are blind to seasonal phase, so the weights act like a recency kernel. A pure recency kernel did at least as well, especially with a finite-sample rank correction (mean absolute coverage error 0.039 against 0.090 for ACI; a post hoc check). Calendar phase weights narrowed German electricity intervals by 23% at equal coverage, but were not better than ACI across the series. We suggest trying adaptive baselines first, and similarity weights only where regimes differ in spectral shape or season and the effective sample size stays large.

stat.ML · cs.LG

版本更新 · v2arXiv:2605.06136

Build-and-Find:一种评估智能体管理代码库的努力感知协议

Build-and-Find: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases

Jhen-Ke Lin

AI 速读 基于摘要

提出 Build-and-Find 协议,将代码库视为面向后续智能体的沟通产物,用恢复准确率、稳定性与检查努力等指标评估生成仓库的可读性与意图可恢复性。

cs.SE · cs.AI

查看原文摘要

Most coding-agent benchmarks ask whether generated code behaves correctly. That remains essential, but repository-level engineering is increasingly agent-managed: one agent writes a repository, and later agents inspect, audit, or extend it as working context. In that setting, a generated repository is not only an answer to a task but also a communication artifact for future work. Even when strong agents nearly satisfy the visible behavioral objective, repositories can differ in how clearly they expose the intended behavior and design choices behind that behavior. We introduce Build-and-Find to evaluate whether downstream agents can efficiently recover intended choices from generated repositories. For each task, a builder creates a codebase from a hidden specification; a finder receives only the codebase and a specification-traced question bank. The protocol separates behavioral correctness from artifact-side recovery and reports recovery accuracy, repeatability, implementation coverage, and inspection effort. Evaluation proceeds in two stages: the first uses recovery accuracy and stability as gates to establish that finders can reliably recover the intended choices; the second compares inspection effort by the same finder across artifacts that pass these gates and allow the same intent to be recovered. Lower effort suggests that the artifact makes that intent easier to locate. We find that several frontier models approach saturation in intent recovery on our task pack, yet second-stage inspection effort reveals differences among their generated artifacts, providing a dimension beyond accuracy for comparing artifact legibility. We also audit artifacts to distinguish unimplemented specification claims from finder failures and check whether correct answers are supported by artifact evidence. We release the harness and benchmark data for reproducibility and extension.

版本更新 · v2arXiv:2606.17241

超越基准:嵌入式车载硬件上交通标志识别的连续边缘推理

Beyond Benchmarks: Continuous Edge Inference for Traffic Sign Recognition on Embedded Vehicular Hardware

Aditya Mishra, Anushka Tailor, Haroon Lone

AI 速读 基于摘要

作者提出面向NVIDIA Jetson Orin Nano的连续边缘推理系统Edge-TSR,并在流式视频评测中揭示图像基准与真实部署之间的性能落差。

cs.CV · cs.RO · eess.SY

查看原文摘要

Traffic sign recognition (TSR) systems deployed on embedded vehicular hardware face deployment effects that image-based benchmark evaluation does not capture, including frame-to-frame prediction instability in streaming video and load-dependent throughput under sustained operation. We present Edge-TSR, a continuous edge inference system for TSR on the NVIDIA Jetson Orin Nano that combines sparse detection, multi-object tracking, region-level fine-grained classification, and a lightweight track-aware temporal stabilization mechanism adding only 0.07~ms per sampled frame. Evaluating on the source videos of the INTSD benchmark, we find that the state-of-the-art TSR models lose 20-30 percentage points of mAP@50 when moving from image-based to streaming evaluation. Edge-TSR achieves the best streaming classification performance among all evaluated baselines, and temporal stabilization improves accuracy by 10.58 percentage points over per-frame inference. We characterize latency, throughput, and thermal behavior across sampling intervals and four driving conditions, showing that throughput is load-proportional (20 ms per classified region) and that every-frame inference is limited by throughput rather than thermal throttling. A 55-minute, 26 km vehicular deployment demonstrates sustained online operation at 16.18 FPS within safe thermal limits without cloud offload. We also release the annotated 50,732-frame streaming evaluation dataset and full implementation.

版本更新 · v2arXiv:2610.19429

自动驾驶中强化学习算法的综合比较

A Comprehensive Comparison of Reinforcement Learning Algorithms in Autonomous Driving

Dechen Xie, Mushuang Liu

AI 速读 基于摘要

在同一无信号交叉口自动驾驶决策问题上,对FVI、RCPI、DQN和D-DDPG四种强化学习方法进行最优性、安全性、训练稳定性与成本比较。

cs.LG · eess.SY

查看原文摘要

This paper presents a comprehensive comparison of four representative Reinforcement Learning (RL) methods in autonomous vehicle (AV) decision-making, including Fitted Value Iteration (FVI), Rollout Classification Policy Iteration (RCPI), Deep Q-Network (DQN), and a discrete-action adaptation of Deep Deterministic Policy Gradient (D-DDPG). The four methods are applied to the same AV decision-making problem at an unsignalized intersection and are compared in terms of optimality, safety, training stability, and training and decision cost. Observations suggest that RCPI provides the closest estimation to the exact solution and has the most stable training curve; however, it is data-intensive and requires the largest volume of data. D-DDPG is the most data-efficient one, but at the price of the training stability. Based on the observations, we provide suggestions for the algorithm selection for AV decision making.

版本更新 · v2arXiv:2609.22183

CleanScore:带负对照与敏感性边界的黑盒基准审计

CleanScore: Black-Box Benchmark Audits with Negative Controls and Sensitivity Bounds

Jeffery Opoku, David Banahene

AI 速读 基于摘要

提出一种仅需答题对错的黑盒审计方法,用改写题与对照题库估计公开基准题的形式优势,并通过受控实验检验其检测污染的能力与盲区。

cs.LG · stat.ME

查看原文摘要

Public benchmark scores reflect skill, prior exposure to the questions, or both, and for most models the training data are unknown. CleanScore is a black-box audit: the estimator needs only a correct-or-incorrect score for each form, not training data or weights. Each benchmark question becomes a parent item with one public form and two independently written fresh forms that keep its numbers, facts and answer. The audit reports an interval for the public-form advantage, not a verdict, and a private control bank with an explicit transport radius provides a proxy for the ordinary form gap that a rewrite alone can produce. A registered controlled-exposure experiment, a preliminary validation, detects planted exposure in one of two model families. A registered audit of five open models on 200 GSM8K and 200 ARC-Challenge items (ARC with stem-only rewrites, scored by option log probabilities) finds no exposure-consistent advantage, and two reruns declared before they were run (GSM8K at a longer token budget, ARC scored from generated letters) leave that conclusion unchanged. For four of the ten model-benchmark pairs the upper end of the interval is about five points or less, and for none is it above 21 points. The registered claim rule is much less sensitive than the primary interval: it flags a planted ten-point advantage in 5% to 11% of audits. Registered positive controls show what a null can mean. In four models, each trained under four seeds, items leaked into fine-tuning gained 25 points on average over unleaked items on the leaked wording and 19 points on paraphrases the model never saw, so a substantial share of the effect, estimated at 76% (95% interval 50% to 113%), is invisible to a paraphrase audit. A null on surface form says much less about contamination than the name suggests.

版本更新 · v3arXiv:2605.00222

CompleteRXN:迈向补全开放化学反应数据库

CompleteRXN: Toward Completing Open Chemical Reaction Databases

Gabriel Vogel, Minouk Noordsij, Evgeny Pidko, Jana M. Weber

AI 速读 基于摘要

作者构建了面向真实缺失数据条件的大规模反应补全监督基准 CompleteRXN,并比较了约束反应配平器 CRB、SynRBL 与一种带约束解码的编码器-解码器模型。

cs.LG · physics.chem-ph

查看原文摘要

Chemical reaction datasets such as USPTO suffer from substantial incompleteness, frequently missing byproducts, co-reactants, and stoichiometric coefficients. This limits their applicability and reliability in downstream applications. Here, we introduce CompleteRXN, a large-scale supervised benchmark for reaction completion under realistic missing-data conditions. We construct a dataset of aligned incomplete and atom-balanced reactions by mapping USPTO records to curated mechanistic reactions. We evaluate representative baselines, including a novel encoder-decoder reaction completion model with constrained decoding, the Constrained Reaction Balancer (CRB), and a recent algorithmic method, SynRBL. On our CompleteRXN benchmark, the CRB achieves high performance across splits of increasing difficulty, reaching 99.28% equivalence accuracy on the random split and 91.71% on the extreme out-of-distribution split. SynRBL produces many balanced and chemically plausible completions, but with lower accuracy on the benchmark test splits. Across all methods, performance degrades with increasing incompleteness. We observe a substantial drop when evaluating on reactions outside the benchmark (full uncurated USPTO), highlighting the gap between benchmark performance and practical robustness and motivating future work. Data, code and models can be found at: https://github.com/Intelligent-molecular-systems/CompleteRxn-Benchmarking.

版本更新 · v3arXiv:2505.20726

ManiTaskGen:用于评测与提升视觉语言智能体具身决策能力的综合任务生成器

ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making

Liu Dai, Haina Wang, Weikang Wan, Hao Su

AI 速读 基于摘要

提出一个能为任意场景自动生成全面、多样且可行的移动操作任务的系统,并用于构建基准和提升视觉语言智能体的具身决策能力。

cs.RO

查看原文摘要

Building embodied agents capable of accomplishing arbitrary tasks is a core objective towards achieving embodied artificial general intelligence (E-AGI). While recent work has advanced such general robot policies, their training and evaluation are often limited to tasks within specific scenes, involving restricted instructions and scenarios. Existing benchmarks also typically rely on manual annotation of limited tasks in a few scenes. We argue that exploring the full spectrum of feasible tasks within any given scene is crucial, as they provide both extensive benchmarks for evaluation and valuable resources for agent improvement. Towards this end, we introduce ManiTaskGen, a novel system that automatically generates comprehensive, diverse, feasible mobile manipulation tasks for any given scene. The generated tasks encompass both process-based, specific instructions (e.g., "move object from X to Y") and outcome-based, abstract instructions (e.g., "clear the table"). We apply ManiTaskGen to both simulated and real-world scenes, demonstrating the validity and diversity of the generated tasks. We then leverage these tasks to automatically construct benchmarks, evaluating high-level embodied decision-making through a grounded skill interface for agents built upon existing vision-language models (VLMs). Furthermore, we propose a simple yet effective method that utilizes ManiTaskGen tasks to enhance embodied decision-making. Overall, this work presents a cross-scene task generation framework facilitating both benchmarking and improvement of embodied decision-making agents. Our code is available at https://manitaskgen.github.io.

版本更新 · v5arXiv:2404.15158

On the Monotonicity of Information Measures

Xiaoyu Cheng, Yonggyun Kim

原文摘要

We study the monotonicity of information measures, functions that assign a value to each statistical experiment, with respect to the Blackwell and Lehmann orders. We show that such monotonicity can be characterized by local, first-order conditions. Under natural invariance properties, a measure is Blackwell monotone if and only if it decreases in the direction of signal replacements, and Lehmann monotone if and only if it decreases in the direction of reverse signal replacements, which replace signals with higher ones only in low states or with lower ones only in high states. We translate both conditions into the space of posterior beliefs and apply them to likelihood-separable and posterior-separable measures, showing in particular that the entropy cost is Lehmann monotone. Among posterior-separable measures, we further identify a Lehmann monotone subclass, posterior-mean-ratio measures, that characterizes the Lehmann order.

econ.TH · cs.IT

版本更新 · v3arXiv:2610.20970

A wind memory for odour source search in reversing wind

Junlong Shen, Shunsuke Shigaki

原文摘要

After wind reversals, old odour arrives while the sensed wind points away from the source, so wind followers, which surge upwind, are misled. A hold gate stores the wind at first odour contact and feeds it to an unchanged follower while the live wind points over 90° away. On 60 random simulated reversing flows it raised a published moth model's success by 10.8 points (95% CI 6.6 to 15.4) and four other followers' by 6.0 to 10.1, but cost the moth model 5 points in steady wind. A fixed wind delay was not resolvably worse at insect scale, but in simulation rescaled to a legged robot's sensors and turn rate the gate beat the best delay for two followers, only one margin surviving Bonferroni correction. As the robot never ran the gate and a plain spiral searcher beat the gated moth model, it is an add-on, not a better searcher.

cs.RO

版本更新 · v3arXiv:2512.22838

超越重叠:面向外存向量搜索的分层图抽象

Beyond Overlap: Hierarchical Graph Abstraction for Out-of-Core Vector Search

Lizheng Chen, Pinhuan Wang, Shaonan Ma, Jie Zhang, Qing Wang, Zhengyi Yang, Heng Zhang, Mingxing Zhang 等 12 位作者

AI 速读 基于摘要

提出分层外存 ANNS 引擎 GANNS,用内存驻留的图抽象在 SSD 访问前实现逻辑重叠,兼顾精度与 I/O 效率。

cs.DB · cs.IR

查看原文摘要

At billion scale, approximate nearest neighbor search (ANNS) often becomes an out-of-core problem: the full vector collection and index structures exceed memory capacity, making query performance dominated by SSD accesses and DRAM-SSD data movement. Existing systems struggle to strike a balance between accuracy and efficiency: physical-overlap methods replicate vectors or index entries across partitions, enlarging the SSD-resident index and incurring extra I/O; quantization-based methods reduce memory usage, but their approximate distances are less reliable and often require costly raw-vector reranking from SSD to preserve recall. We present GANNS (Graph-Abstraction ANNS), a hierarchical out-of-core ANNS engine that improves accuracy and I/O efficiency simultaneously. GANNS stores each cluster as a disjoint SSD partition with scale-aware indexes, while a memory-resident graph abstraction provides logical overlap before SSD access. During serving, GANNS uses query hotness and cluster priorities from the graph abstraction to prune low-value clusters and improve access locality. Across five datasets under strict memory constraints, GANNS delivers representative QPS improvements of 2.0--4.7x over state-of-the-art baselines, while preserving accuracy.

版本更新 · v2arXiv:2609.39078

参数对称性决定过参数化非线性网络中的表征几何

Parameter Symmetries Determine Representational Geometry in Overparameterized Nonlinear Networks

Marvin Theiss, Lukas Braun, Andrew M. Saxe, Erin Grant

AI 速读 基于摘要

作者提出参数对称性通过加法、复制与缩放三种基本特征变换作用于表征,并给出表征几何的闭式分解,说明过参数化下功能固定时表征仍可能退化。

cs.LG

查看原文摘要

Representations are routinely used across machine learning, psychology, and neuroscience to draw inferences about the computations of biological and artificial systems. Such inferences presume that the geometry of these representations reflects the computation being performed. For artificial neural networks, however, the extent to which the function a network computes constrains this geometry remains unclear. One key obstacle is that these networks admit parameter symmetries: changes in parameterization that preserve function exactly while reshaping representational geometry. Here, we show that a broad class of parameter symmetries acts on representations through just three primitive feature transformations: addition, duplication, and scaling. This feature-level characterization yields a closed-form decomposition of representational geometry into essential and auxiliary components, revealing how representational degeneracy can exist without and grows with overparameterization even when function is held fixed. Finally, we establish conditions under which implementation-level selection rules resolve this degeneracy, yielding identifiable geometries in which features are weighted according to their contributions to the network's function. Together, our results delineate when representational geometry can support inferences about computation, and when it cannot.

版本更新 · v2arXiv:2610.02945

面向AI辅助数学发现的持续图记忆与社区基础设施

Continual Graph Memory and Community Infrastructure for AI-Assisted Mathematical Discovery

Eric Hanchen Jiang, Junyi Zhang, Jinxi Yu, Jiachen Lu, Zhi Zhang, Michael Simon, Justin Baker, Richard Cai 等 30 位作者

AI 速读 基于摘要

作者提出Ansatz研究框架与Ansatze社区平台,用持续图记忆区分模型接受的结论与人工整理探索,并支持数学研究的检查、引导与形式化验证。

cs.AI · cs.CL

查看原文摘要

Mathematical discovery requires preserving partial ideas and the evidence supporting their reuse. We present Ansatz, a research harness whose continual graph memory separates model-accepted claims and dependencies from curated exploration, and Ansatze, a community platform for inspecting, guiding and checking this work. On First Proof, Ansatz recorded nine local verifier closures in each of two ten-problem batches; a partial result in the Second Batch also counted as a pass under the study's criterion. These model-assessed outcomes include continued searches and differ from expert validation. Component studies and re-review expose disagreements and their dependency reach. Open-problem investigations produced candidate results, with five Lean formalizations reported. The platform connects problem discovery, research records, manuscript analysis and formal checking while preserving distinct evidence states. Together, these systems support cumulative human-AI research through persistent investigation and inspectable contributions.

版本更新 · v2arXiv:2605.05921

意图建构与意义建构:人类与AI引导的数学发现交互

Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery

Alex Bäuerle, Adam Connors, Alexander Novikov, Adam Zsolt Wagner, Ngân Vũ, Fernanda Viegas, Martin Wattenberg, Lucas Dixon

AI 速读 基于摘要

通过对11位数学家使用进化编码智能体AlphaEvolve三个月、逾2300次实验的研究,提出并刻画“意图建构”(intentmaking)作为“意义建构”(sensemaking)的对应过程。

cs.AI · cs.HC

查看原文摘要

Artificial intelligence offers powerful paradigms for scientific discovery, orchestrating autonomous inner search loops over long horizons. However, discovery remains bottlenecked by the friction of the outer human-AI loop: the cycle where domain experts formulate research objectives, diagnose reward hacks, and extract meaning. We present findings from a study with 11 expert mathematicians using AlphaEvolve, an evolutionary coding agent, across more than 2,300 experiments over three months. We identify and characterize intentmaking, the iterative process of discovering, defining, and refining experimental goals through system interaction, as a reciprocal counterpart to sensemaking. We observe that domain experts effectively alternate between steering the search space (intentmaking) and extracting mathematical insights (sensemaking). Our findings suggest an approach to designing AI tools for scientific discovery that moves beyond the existing question--answer model, treating them as collaborative instruments rather than opaque black-box oracles.

版本更新 · v2arXiv:2605.06919

大语言模型能否对检索信息持保留态度?

Can LLMs Take Retrieved Information with a Grain of Salt?

Behzad Shayegh, Mohamed Osama Ahmed, Fred Tung, Leo Feng

AI 速读 基于摘要

评估八个大语言模型能否根据检索上下文中表达的不确定性调整回答,并提出无需改权重的交互策略来减少遵从错误。

cs.CL

查看原文摘要

Large language models have demonstrated impressive retrieval-augmented capabilities. However, a crucial area remains underexplored: their ability to appropriately adapt responses to the certainty of the retrieved information. It is a limitation with real consequences in high-stakes domains like medicine and finance. We evaluate eight LLMs on their context-certainty obedience, measuring how well they adjust responses to match expressed context certainty. Our analysis reveals systematic limitations: LLMs fail to reproduce their prior outputs after observing an uncertain context, respond to expressed certainties in a distorted way, and overrely on complex contexts. To address these, we propose an interaction strategy combining prior reminders (feeding the model's own context-free answer back into the prompt), context-certainty recalibration, and context simplification. This approach reduces obedience errors by 25% on average, without modifying model weights, demonstrating the efficacy of interaction design in enhancing LLM reliability. Our contributions include a principled evaluation metric, empirical insights into LLMs' uncertainty handling, and a portable strategy to improve context-certainty obedience across diverse LLMs.

版本更新 · v2arXiv:2605.23362

预算约束下多LLM评审的实例最优估计

Instance-Optimal Estimation with Multiple LLM Judges on a Budget

Junghyun Lee, Sanghwa Kim, Yassir Jedra, Alexandre Proutière, Se-Young Yun

AI 速读 基于摘要

在固定预算下,研究如何将评估查询分配给价格与可靠性各异的多个LLM评审和不同难度的实例,以最准确地估计得分向量。

cs.LG · cs.IT · math.ST · stat.ML

查看原文摘要

Evaluating large language models increasingly relies on LLM-as-a-judge protocols, but such evaluations remain costly: different judges have different prices and reliabilities, and the difficulty of each prompt-response pair can vary substantially. This raises a basic allocation question: under a fixed budget, how should one distribute evaluation queries across heterogeneous judges and instances to obtain the most accurate score estimates? We formalize this question as budgeted heteroskedastic multi-judge estimation under independent, unbiased score observations. Given $K$ prompt-response pairs and $J$ judges with known costs but unknown query-judge variances, our goal is to estimate the bounded score vector while minimizing an $\ell_p$-error. Our first contribution is to analyze the inverse-variance weighted estimator (IVWE) and to derive the oracle allocation that minimizes its leading error bound. Since this allocation depends on the unknown variances, we then address the unknown-variance setting by proposing EST-IVWE, an adaptive algorithm that constructs and uses optimistic variance estimates to stabilize the empirical allocation. We prove that EST-IVWE matches the oracle IVWE rate up to lower-order terms in the budget. Our second and central theoretical contribution is a local minimax lower bound matching the leading allocation-dependent rate, establishing asymptotic instance-optimality up to logarithmic factors. An Assouad-type construction based on local, variance-preserving perturbations yields this bound both in expectation and with constant probability. A complementary Fano-type change-of-measure argument captures the logarithmic dependence on the confidence level with a different (suboptimal) allocation geometry. Finally, we numerically validate our approach on synthetic data and resampled HelpSteer2 evaluations, demonstrating improvements over naïve uniform allocation.

版本更新 · v3arXiv:2504.04619

增量最小生成树的新算法及其时序图应用

New Algorithms for Incremental Minimum Spanning Trees and Temporal Graph Applications

Xiangyun Ding, Yan Gu, Yihan Sun

AI 速读 基于摘要

作者提出 AM-tree 数据结构,用于增量最小生成树,并在理论上达到与 link-cut tree 相同的界,同时报告了在实践中优于 link-cut tree 的性能,还讨论了如何用时序图处理中的多类设置-问题组合来求解。

cs.DS

查看原文摘要

Processing graphs with temporal information (the temporal graphs) has become increasingly important in the real world. In this paper, we study efficient solutions to temporal graph applications using new algorithms for Incremental Minimum Spanning Trees (MST). The first contribution of this work is to formally discuss how a broad set of setting-problem combinations of temporal graph processing can be solved using incremental MST, along with their theoretical guarantees. Despite the importance of the problem, we observe a gap between theory and practice for efficient incremental MST algorithms. While many classic data structures, such as the link-cut tree, provide strong bounds for incremental MST, their performance is limited in practice. Meanwhile, existing practical solutions used in applications do not have any non-trivial theoretical guarantees. Our second and main contribution includes new algorithms for incremental MST that are efficient both in theory and in practice. Our new data structure, the AM-tree, achieves the same theoretical bound as the link-cut tree for temporal graph processing and shows strong performance in practice. In our experiments, the AM-tree has competitive or better performance than existing practical solutions due to theoretical guarantees, and can be significantly faster than the link-cut tree (7.8-11x in updates and 7.7-13.7x in queries).

版本更新 · v2arXiv:2608.11624

学习说服揭示大语言模型放弃正确信念的脆弱性

Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs

Nimet Beyza Bozdag, Emre Can Acikgoz, Gokhan Tur, Dilek Hakkani-Tür

AI 速读 基于摘要

作者提出对抗性说服威胁,并用对抗强化学习训练说服者智能体,展示其能大幅提升让目标模型改变答案的成功率。

cs.CL · cs.AI

查看原文摘要

Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions. As LLMs increasingly debate, advise, and think collaboratively with humans and each other, resistance to harmful persuasion becomes a core requirement for reliable behavior. Yet a single targeted persuasive argument can be enough to collapse model accuracy to near zero, even when the argument is factually false. We formalize this threat as adversarial persuasion and introduce an adversarial reinforcement learning framework that trains persuader agents to change a target model's answer in a single interaction. First, we show that RL-trained persuaders raise persuasion success from approximately 24% to over 93% against the training-time persuadee. Second, we find that these learned strategies generalize across four out-of-distribution benchmarks, maintaining 89-95% persuasion success against the training-time persuadee. They also transfer to unseen models, achieving 83% success on Qwen-14B, 79% on Llama-3.1-8B, and 25% on GPT-4o-mini, although effectiveness can be limited for frontier models, with only 4% success on GPT-5-mini. Third, we demonstrate that a curriculum that bootstraps on more persuadable open-weight models before targeting harder models further increases GPT-4o-mini attack success from 25% to 38%. Moreover, our results reveal that optimized persuaders increasingly rely on credibility-based tactics, including fabricated citations and false authoritative evidence. Together, these findings expose a critical weakness in current LLM agents. Even when they initially reason correctly, they can be steered toward false conclusions by optimized natural language influence. This positions persuasion robustness as a necessary safety criterion for multi-agent and human-AI decision-making systems.

版本更新 · v2arXiv:2606.02294

正则化大邻域搜索

Regularized Large Neighborhood Search

Germain Vivier-Ardisson, Laurent Demonet, Axel Parmentier, Mathieu Blondel

AI 速读 基于摘要

作者提出正则化大邻域搜索(RLNS),将大邻域搜索启发式转化为组合可行解集上的高效 MCMC 采样器,并配套 Fenchel-Young 损失,用于无需全局求解器的端到端学习。

cs.LG

查看原文摘要

Operations research practitioners typically tackle NP-hard combinatorial problems using large neighborhood search (LNS), a scalable heuristic that iteratively refines a current solution by locally re-optimizing subsets of its variables. In contrast, most existing approaches for integrating combinatorial optimization layers into neural networks still assume access to an exact global solution, which is computationally intractable. We bridge this gap by introducing regularized LNS (RLNS). By regularizing or perturbing local subproblems, we turn the LNS heuristic into an efficient MCMC sampler over the combinatorial set of feasible solutions, with associated Fenchel-Young losses. Under entropic regularization, we prove that RLNS performs exact block Gibbs sampling. Furthermore, adjusting the number of RLNS iterations allows us to interpolate between pseudolikelihood and exact maximum likelihood estimation, for end-to-end learning without global solvers. We demonstrate our approach on $k$-subset selection, generalized assignment, and stochastic vehicle scheduling problems.

版本更新 · v3arXiv:2602.15815

隐私过滤器被残差刻画:自由自然过滤器的特征与自适应性的代价

Privacy Filters are Captured by Residues: A Characterization of Free Natural Filters and the Cost of Adaptivity

Matthew Regehr, Bingshan Hu, Ethan Leeman, Pasin Manurangsi, Pierre Tholoniat, Mathias Lécuyer

AI 速读 基于摘要

论文用贝尔曼方程刻画隐私过滤器的最坏情况隐私损失,提出统一现有过滤器的残差过滤器,并研究自然过滤器的自由性与自适应代价。

cs.CR · cs.DS

查看原文摘要

We study privacy filters, which enable privacy accounting for differentially private (DP) mechanisms with adaptively chosen privacy characteristics. We show that the worst-case privacy loss of interacting with any privacy filter is characterized by a Bellman equation. We apply this theory to develop residue filters, which unify existing privacy filters. We develop the Gaussian DP (GDP) residue filter, which strictly improves upon the naïve GDP filter. We show that, in the average case, this new filter asymptotically permits as many pure DP queries as in the non-adaptive case and a factor $π/2$ more pure DP queries than the naïve GDP filter. We also show that residue filters capture the natural filter, which promises greater utility by leveraging exact privacy accounting techniques. Earlier privacy filters consider only simple privacy parameters such as Rényi-DP or GDP parameters. Natural filters account for the entire privacy profile of every query, promising more efficient use of a given privacy budget. We show that, contrary to other forms of DP, natural privacy filters are not free in general. We present a characterization of when a family of private queries admits free natural filters for a given budget. In particular, only families of privacy mechanisms that are totally-ordered when composed admit free natural privacy filters with respect to an arbitrary privacy budget. Finally, we show that, while the natural approximate-DP filter can fail in the presence of an adaptive adversary, it cannot fail too badly: the output remains approximate-DP with parameters at most poly-logarithmically worse than the intended privacy parameters.

版本更新 · v2arXiv:2605.11673

Incremental Matrix Assembly for Preplanned Dynamic Tetrahedral Meshes

Manish Acharya, David Hyde

原文摘要

Local topology edits require updating assembled operators even when most of a tetrahedral mesh remains unchanged. We implement and evaluate incremental matrix assembly for preplanned edits, assuming a fixed pool of candidate elements with precomputable contributions. A preallocated sparse layout allows operator values to be updated from edited elements without rebuilding the sparsity structure. We compare full reassembly, local recomputation, and persistent incremental updates using a shared layout. Across tested meshes with up to 460k tetrahedra, incremental assembly achieves 6-27 times assembly speedups over a vectorized full-reassembly baseline for a proxy graph Laplacian and 2-17 times for linear elasticity. Frame times decrease by 1-3% when the linear solve dominates and by 18-20% in the tested synthetic dynamic elasticity loop with shorter solves. Local Recompute often achieves comparable frame times. For fixed time-step coefficients, directly maintaining the combined elasticity system also avoids a global matrix-combination pass. The Laplacian matches full reconstruction exactly in every tested frame; elasticity differences remain at rounding scale, reaching a maximum entry difference of 4.2 times 10^(-16) over 5,000 frames.

cs.GR

版本更新 · v3arXiv:2511.16558

在图上以多项式时间模拟高斯玻色采样

Simulating Gaussian boson sampling on graphs in polynomial time

Konrad Anand, Zongchen Chen, Mary Cryan, Graham Freifeld, Leslie Ann Goldberg, Heng Guo, Xinyuan Zhang

AI 速读 基于摘要

作者报告,与图上高斯玻色采样(GBS)相关的一个分布以及另一个与玻色采样相关的分布,都可以在经典计算下以多项式时间采样。

quant-ph · cs.DS

查看原文摘要

We show that a distribution related to Gaussian Boson Sampling (GBS) on graphs can be sampled classically in polynomial time. Graphical applications of GBS typically sample from this distribution, and thus quantum algorithms do not provide exponential speedup for these applications. We also show that another distribution related to Boson sampling can be sampled classically in polynomial time.

版本更新 · v2arXiv:2609.17212

高斯多用户信道容量域

The Gaussian Multiuser Channel Capacity Region

John M. Cioffi

AI 速读 基于摘要

该工作利用接收机子集消息原子、高斯单用户等效与连续解码来刻画高斯多用户信道的容量域。

cs.IT

查看原文摘要

This work characterizes a Gaussian multiuser-channel capacity-region using receiver-subset message atoms, Gaussian single-user equivalents, and successive decoding. A memoryless multiuser-channel model specifies both the channel conditional distribution and the independent-use input distribution. For all linear Gaussian channels, independent Gaussian user signaling and receiver-local worst-case-noise/MMSE-GDFE transformations provide a single-user-equivalent basis for the complete capacity-region construction. Each user distributes its input autocorrelation among a finite set of receiver-subset atoms, whose rate sums satisfy the applicable receiver constraints. Minimum-energy and weighted-rate-sum designs optimize these allocations, while fixed-allocation linear programs determine feasible atomic rates and synchronized time-shared successive-decoding implementations. The resulting framework includes Gaussian multiple-access, broadcast, and interference channels, with numerical examples illustrating their rate regions and receiver designs.

版本更新 · v2arXiv:2610.07473

From Dialogue to Diagnostic Hypotheses: Evaluating LLM Agents for Psychiatric Assessment

Milad Mohammadi, Fatemeh Akrami Shamsabadi, Zahra Mohseni, Amirhossein Safdarian, Malekfarhad Malek, Hadi Moradi, Hesham Faili

原文摘要

Although LLMs show promising diagnostic reasoning on supplied clinical evidence, their ability to elicit such evidence through free-form psychiatric interviews remains less understood. We evaluate interview quality and diagnostic hypotheses using simulated patients and human participants. For controlled simulation, we introduce PsyCPG, transforming clinical cases into structured patient profiles. On 30 paired cases, experts rate PsyCPG simulations higher in quality than raw-case role-play (4.50 versus 3.83/5). We introduce PsyCIDRA, a dual-agent framework: its interviewer agent uses a notepad tool, expert-written skills, and ICD-11 reference tools to guide interviews; its diagnostic agent analyzes the transcript and produces a report for expert review, ranking differential diagnoses with supporting, conflicting, and missing evidence. Across four models and 53 development cases, PsyCIDRA achieves higher observed diagnostic agreement than direct prompting. On 81 held-out simulated cases, exact-code rank-1 accuracy reaches 60.5% versus 51.9%. We conduct 101 interviews with human participants; two psychologists, blinded to interview condition and model reports, independently assess interview quality and transcript-supported hypotheses. In separate arms, PsyCIDRA agrees with experts on whether to issue a hypothesis in 79.6% of cases versus 65.4% for direct prompting. This study provides an empirical basis for understanding and evaluating LLM agents in free-form psychiatric interviewing.

cs.AI

版本更新 · v2arXiv:2605.11884

Sobolev Regularized MMD Gradient Flow

Chenyang Tian, Bharath K. Sriperumbudur, Arthur Gretton, Zonghao Chen

原文摘要

We analyze Sobolev descent, a regularized variant of maximum mean discrepancy (MMD) gradient flow based on a gradient penalty on the MMD witness function. This regularization mitigates the non-convexity of the MMD objective, and yields provable \emph{global} convergence guarantees in MMD, in both continuous and discrete time. A surprising appeal is that our convergence analysis does not rely on isoperimetric assumptions on the target distribution. Instead, it is based on a regularity condition on the difference between kernel mean embeddings. We extend Sobolev descent such that it is applicable in both sampling (from an unnormalized target distribution)---using Stein kernels---and generative modeling settings, unlike previous works, where a gradient flow is suitable for only generative modeling or sampling but not both. We empirically validate the method on a broad range of tasks across both settings.

cs.LG

版本更新 · v2arXiv:2605.09630

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models

Lin Zheng, Vasilisa Bashlovkina, Timothy Dozat, Dan Garrette, Laura Rimell, Joshua Maynez

原文摘要

Tokenizer-free language models eliminate the tokenizer step of the language modeling pipeline by operating directly on bytes; patch-based variants further aggregate contiguous byte spans into patches for efficiency. However, the average patch size chosen at the model design stage governs a tight trade-off: larger patches reduce compute and KV-cache footprint, but degrade modeling quality. We trace this trade-off to patch lag: until a patch is fully observed, byte predictions within it must rely on a stale representation from the previous patch to preserve causality; this lag widens as patches grow larger. We introduce Scratchpad Patching (SP), which inserts transient scratchpads inside each patch to aggregate the bytes seen so far and refresh patch-level context for subsequent predictions. SP triggers scratchpads using next-byte prediction entropy, selectively allocating compute to information-dense regions and enabling post-hoc adjustment of inference-time compute. Across experiments on natural language and code, SP improves model quality at the same patch size; for example, even at $16$ bytes per patch, SP-augmented models match or closely approach the byte-level baseline on downstream evaluations while using a $16\times$ smaller KV-cache over patches and requiring roughly $3$-$4\times$ less inference compute than the byte-level baseline.

cs.CL · cs.LG

版本更新 · v2arXiv:2605.28001

What Does a Copyright Budget Certify? An Exact Threshold for Per-Token Meters, and a Length-Independent Certificate for Selection

J. Vijayavallabh

原文摘要

Certified inference-time copyright defences publish a divergence budget between the served model and a safe anchor trained without the protected works. We ask what such a budget certifies. Proved: a budget of K nats says nothing about a work whose surprisal under the anchor is at most K, at every Rényi order. Anchored decoding charges per token, so its budget grows with the output. Measured: at its authors' setting, the budget exceeds the anchor's surprisal of every one of the 758 protected passages we test, so it certifies nothing about them. Proved: serving one of n anchor draws, by any rule, is certified at log n nats for the whole output, at any length; in installments, a window is certified only given the text up to a block boundary. Measured: over a vetted anchor, with an adversarial scorer, selection reproduced no protected passage near-verbatim. Its draws cost 21.8x a metered decode on an anchor-only server. Judged: in the headline configuration, at the only published meter budget that bounds a 50-token window, selection's gain over one anchor draw is reliably positive and the meter's is, by a post-hoc equivalence test, zero. At matched compute selection loses. At the authors' sampling settings on the 8B, the two tie at that budget. Where the meter's certificate is vacuous, the ranking depends on how the stronger model is served. It reverses under a chat template, at the authors' sampling settings on the 8B, and on AlpacaEval.

cs.AI · cs.CR

版本更新 · v3arXiv:2605.07013

CoBit: Language Modeling with Bitstream Diffusion

Georgios Batzolis, Mark Girolami, Luca Ambrogioni

原文摘要

We introduce CoBit, a continuous diffusion language model that generates text by jointly denoising fixed-width binary token codes. Grouping each code's bits into a single Transformer patch preserves sequence length while replacing vocabulary-wide predictions with $\lceil\log_2 V\rceil$ bit logits. A matched-filter residual parameterization supplies the analytic isolated-bit posterior, leaving the network to learn contextual corrections. Stochastic sampling on an entropy-rate grid provides the largest empirical gain; the grid allocates both solver resolution and effective Langevin correction to noise levels where information is resolved. At 256 denoiser evaluations, CoBit-S (130M parameters) achieves generative perplexity 59.76 on LM1B and 27.06 on OpenWebText, at unigram entropies 4.31 and 5.26, respectively. Scaling to 462M parameters improves OpenWebText generative perplexity to 19.48 at entropy 5.40. Beyond open-ended text generation, CoBit achieves 65.9% exact-match accuracy on hard Sudoku. On GSM8K, score-temperature scaling with an untempered final integration step raises CoBit-S accuracy from 28.1% to 35.3% without additional denoiser evaluations, placing it within the reported range of temperature-tuned discrete diffusion baselines. Matched-trunk profiling also shows lower peak memory and higher throughput than a dense token-output baseline.

cs.CL

版本更新 · v2arXiv:2602.06909

Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Models

Yunshi Wen, Wesley M. Gifford, Chandra Reddy, Lam M. Nguyen, Jayant Kalagnanam, Anak Agung Julius

原文摘要

The recent surge of interest in Time Series Foundation Models has rapidly advanced the field. Yet, heterogeneous training setups across studies make it difficult to determine whether performance improvements came from architectural innovations or effective data engineering. In this work, we investigate whether a standard patch Transformer architecture, paired with a straightforward training protocol, can match the zero-shot forecasting performance of state-of-the-art TSFMs. We conduct a comprehensive ablation study covering model scaling, data composition, and training techniques to examine the ingredients behind this performance. Our findings show that pretraining data composition, contiguous patch masking, and context length have a substantial effect on forecasting accuracy, and that the generic architecture itself can deliver high performance with good scalability. By strictly controlling these experimental variables, we provide comprehensive empirical results on model scaling across multiple dimensions. Furthermore, we establish that the effectiveness of this training protocol generalizes robustly across benchmarks and alternative architectures. We release our pretrained models and document the detailed training protocol and findings to establish a transparent, reproducible baseline for future research.

cs.LG