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

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描：2026-11-16 01:34 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 06:10 — 2026-11-16 06:10（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：2026-11-16 01:34最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

论文修订列表

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 6,729 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33（北京时间）
版本更新 · v3arXiv:2610.23002

Robotic Spatiotemporal Editing: A Unified Interface for Controllable Action Generation via Masked Action Reconstruction

Yanbang Li, Bu He, Yi Tian, Yu-Chiao Huang, Chenyu Zhang, Ruoqu Chen, Yuanzhe Liu, Yuxiang Gao 等 9 位作者

原文摘要

Generative policies can synthesize robot behaviors, yet controlling and editing them through diverse spatiotemporal references remains challenging. In the real world, human intent requires robot behaviors that satisfy constraints on where, when, and how actions are executed. Our key insight is that spatiotemporal control references, such as keypoints, flows, orientations, and keyposes, can be viewed as partial specifications of the same temporal Cartesian action space. We introduce the MAP (Masked Action Space) interface to unify these action references and formulate controllable manipulation as an action inpainting problem. Our Inpainting Policy (IP) reconstructs missing action dimensions of the end-effector, combining progress-guided alignment with multi-mask training supporting unseen action-constraint combinations. We further adopt a training-free RePaint variant that iteratively inpaints the action during denoising to reduce control error. On ManiSkill and LIBERO-10, our policy achieves average task success rates of 92.67% and 64.67%, respectively.Real-world experiments demonstrate spatiotemporal control with average positional and rotational errors of 44.3 mm and 7°, respectively, showing that our policy can use diverse references to guide executable robot behaviors.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04371

Embodied AI for Scientific Discovery: From Physical Action to Scientific Evidence

Wenhao Xu, Changwei Wang, Shunpeng Chen, Yukun Song, Sifan Zhou, Kaize Luo, Shibiao Xu, Yuehua Zhao 等 9 位作者

原文摘要

Scientific experiments are increasingly selected, executed and interpreted by learned systems that act through physical interfaces. Robot learning builds physical competence, whereas AI for science chooses which experiment to run, each reporting different endpoints. This review treats their interface as one problem, embodied AI for science, where the experiment itself is partially observed: specimen state, apparatus state and measurement processes are latent, actions are costly and irreversible, and missingness depends on execution and outcome. We organize the literature by three closures operating at distinct levels: operational closure (the experiment realized is the one intended), epistemic closure (the result updates beliefs or selects subsequent experiments) and evidential closure (the record supports a claim). We analyze workflows through a record-linked evidence cycle - Record, Diagnose, Calibrate, Confirm - as analytic functions with feedback. A taxonomy crosses these closures with six delegated decisions and five embodiment classes. Our formulation separates commanded, realized and observed conditions and models diagnosis with explicit resource, risk and sample-change costs. We compare experiment-selection methods by terminal decision, review perception, protocol compilation, visuomotor policies, world models, recovery and transfer by evidence emission requirements, and compare chemistry, materials, biology, microscopy and field workflows by what their records establish. An appendix provides an evidence map of 28 workflows (26 physical, two software-boundary), characterizing validation pathways and claim confirmation requirements. We propose evaluation that separates actions, valid experiments, campaigns and confirmed claims, framing open challenges as controlled comparisons with measurable failure conditions.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2511.09895

SE-Diff: Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generation

Xiaoda Wang, Kaiqiao Han, Yuhao Xu, Xiao Luo, Yizhou Sun, Wei Wang, Carl Yang

原文摘要

Cardiovascular disease (CVD) is a leading cause of mortality worldwide. Electrocardiograms (ECGs) are the most widely used non-invasive tool for cardiac assessment, yet large, well-annotated ECG corpora are scarce due to cost, privacy, and workflow constraints. Generating ECGs can be beneficial for the mechanistic understanding of cardiac electrical activity, enable the construction of large, heterogeneous, and unbiased datasets, and facilitate privacy-preserving data sharing. Generating realistic ECG signals from clinical context is important yet underexplored. Recent work has leveraged diffusion models for text-to-ECG generation, but two challenges remain: (i) existing methods often overlook the physiological simulator knowledge of cardiac activity; and (ii) they ignore broader, experience-based clinical knowledge grounded in real-world practice. To address these gaps, we propose SE-Diff, a novel physiological simulator and experience enhanced diffusion model for comprehensive ECG generation. SE-Diff integrates a lightweight ordinary differential equation (ODE)-based ECG simulator into the diffusion process via a beat decoder and simulator-consistent constraints, injecting mechanistic priors that promote physiologically plausible waveforms. In parallel, we design an LLM-powered experience retrieval-augmented strategy to inject clinical knowledge, providing more guidance for ECG generation. Extensive experiments on real-world ECG datasets demonstrate that SE-Diff improves both signal fidelity and text-ECG semantic alignment over baselines, proving its superiority for text-to-ECG generation. We further show that the simulator-based and experience-based knowledge also benefit downstream ECG classification.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.00635

FlowPilot: Real-Time World-Action Modeling for Agile UAV Navigation

Runqing Wang, Ding Yu, Pengyuan Min, Xinhong Zhang, Wei Xiao, Yu Hu, Jie Chen, Fu Zhang 等 9 位作者

原文摘要

We present FlowPilot, the first world-action model for real-time onboard UAV navigation from depth. Unlike map-then-optimize pipelines that require local reconstruction or end-to-end policies that lack explicit scene prediction, FlowPilot jointly denoises future depth observations and executable trajectories with flow matching. A dual-stream mixture-of-transformers couples video and action experts through shared attention, allowing future-scene prediction and trajectory generation to inform each other. At deployment, the model runs action-centrically and outputs only a trajectory. To generate smooth, state-consistent references, actions are parameterized as degree-7 Bernstein polynomials: the current state constrains the initial control points, and the network predicts five free control points, yielding C^2-continuous references with closed-form velocity, acceleration and jerk. FlowPilot is trained on a three-level depth pyramid spanning high-throughput simulation, photorealistic simulation, and real onboard data. In closed-loop simulation, it outperforms learning- and optimization-based baselines under increasing clutter and commanded speeds up to 10 m/s. On a physical quadrotor, FlowPilot achieves a mean inference latency of 10.2 ms on a Jetson Orin NX and reaches a peak speed of 10 m/s during outdoor flight using only onboard sensing and computation.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.12541

PPG2ECG: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation

Xiaoda Wang, Minxiao Wang, Kaiqiao Han, Defu Cao, Ching Chang, Yidan Shi, Runze Yan, Xiao Luo 等 13 位作者

原文摘要

Electrocardiography (ECG) is the clinical standard for cardiac assessment but requires dedicated hardware that does not scale to daily-life monitoring. Photoplethysmography (PPG) is ubiquitous in wearables but lacks ECG-specific diagnostic morphology and is corrupted by motion and sensor noise. PPG-to-ECG generation aims to bridge this gap by recovering electrical morphology and timing from peripheral pulse signals. However, existing methods largely rely on statistical alignment and data-driven generation. They fail to explicitly structure the latent space around physiology-aware electro-hemodynamic factors and lack constraints from forward physiological dynamics. To address these challenges, we propose PPG2ECG, a physiology-guided latent rectified flow framework. PPG2ECG introduces an electro-hemodynamic simulator that co-models ECG and PPG through shared cardiac phase dynamics. Guided by this simulator, a Physiology-Aware AutoEncoder learns a structured electro-hemodynamic latent space. Then we integrate this simulator guidance into a PPG-conditioned latent rectified flow, enforcing ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency during generative transport. Experiments on the large-scale MC-MED dataset demonstrate that PPG2ECG significantly improves PPG-to-ECG generation and downstream cardiovascular disease classification, proving its ability to generate ECGs that are both signal-faithful and physiologically plausible under the ECG-to-PPG hemodynamic pathway

eess.SP · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.07665

AgentCompile: An LLM-Guided Compiler for Direct CUDA Inference

Xuanzhe Li, Ziyan Weng, Zhiyu Zhu, Junhui Hou

原文摘要

Transformer inference increasingly relies on specialized compiler and runtime support, while recent LLMs can generate nontrivial CUDA kernels. However, unconstrained generation guarantees neither correctness nor performance. We present \textsc{AgentCompile}, an LLM-guided CUDA inference compiler that combines two complementary uses of LLMs. First, the LLM provides advisory metadata for compiler-derived region summaries and bounded candidate spaces. The compiler then instantiates template-based CUDA candidates, validates correctness, selects implementations by measured latency, and falls back when specialization is unsupported or unprofitable. Second, under compiler-defined contracts, the LLM directly generates five classes of decode-critical kernels to accelerate inference, prompted by distilled optimization principles. \textsc{AgentCompile} integrates these kernels into a serving runtime with paged KV cache, continuous batching, preemption, chunked prefill, and bucketed full-step CUDA Graph replay. Across six evaluated model families, \textsc{AgentCompile} achieves speedups of \textbf{2.23--6.98$\times$} over PyTorch eager for single-request generation, and \textbf{1.04--1.16$\times$} over vLLM for both single-request generation and multi-request serving. Our code is publicly available at https://github.com/veneno1213822/AgentCompile.

cs.PL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.12492

Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation

Kexuan Shi, Hanxuan Li, Zeju Qiu, Yandong Wen, Simon Buchholz, Weiyang Liu

原文摘要

We introduce Pion, a spectrum-preserving optimizer for large language model (LLM) training based on orthogonal equivalence transformation. Unlike additive optimizers such as Adam and Muon, Pion updates each weight matrix through left and right orthogonal transformations, preserving its singular values throughout training. This yields an optimization mechanism that modulates the geometry of weight matrices while keeping their spectral norm fixed. We derive the Pion update rule, systematically examine its design choices, and analyze its convergence behavior along with several key properties. Empirical results show that Pion offers a stable and competitive alternative to standard optimizers for both LLM pretraining and finetuning.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.21160

FISolver: Data-Driven Discovery of First Integrals via Backward Generation and Guided Reinforcement Learning

Jingfeng Zhong, Zhengxiang Liu, Zhijie Wang, Shuai Li

原文摘要

The discovery of first integrals is of profound scientific significance for understanding physical conservation laws in dynamical systems. However, existing symbolic computation systems and Large Language Models (LLMs) struggle with this task due to the scarcity of high-quality training data and the reliance on mathematical intuition for finding solutions. This paper introduces FISolver, an LLM-based solver designed to bridge this gap. First, we propose a novel "Backward Generation" algorithm that systematically constructs large-scale datasets of (differential equations, first integrals) pairs by deriving equations from sampled integrals, effectively overcoming the data scarcity bottleneck. Second, we perform supervised fine-tuning on a compact mathematical model and further enhance its capabilities using reinforcement learning with a Levenshtein Distance-based shaped reward function. Additionally, we introduce data synthesis and blending techniques that enable effective adaptation to specific hard instances with sparse examples. Experiments demonstrate that FISolver, with significantly lower computational cost, substantially outperforms larger mathematical LLMs and commercial solvers like Mathematica on complex benchmarks, establishing a new data-driven paradigm for automated mathematical discovery.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.02068

Sequential Capacity of Quantum Processes with Finite Memory

Yibin Wang

原文摘要

How complex can the responses of a quantum process become as it runs longer with fixed internal memory? We measure this complexity by sequential response capacity, the depth of an adaptive tree of experiments whose acceptance probabilities separate possible processes by a prescribed gap. Each experiment uses a fresh complete run, and one fixed process must realize every response along a path. For any fixed common visible dimension of at least two and internal memory cap, we prove that capacity has order $K\log((K+1)/γ)$ for $K$ transitions per run and probability gap $0<γ\leq1$. Time-dependent single-qubit phase channels without internal memory already attain the fixed-gap $K\log K$ growth, realizing each path with zero-or-one response probabilities. Under the same tester permissions, classical stochastic processes that measure in a fixed basis at every transition have only linear capacity at fixed dimensions and gap. For phase sequences selected by a classical address stored inside the process, we then quantify how known independent Pauli noise changes this logarithmic enhancement. With ideal tester controls and weak residual phase noise after correction, we prove matching capacity bounds at a fixed small gap. At fixed address size and fixed positive residual noise, the logarithmic enhancement saturates once the phase-sequence length exceeds the inverse noise scale, and capacity then grows linearly with sequence length.

quant-ph · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.12190

Information-Theoretic Generalization Bounds for Sequential Decision Making

Futoshi Futami, Masahiro Fujisawa

原文摘要

Information-theoretic generalization bounds based on the supersample construction are a central tool for algorithm-dependent generalization analysis in the batch i.i.d. setting. However, existing supersample conditional mutual information (CMI) bounds do not directly apply to sequential decision-making problems such as online learning, streaming active learning, and bandits, where data are revealed adaptively and the learner evolves along a causal trajectory. To address this limitation, we develop a sequential supersample framework that separates the learner filtration from a proof-side enlargement used for ghost-coordinate comparisons. Under a row-wise exchangeability assumption, the sequential generalization gap is controlled by sequential CMI, a sum of roundwise selector--loss information terms. We also establish a Bernstein-type refinement that yields faster rates under suitable variance conditions. The resulting bounds specialize to online learning, streaming active learning with importance weighting, and stochastic multi-armed bandits.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2401.07174

On the (In)Compatibility between Group Fairness and Individual Fairness

Shizhou Xu, Thomas Strohmer

原文摘要

We study the compatibility between utility-optimized statistical parity and individual fairness. While individual fairness seeks to treat similar individuals similarly, optimal statistical parity aims to provide similar treatment to individuals who share relative similarity within their respective sensitive groups. Although both fairness perspectives are desirable, they often conflict in practical applications. Our goal in this work is to analyze the existence of this conflict and its potential solution. In particular, we establish sufficient (sharp) conditions for the compatibility between the optimal (post-processing) statistical parity $L^2$ learning and the ($K$-Lipschitz or $(ε,δ)$) individual fairness requirements. When a conflict arises, we first relax the optimal statistical parity solution to the Pareto frontier, representing the optimal trade-off between $L^2$ error and statistical disparity, and then examine its compatibility with individual fairness. Our analysis identifies regions along the Pareto frontier that satisfy individual fairness constraints. Additionally, we provide individual fairness guarantees for the composition of a trained model with the optimal post-processing step, enabling practitioners to assess the compatibility of post-processed models. This provides practitioners with a principled approach to achieving Pareto-optimal statistical parity while maintaining individual fairness constraints.

math.ST · cs.CY · cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.08315

Reusable Conditional Resampling via Flow Matching for Constraint-Based Causal Discovery

Shunyu Zhao, Yanfeng Yang, Shuai Li, Kenji Fukumizu

原文摘要

Constraint-based causal discovery requires many conditional independence (CI) tests. Generative CI tests are attractive in nonlinear and high-dimensional settings because they can model complex conditional distributions, but often suffer from high per-test costs and limited reusability across query-dependent conditional resampling tasks in graph search. We propose a generative nonlinear CI testing and graph search framework for PC-style causal discovery. We introduce Langevin-RePaint for conditional imputation. Building on Langevin-RePaint and joint flow matching modeling, we propose the Flow Matching based Conditional Independence Test (FMCIT), which reformulates generative CI testing from query-specific conditional modeling into a reusable conditional resampling framework. We establish theoretical guarantees for FMCIT's type-I error control. FMCIT reuses a single trained generative model to generate randomized copies throughout graph search. We then introduce GPC-FMCIT, which embeds FMCIT into a guided PC pipeline with screening, guidance, refinement, and orientation. By using low-cost screening to shrink the search space, constructing edge-specific candidate conditioning sets from local graph structure, and invoking FMCIT only in a budget-controlled refinement stage, GPC-FMCIT reduces both the deployment cost of individual nonlinear CI queries and the overall query complexity. On synthetic nonlinear structural equation models, GPC-FMCIT improves CPDAG recovery over PC-stable baselines and requires far fewer FMCIT queries than direct FMCIT-based PC search, and on hESC gene-expression data it yields smaller graphs than PC/FisherZ in a descriptive comparison. Overall, our results suggest that, through the joint design of reusable conditional resampling and controlled graph search, generative nonlinear CI testing can become a practical component of PC-style causal discovery.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.01472

Causal Optimal-Transport Attention: Positional Priors and Length Extrapolation

Ming Lian

原文摘要

Causal masking obstructs the column balancing used by optimal-transport (OT) attention. We study an unbalanced OT operator that uses only current and earlier rows and characterize its induced positional prior. For bounded scores and any fixed balancing strength below one, its fixed point assigns vanishing mass to every fixed window as context grows. With constant scores, the prior has an exact scale-invariant form. We classify positional encodings by whether they prevent this dilution. We also derive finite-length window-mass bounds for log-distance priors with exponents near one. Preregistered experiments use 25M- and 100M-parameter language models. The OT operator improves loss extrapolation over softmax, while exploratory comparisons favor an explicit distance bias at a fraction of the cost. Changing only the bias beyond the training length moves long-context loss in the predicted direction on all 30 tested checkpoints. During training, learned exponents approach one even when constrained above it. A margin chosen from prior calculations controls distant-mass growth in the tested setting.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.39383

From Search to Signal: Search-Value Credit for Evolutionary Automatic Heuristic Design

Yilun Yuan, Tianyu Zhou, Zhenzhou Tang

原文摘要

Large language models generate candidate programs for automatic heuristic design, while evolutionary search evaluates and selects them to guide further generation. Online post-training uses rewards from candidate evaluations to adapt the generator. Retained programs can also guide later generation as parents. This motivates rewards that reflect their reuse opportunities beyond immediate fitness. We propose Search-value credit (SVC), which constructs response-level rewards from actual admission to the retained set and a short-term parent-exposure proxy. Admission determines reward eligibility; the proxy weights eligible responses by reuse opportunities under existing parent-selection rules. Rewards are computed after candidate evaluation, without evaluating descendants. SVC retains the search and learning procedures of the Co-Evolution of Algorithms and Language Model (CALM) framework. Across four combinatorial optimization tasks with the same base model and response budget, SVC achieves the best mean final search performance on three tasks among six conditions. Under identical prompts and parents on traveling salesman and capacitated vehicle routing tasks, SVC-trained generators yield a higher mean proportion of responses whose programs outperform the best prompting parent than those trained with CALM's native reward. These findings support reward construction using search retention and selection information.

cs.LG · cs.AI · cs.NE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.05709

Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction-Concealment Tradeoff in MLLMs

Md Farhamdur Reza, Richeng Jin, Tianfu Wu, Huaiyu Dai

原文摘要

Intent-obfuscation-based jailbreak attacks on multimodal large language models (MLLMs) transform a harmful query into a concealed multimodal input to bypass safety mechanisms. We study these attacks through the lens of a reconstruction-concealment tradeoff: the transformed input must sufficiently obscure harmful intent while preserving enough information for the victim model to recover the underlying request. Through a reconstruction and concealment analysis of representative black-box methods, we find that existing transformations struggle to balance this tradeoff, limiting their effectiveness. In contrast, we show that character-removed variants, constructed by randomly removing characters from the original query, achieve a better balance, motivating their use as the basis for our attack construction. Building on this observation, we propose concealment-aware variant construction, which selects character-removed variants with low harmful keyword/phrase alignment and high mutual diversity, and instantiates them through five prompting strategies that distribute the transformed information across text and image channels. We further introduce keyword/phrase-related distractor images that depict the harmful concept in diverse contexts, providing more effective distraction than generic distractor images. Experiments across diverse closed-source and open-source MLLMs show that the proposed strategies substantially outperform the evaluated baselines. Code and reproduction instructions are available at https://github.com/Farhamdur/CRJ.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2605.14322

Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows

Zixin Chen, Peng Liu, Rui Sheng, Haobo Li, Jianhong Tu, Xiaodong Deng, Kashun Shum, Dayiheng Liu 等 9 位作者

原文摘要

Language agents are increasingly deployed in professional workflows, yet tutoring remains a high-stakes capability that existing evaluations only partially capture. Effective tutor agents require more than producing correct answers or executing accurate tool calls: they must infer a warranted teaching decision from evidence, adapt support as learner state changes, and carry an instructor's request through a learning-management system (LMS) to a completed, verified intervention. We introduce TeachArena, a source-grounded benchmark that jointly evaluates three complementary surfaces of teaching work: professional pedagogical judgment, situated multi-turn tutoring, and end-to-end LMS teaching workflows. Its 354 tasks are each built around a pedagogical insight, grounded in evidence, and evaluated with matched verifiers over observable turn-level responses, tutoring trajectories, and persistent artifacts or environment states. Across a comprehensive evaluation of frontier models, our findings reveal that current models are generally capable of bounded pedagogical judgment, but still fall short of professional teaching standards in situated tutoring and end-to-end teaching-workflow execution. By unifying teacher judgment, adaptive tutoring, and institutional action in one benchmark, TeachArena provides a measurement foundation for developing tutor agents that can support realistic teaching work.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.17162

OraclePhys: A Systematic Framework for LLM Fine-Tuning on Structural Mechanics

Mingyu Li, Guorui Song, Jing Lin, Haoqian Wang

原文摘要

What fine-tuning teaches a model is usually diagnosed after the fact. We make it an experimental variable. OraclePhys has three parts. OraclePhys-Bench is a structural-mechanics benchmark whose finite-element oracle grades every answer and counterfactual edit. OraclePhys-30K holds seven answer forms over byte-identical structure descriptions. A controlled training study compares the forms and verifier roles. Two findings follow. First, within this task family the answer form of the label determines what fine-tuning teaches. Ranking supervision lifts held-out localization of the most-deforming story on taller structures from 0.25 to 0.86, a peak-value label yields at best a partial predictor, and a pass/fail label none. This ranking-versus-peak gap replicates on a second domain, a second model family and a paraphrased surface. Second, the gap between our standard SFT and GRPO runs is mostly a recipe effect. With learning rate and step budget matched, the two reach held-out accuracies within 0.03 of each other. At higher rates, GRPO falls below its start while SFT does not. Both also teach the model to apply edits given as instructions. The trained 8B matches a specialist and exceeds a frontier LLM. Both domains are linear, steady-state systems with synthetic text inputs.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.39070

When the Same Prompt Gives Different Answers (and the Same Answer Isn't Always Right): A Taxonomy of Failure Mechanisms, Testing, and Mitigation Strategies for LLM-Assisted Evidence Synthesis Read-and-Evaluate Tasks

Carole Lunny, Ian Goodman, Stefano Berrone, Connor TA Brenna, Emma K Reid, Ivan Perez-Neri, Shailesh Kolekar, Nityanand Jain 等 15 位作者

原文摘要

LLM read-and-evaluate tasks include study screening, data extraction, risk-of-bias assessment, and critical appraisal in the evidence synthesis field. These task differ in the amount of LLM interpretation they require. Some tasks involve retrieving relatively simple information, such as an author name, sample size, or publication year. Others require the LLM to read source material, interpret it against predefined criteria, and make a judgement. Researchers should assess whether LLM judgements are accurate, supported by appropriate source evidence, and reproducible under specified conditions. A correct judgement does not necessarily indicate that the underlying evaluation process is reliable. We developed a taxonomy for identifying mechanisms that may compromise these properties and for informing the selection and reporting of appropriate evaluation methods. The taxonomy outlines potential ways that LLM judgments from read-and-evaluate tasks can fail, called TRAILS (Taxonomy of Reliability And Instability in LLM-assisted evidence Synthesis). The TRAILS taxonomy addresses two complementary questions. First, what mechanisms can cause the same read-and-evaluate task to produce different judgements across repeated LLM runs? Second, what mechanisms can systematically affect the judgement or required output in a way that is not apparent from the judgement itself? This study presents 38 mechanisms and identifies the deployment settings in which each can operate, approaches for testing them, and mitigation strategies. We also show why repeatability or accuracy does not rule out a hidden judgement failure and why human evaluation should assess whether a judgement is grounded in the supplied evidence, independent of inappropriate external influence, and produced through a process that can be examined and verified.

cs.AI · cs.PF · stat.ME

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.03014

MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency

Saptarshi Mitra, Yifan Zhang, Rachid Karami, Sreetama Sarkar, Phyo Pyae Moe Aung, Nazmul Takbir, Souvik Kundu, Sitao Huang

原文摘要

Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs. Efficiently executing this workload on limited GPU resources has bottlenecks. Skill-based routing creates skewed expert demand, and combining instruction-tuned LLMs with long-reasoning models results in extreme variability in generation lengths. Consequently, traditional scheduling strategies suffer from significant GPU idling and throughput collapse due to load imbalances. We present MOSAIC, a scheduling framework for accelerating batch-oriented MoA workloads. MOSAIC uses two-stage workload-aware scheduling: an expert placement stage, where an integer linear program (ILP) decides expert placement, followed by a query-sequencing stage that schedules requests based on predicted output lengths. Additionally, MOSAIC uses confidence-aware adaptive aggregation, leveraging inter-expert agreement to bypass the heavy aggregator LLM for consensus queries. On a 4-GPU system, MOSAIC achieves 2.7-3.4x end-to-end speedups over round-robin scheduling and reduces the mean time-to-answer by 3.9-7.8x, while matching accuracy within +/-1pp.

cs.LG · cs.AR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.30946

Tracing Hallucinations in LLM Reasoning for UML Class Diagram Generation: An Empirical Taxonomy and Mitigation Study

Mojdeh Rahmanian, Foutse Khomh, Yanchao Yu, Ashkan Sami

原文摘要

Large Language Models (LLMs) can generate UML class diagrams from natural language requirements, but hallucinations may compromise the correctness and completeness of the resulting diagrams. Existing evaluations mostly assess the final diagram, without examining the intermediate traces of reasoning-capable LLMs, which can reveal where these hallucinations arise. We develop an empirical taxonomy of eleven hallucination sub-types organised into three dimensions: Prompt Faithfulness (deviations between requirements and reasoning), Code Faithfulness (discrepancies between reasoning and generated PlantUML code), and Reasoning Quality (problems within the reasoning). The taxonomy was derived from 60 manually annotated DeepSeek-R1 traces, applied to 120 further DeepSeek-R1 traces through a dual-LLM annotation pipeline, and examined on 20 DeepSeek-V4-Pro traces. Code Faithfulness was the most frequent dimension for DeepSeek-R1 in both datasets, whereas Prompt Faithfulness dominated for DeepSeek-V4-Pro, suggesting model-dependent failure patterns. In the manually annotated traces, reasoning-trace length showed no significant monotonic association with hallucination frequency, whereas requirement complexity was negatively associated with it, particularly for Prompt Faithfulness errors. In a mitigation experiment on 13 Golden UML ModelSet cases with three Qwen3-based models, adding Prompt Faithfulness and Reasoning Quality constraints to the generation prompt raised the pooled mean F1 score by 4.0 percentage points, whereas a post-hoc Code Faithfulness review provided no consistent further benefit. Relationship modelling remained the lowest-scoring element throughout. These results suggest that localising hallucinations within the generation process can inform targeted, prompt-based mitigation. Whether these findings generalise beyond the DeepSeek and Qwen3 model families remains to be tested.

cs.SE · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.07365

Private Sparse Sketches for Linear Regression

Shrutimoy Das, Anirban Dasgupta

原文摘要

Sketching compresses a large dataset into a smaller summary, allowing regression on the sketch to approximate the full-data objective. A sketch released under differential privacy can be reused with any non-private regression solver, any number of times, without further privacy loss. We study private sparse sketches for $\ell_2$ and $\ell_1$ regression. We first prove lower bounds on the noise required by common sparse sketches for both problems when the sketching matrix is public. Since regression on a sketch can be solved without revealing the sketching matrix, we construct sketches whose randomness is kept secret. Hiding how individual records enter the sketch provides an additional source of privacy, allowing less noise for the same privacy guarantee. We prove differential privacy guarantees for both constructions, and experiments on real datasets show improved utility over public-sketch baselines.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.02915

ChemBART: Pre-training a Reaction Language Model for Comprehensive Synthesis Planning

Kenan Li, Yijian Zhang, Jin Wang, Haipeng Gan, Zeying Sun, Xiaoguang Lei, Hao Dong

原文摘要

Recent advances in large language models (LLMs) have demonstrated transformative potential across diverse fields. However, in computer-aided synthesis planning (CASP), current LLM methodologies are often restricted to single-molecule representations, limiting their application to isolated, single-task scenarios such as precursor prediction. Addressing this gap, we present ChemBART, a BART-based language model that adopts a reaction-centric pre-training strategy. By leveraging a mask-filling pre-training task on holistic reaction expressions (Reactant > Reagent > Product), ChemBART effectively solves a variety of chemical problems, including precursor/reagent generation, temperature-yield regression, and molecular property classification. The reaction-centric pre-training further enables the integration of ChemBART with Monte Carlo tree search (MCTS) for multi-step synthesis route design, where the model serves to optimize the policy and value functions within a reinforcement learning framework. Beyond single-molecule pre-trained LLMs that are constrained to specific applications, ChemBART unifies diverse chemical tasks to facilitate synthesis planning with comprehensive implementation information. Most significantly, the proposed multi-step synthesis routes and reaction conditions were validated in the wet lab, confirming the discovery of shorter synthetic pathways with a >20% yield improvement over established literature benchmarks. Our work highlights the potential of reaction-focused pre-training and showcases the broad utility of ChemBART in closing the loop between in silico prediction and wet-lab synthesis.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.08884

Beyond RGB: Benchmarking and Enhancing MLLMs for Hyperspectral Image Understanding via Training-Free Reasoning Framework

Xinyu Zhang, Zurong Mai, Qingmei Li, Xiaoya Fan, Zjin Liao, Haoyuan Liang, Yibin Wen, Yuhang Chen 等 16 位作者

原文摘要

Multimodal Large Language Models (MLLMs) have achieved strong performance on RGB image understanding, yet their ability to use spectral evidence beyond the visible range remains largely unexplored. Hyperspectral imagery (HSI) provides dense spectral measurements that reveal material and environmental cues unavailable in RGB, but current MLLMs cannot directly ingest high-dimensional HSI. To study this gap, we introduce HM-Bench, an evidence-grounded benchmark for hyperspectral image understanding with MLLMs. HM-Bench contains 19,337 question--answer pairs from 2,178 hyperspectral samples across 13 task categories, covering general perception, spectral reasoning, and spatial--spectral reasoning. To make HSI accessible to the native image--text interfaces of existing MLLMs, we further propose VSR$^{2}$, a training-free Visual--Spectral--Report Reasoning framework. VSR$^{2}$ represents each HSI sample with three aligned views: an RGB image for visual semantics and spatial context, a PCA-based image for dominant spectral variation, and a structured report for quantitative spectral--spatial evidence. Under a controlled RGB-only versus VSR$^{2}$ evaluation protocol, experiments on 17 representative MLLMs show that HSI information improves average accuracy from 38.90% to 40.95%, with gains varying substantially across models and task categories. These results indicate that HSI information (beyond RGB) is useful for current MLLMs, while robust hyperspectral reasoning remains an open challenge.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.08140

FATE: Fault-Aware Transfer Error for Unsupervised Anomaly Detection

Tao Wang

原文摘要

We study unsupervised industrial anomaly detection in the single-class setting, where a detector learns only from normal images of one product category. Reconstruction-based detectors model normal features from a frozen encoder, but their target layers are usually chosen by architectural convention. We instead ask what information one block can pass to another. Treating depth as a sequence of discrete transitions, we train eight directed, token-wise predictors from block 1 and blocks 21-23 to blocks 7 and 14. Adjacent-layer cosine similarity drops at four repeatable fault lines in DINOv2 ViT-L, separating stable depth segments. The deepest blocks retain semantic context but lose local detail, so the residual of a source-to-sensitive prediction measures information that cannot be transported. The fault structure constrains the source and target roles, and the same rule transfers to ViT-B and RADIO-B. A bounded foreground prior, calibrated only on normal training images, suppresses background residuals while retaining a positive floor for evidence outside the estimated foreground. With the same eight channels and a common training-only calibration procedure in every single-category model, category-averaged image AUROC reaches 99.75 on MVTec-AD, 99.42 on VisA and 94.27 on Real-IAD; object-level AUROC on Real-IAD is 96.26. For the 448x448 runs, category-averaged P-AUROC/P-AUPRO on a common 256x256 evaluation grid is 98.46/95.97 on MVTec-AD, 99.21/96.12 on VisA and 99.26/96.59 on Real-IAD.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.01425

Why Does Train-Validation Separation Emerge? Update-Pressure Density Dynamics in Pretrained Backbones

Yuchen Li, Zongqi Fan, Ken-Tye Yong, Nguyen H. Tran

原文摘要

During fine-tuning, training accuracy often continues to improve after validation accuracy levels off, widening the empirical gap. We propose a support-transfer account: early updates reuse broadly shared structure, while later fitting relies increasingly on narrower structure with less benefit for held-out examples. From fixed training probes, we normalize per-example gradient magnitudes and measure their pooled dispersion, $D_{\mathrm{den}}$, and their probe-count-weighted within-class dispersion, $D_{\mathrm{within}}^{\mathrm{wt}}$. A local model gives conditions for dispersion and directional cross-entropy separation to grow together, separating uniform logit scaling; additional decision-boundary conditions characterize accuracy-gap growth. A controlled five-level hierarchy tests the effect of sample-private support. A 240-branch intervention matrix crosses training-progress anchors, batch sizes, private shares, and gradient-differentiation doses. The negative gap dose response is clearer at later training stages and is retained across the four batch sizes. A further 48 branches replicate its direction across additional seeds at a fixed stage and batch. Both normalized readouts are positively associated with the accuracy gap in all 90 language fine-tuning runs across three backbones and six tasks. The same direction holds in all 20 vision runs across four datasets. Together, the controlled hierarchy, targeted intervention, and real-model trajectories support a connection between evolving gradient differentiation and train-validation separation.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.23522

Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models

Jade Zou, Tao Huang, Weijie Kong, Junzhe Li, Yue Wu, Qi Tian, Jiangfeng Xiong, Jianwei Zhang 等 10 位作者

原文摘要

Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic sampling trajectory into a stochastic policy, typically by replacing the reverse-time Ordinary Differential Equation (ODE) with a Stochastic Differential Equation (SDE). The stochastic sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy, and its design can significantly affect the reward optimization performance. We break down the sampler design into two interdependent components: choosing the right amount of stochastic exploration, and discretizing the resulting SDE faithfully at the small step counts used in RL. To address the first component, we analyze the inherent tension between exploration and stability in denoising and derive an SDE schedule that balances the two. Turning to the discretization challenge, we use a toy example to show that existing samplers can deviate from the flow-matching process, either by introducing excessive discretization noise or by relying on heuristic rules that do not guarantee convergence to the data distribution. To address these issues, we propose Precise, a new stochastic sampler that balances effective exploration with stability. Crucially, Precise keeps the denoising trajectory SDE-consistent through a novel approximation that freezes the clean-latent posterior mean, resolving the excess noise issue in standard samplers. Extensive experiments demonstrate that this formulation leads to significantly faster and more stable reward optimization via reinforcement learning, achieving state-of-the-art alignment scores (e.g., PickScore, HPSv2.1) while requiring 13.1-53.2% less wall-clock training time to match the best in-domain performance of prior samplers.

cs.LG · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.12616

PersonaDrive: Human-Style Retrieval-Augmented VLA Agents for Closed-Loop Driving Simulation

Mahmoud Srewa, Praneetsai Vasu Iddamsetty, Mohammad Abdullah Al Faruque, Salma Elmalaki

原文摘要

Closed-loop driving simulators mostly fill their environments with traffic agents that behave alike, whether they are rule-based or learned. Recent methods that control driving style learn it from labels inferred from existing driving recordings, from synthetic data generated to reflect each style, or from reward weights estimated by a large language model (LLM). All of these are indirect estimates of a style, not recordings of people who were instructed to drive in it. We introduce PersonaDrive, a vision-language-action (VLA) driving agent that takes its style from retrieved human demonstrations. The demonstrations come from a new dataset in which 15 participants drove CARLA routes on a driving simulator under conservative, neutral, and aggressive instructions. PersonaDrive trains a lightweight retrieval head on features from a frozen image encoder and on control signals over per-style databases, and fine-tunes one VLA backbone over the retrieved demonstrations. Switching style only means searching a different FAISS index, with no retraining. On the Bench2Drive benchmark without style conditioning, PersonaDrive improves the Driving Score by 4.6% over SimLingo and by 2.5% over HiP-AD, a gain that fine-tuning without retrieval does not reproduce. With style conditioning, PersonaDrive outperforms the strongest baseline, Drive My Way, in every style, with a Driving Score 6.7% to 11.6% higher. Its driving also follows the instruction, since average speed rises by 19.8% from the conservative to the aggressive style. Each traffic agent is evaluated individually as a driving policy. The dataset and model weights are available on the project page: https://pervasiveautonomylab.github.io/personadrive-landpage/.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.01077

Multi-Turn Semantic Caching for Low-Cost LLM Serving

Baran Atalar, Selly Beyene, Xutong Liu, Carlee Joe-Wong

原文摘要

Semantic caching lowers the cost of serving large language models (LLMs) by reusing stored responses for similar requests. In multi-turn conversations, whether a cached response is acceptable depends on both conversations' histories, which embedding similarity of requests and histories predicts poorly (AUC 0.62--0.74 on five workloads). We therefore learn the \emph{reuse risk}, the probability that a cached response is unacceptable, from judge feedback, and choose a budgeted set of conversation states to cache by weighing the generation cost a reuse avoids against a price for unacceptable reuse. We propose CUCB-SC-MT, which learns a cache from logged conversations with a suboptimality guarantee, and CLCB-LS-MT, which learns online and has $\tilde O(\sqrt N)$ regret over $N$ requests when conversation states recur. On math-tutoring (SocraTeach) and movie-ticketing (Taskmaster-3) conversations, both achieve lower loss than prior semantic caching approaches: ContextCache, multi-turn variants of ElastiCache and vCache, and single-turn semantic caching at every cache budget. With 1,000 cache entries, CLCB-LS-MT avoids 35--41\% of the generation cost through acceptable reuses, against at most 22--25\% for the baselines, and lowers estimated serving latency by 19--35\%.

cs.LG · cs.CL · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.24093

The Power of Menus in Dynamic Pricing: Optimal Regret and Equivalence Results

Shiliang Zuo

原文摘要

We study dynamic pricing where a seller repeatedly interacts with a strategic, non-myopic buyer who has a fixed private valuation and discounts future utility. Prior work focused exclusively on posted-price mechanisms, where the seller gives a take-it-or-leave-it offer. For our first result, under geometric discounting $γ_t = γ^{t-1}$, we show that menu mechanisms consisting of allocation-payment contracts achieve $O(T_γ)$ regret, where $T_γ$ is the buyer's effective discounted time horizon. We also establish a $Ω(T_γ)$ lower bound, demonstrating the bound is tight. Considering the geometric discounting buyer with a constant discount factor, our bound is $O(1)$, while prior bounds using posted-price mechanisms incur an unavoidable $Ω(\log\log T)$ factor in regret. Our second contribution is more conceptual in nature. The problem of dynamic pricing sits at the intersection of two paradigms: learning with strategic agents in computer science / machine learning and revelation-principle-based mechanism design in economics, yet their relationship has remained unclear. We establish an equivalence between these two classes of mechanisms in our single-buyer setting: any adaptive indirect menu mechanism can be converted into an incentive-compatible direct mechanism with no less revenue, and conversely, any such direct mechanism can be implemented by an adaptive indirect menu mechanism with no less revenue. Consequently, the two classes achieve identical optimal regret. The adaptive, data-driven algorithms of online learning and explicit type elicitation from direct revelation type mechanisms are two languages towards solving the same problem.

cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34248

HNSecW: A Logarithmic-Time MPC Protocol for Approximate Nearest Neighbor Search

Fahong Zhang, Weijie Jin, Lixu Wang, Ning Luo, Xiao Wang, Wei Dong

原文摘要

As a core component of modern RAG systems, approximate nearest neighbor (ANN) search has been extensively studied for decades. In practice, deploying ANN often requires symmetric privacy, where the querier's query and the database owner's data must remain hidden from each other, necessitating a secure multi-party computation (MPC) solution. So far, most MPC-based ANN protocols follow a cluster-based approach: they evaluate distances for the query over a large candidate set and rely on heavyweight primitives such as distributed ORAM to hide access patterns. As a result, each search typically requires $O(\sqrt{N})$ time. We propose HNSecW, a novel MPC protocol for ANN search that achieves the $O(\log N)$ search time for the first time. We first study the single-query setting. Starting from HNSW, the state-of-the-art ANN algorithm, we redesign its control flow and data structures to achieve fully data-independent execution. To further achieve logarithmic search time, we employ offline reshuffling and partial database duplication. Furthermore, we extend our protocol to support multiple sequential queries by introducing a "double visited" caching structure that eliminates redundant cross-query memory accesses, thereby avoiding per-query online shuffling. In addition, we develop a batch-query protocol that exploits higher parallelism to reduce both round complexity and the circuit's critical path. Our experiments show that HNSecW preserves the high accuracy of plaintext HNSW ($\geq 90\%$ recall) and delivers over a $20\times$ efficiency improvement over prior work on million-scale datasets.

cs.CR · cs.DB

查看论文
arXiv ↗PDF ↗