跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+758新增论文
+578其中 AI 相关
+94已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 08:06 — 2026-11-17 08:06(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:2026-11-17 04:58最近发现新增版本:2026-11-17 04:58库内论文最新更新时间:2026-11-14 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。

24,106 已收录论文20,158 AI 相关7,049 有修订112 HF 社区发现

浏览论文库

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 1,557 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2611.17742

Analysing Busy Beaver Machines (Or How to Find Ossified Ocelots)

James Harland

原文摘要

The busy beaver problem involves working with machines which can produce very large numbers, both for the output of certain Turing machines and for the number of steps taken to execute them. Given that these numbers can involve thousands of digits, it is crucial to have a means of proving properties of the relevant machines which allow manipulation of such large numbers. In this paper we introduce the notion of \textit{shape computations} as a means of isolating key properties that allow efficient execution of the relevant Turing machines based on verifiable properties of state transitions. In particular, this notion allows us to provide an analytical result which demonstrates the quadratic relationship between the size of the output and the number of steps required to generate it. We have also developed an initial implementation of our approach, and we provide empirical evaluation of it on a suite of 240 example machines.

cs.FL · cs.LO

新论文 · v1arXiv:2611.17710

Cross-Linguistic Acoustic Biomarkers of Cognitive Impairment Across Interactive and Single-Speaker Speech Tasks

Kenyu Ikeuchi, Tomoaki Ohtsuki, Michelle Cohn, Alyssa Weakley, Yui Ishihara, Joseph Hoang, Taishiro Kishimoto, Sarah Tomaszewski Farias 等 10 位作者

原文摘要

Multilingual dementia detection is essential for scalable and equitable screening. In recent years, automated speech analysis has emerged as a promising approach for supporting dementia detection by enabling non-invasive and scalable assessment of cognitive function. However, existing studies that use automated speech analysis often rely on one type of task, such as picture description, and use black-box models. These studies often neglect the role of task and language. To address these gaps, we performed a cross-linguistic and cross-task acoustic analysis that integrates a conversational dataset with structured speech tasks across four languages (Spanish, Mandarin, English, Japanese). We applied statistical, linguist-/clinician-guided, and machine learning model-based feature selection to derive compact acoustic feature sets while maintaining classification performance. This enabled systematic comparison of cognitive impairment-relevant features across datasets and tasks. Our results revealed that acoustic features did not generalize uniformly across tasks and languages. Temporal features remained robust across all datasets, consistently capturing timing disruption regardless of language or task. In contrast, speech rate showed strong task dependence -- emerging as informative mainly in single-speaker tasks with externally anchored content and pacing, but becoming less reliable when speech content was highly individualized. Pitch-related features further exhibited language-specific patterns, favoring chroma-related features in tonal languages (e.g., Mandarin) and F0-related features in non-tonal languages. These findings caution against indiscriminate pooling of heterogeneous speech data and underscore the need for interpretable, context-aware approaches to multilingual dementia detection using automated speech analysis.

cs.AI · eess.AS

版本更新 · v2arXiv:2605.24366

SA-RAG: Structuring Noisy Conversations for Retrieval-Augmented Generation

Kaiqiao Han, LuAn Tang, Renliang Sun, Peng Yuan, Wei Cheng, Haoyu Wang, Wei Wang, Yizhou Sun 等 9 位作者

原文摘要

Large Language Models (LLMs) have been widely adopted in conversational applications. However, their reliance on parametric knowledge limits reliability in real-world scenarios that require dynamic or domain-specific information. Retrieval-Augmented Generation (RAG) addresses this limitation by incorporating external knowledge during generation, but existing RAG methods often struggle with noisy or irrelevant contexts, as they typically assume that high-quality structures are already available. In this work, we propose Structure-aware Retrieval-Augmented Generation (SA-RAG), a principled structure induction and generation framework that constructs reliable intermediate structures directly from noisy conversational data. SA-RAG uses tables as compact and controllable structured representations. We introduce a quality-aware structure induction framework that jointly models semantic and structural consistency. Furthermore, we explore both training-free and training-based structure generation strategies to further improve structure quality while maintaining fidelity. Experiments on two noisy real-world datasets show that SA-RAG significantly outperforms existing RAG baselines. Further analysis highlights that high-quality structural representations are crucial for robust RAG applications.

cs.CL · cs.LG

新论文 · v1arXiv:2611.17686

What Do Multilingual Self-Supervised Speech Encoders Know About Sentence Meaning?

Kevin Krahn, Eric Fosler-Lussier

原文摘要

Self-supervised speech models (S3Ms) have been scaled up to thousands of languages and millions of hours of audio, yet little is known about how these models structure semantic knowledge across languages. In this work, we probe sentence-level semantics in massively multilingual S3Ms across 76 languages, using linear maps from frozen speech representations into a frozen text embedding space, evaluated by cross-modal retrieval. Sentence meaning is linearly accessible but highly uneven across languages and resource tiers. Cross-lingual probes can match language-specific probes on languages never seen in probe training, but per-model monolingual decodability does not predict transfer. Within the OmniASR wav2vec family, scaling from 300M--7B disproportionately benefits high-resource languages, and ASR tuning sharply improves semantic decodability while making representations more language-specific. However, semantic content is entangled with acoustics, inflating apparent performance on single-speaker corpora.

cs.CL

版本更新 · v2arXiv:2609.37670

MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators

Haocheng Tang, Tianchi Xie, Xingqiao Lin

原文摘要

MeanFlow enables efficient few-step generation by predicting interval-average velocities, but this representation creates a mismatch for reward fine-tuning: existing advantage-based objectives are typically defined on instantaneous velocities or equivalent $x_0$-space predictions, whereas inference directly uses the learned average-velocity map. We introduce MeanFlowAdvantage, a signed advantage-weighted least-squares objective for average-velocity generators. Our key construction uses a shared, detached MeanFlow derivative correction to express the reward objective in prediction space while making rollout and reference regularization exact penalties on the average-velocity network deployed at inference. The resulting formulation preserves MeanFlow's native few-step sampler and provides a direct mechanism for transferring reward improvements to the deployed flow map. On SD3.5-Medium, MeanFlowAdvantage improves all eight reported metrics over the matched four-step MeanFlowNFT baseline and, with only four NFEs, matches or exceeds the 40-step DiffusionNFT baseline on six of eight metrics. The same objective also transfers to DNA promoter design, where it supports both teacher-free on-policy RL for a generator defined on a manifold and teacher-guided reward-graded distillation, with the latter yielding the lowest one-step Sei profile MSE among the compared configurations.

cs.AI · cs.CE · cs.CV

版本更新 · v2arXiv:2611.09054

From Emergence to Reversibility

Zhengye Han, Linda Ng Boyle

原文摘要

Multi-agent systems become capable through institutional mechanisms, such as rules that route information to agents that act on it. These mechanisms are also natural places to restrict the system. Yet as agents learn, share memory, delegate, and repair failures, the collective can find other paths to the same effects. A restriction on the original mechanism can then keep operating but no longer stops them, while routine performance and compliance still passes. We propose \textbf{Reversible Multi-agent Systems} as a research agenda: collectives that grow while an authorized supervisor can still restrict specified effects, keep them restricted as agents adapt, and reconstitute useful cooperation under renewed authority. What is reversed is the ability to produce a specified effect; restrictions must hold even if learned knowledge persists. The goal is to preserve effective intervention, not a particular mechanism: at every step of growth, some authorized intervention must keep a specified prohibited effect rare while maintaining required service. We identify three research problems: tracking what capabilities depend on, handing off control before an old mechanism loses its effect, and separating legitimate repair from unauthorized reconstruction. We outline how to evaluate control across growth paths, back control claims with evidence, and allocate the rights to restrict and restore.

cs.MA

新论文 · v1arXiv:2611.17629

Training-Free Acceleration of Multi-View 3D Transformers via Regime-Aware Attention Approximation

Muhammed Izzet Sezer, Sevval Belkis Dikkaya

原文摘要

Multi-view 3D transformers such as VGGT reconstruct a scene from a set of unposed images in a single forward pass, predicting camera poses, depth and 3D points, but the cost of their global attention grows quadratically with the num- ber of images. Accelerators borrowed from large language models assume that each token attends to only a few oth- ers; on these models they lose accuracy or gain little speed. We study the global attention of three multi-view transform- ers on seven datasets and find that every layer plays one of three roles: it averages over the whole scene, matches points across many images, or anchors on the first image, whose coordinates the outputs use. Building on this anal- ysis, we propose Regime-AWare ATTention Approximation (RAWATTA), a training-free method that runs attention in 8- bit precision and keeps 16-bit precision only in the layers where a worst-case calibration check requires it. Its fast set- ting, RAWATTA-Fast, also approximates attention in a few averaging and anchoring layers, while matching layers and the first image keep all their keys. On a 12 GB GPU at 50 im- ages, RAWATTA runs VGGT faster than the released code, mostly through our CUDA engine, and loses at most about one point of pose accuracy (AUC@3) on any dataset; RAWATTA-Fast is slightly faster and less accurate. Both fit 200 images, where the released code runs out of memory at 100.

cs.CV · cs.AI

版本更新 · v2arXiv:2611.04240

VerfGraph: Efficient Zero-Knowledge Verifiable Graph Query Evaluation System

Tianyi Ma, Yuncong Zhang, Yuanzhuo Yu, Boshi Yuan, Shi-Feng Sun

原文摘要

Graph databases are widely used to manage relationship-rich data and support multi-hop traversal and shortest-path queries in applications such as financial risk control and social networks. When a client issues such queries to a database owner, the returned result may be incorrect. However, the client cannot directly verify it because the graph is typically large and private, making re-executing the query both infeasible and insecure. Verifiable and confidential graph query evaluation thus plays an important role in such applications. We present VerfGraph, a zero-knowledge verifiable graph query evaluation system, which enables a client to verify that the query result was correctly computed over a committed graph, without revealing anything beyond the public inputs and what is implied by the query result. While adopting the expansion-centric operator model introduced by ZKGraph (ICDE'26), VerfGraph improves both proving efficiency and query expressiveness in two key ways. First, we propose new proof methods for the core operators in ZKGraph, such as graph expansion and shortest path, that require substantially fewer expensive comparisons and eliminate edge canonicalization for bidirectional edge relations. Second, we introduce dedicated proofs for count and weighted shortest-path operators, which ZKGraph does not support, broadening the class of graph queries that can be verified. We evaluate VerfGraph using the LDBC Social Network Benchmark. Compared with the state-of-the-art zero-knowledge graph query system ZKGraph on complex IC queries, VerfGraph achieves $33.9\times$-$59.7\times$ speedups in proof generation and reduces peak prover memory by a factor of $4.5\times$-$6.6\times$, while maintaining millisecond-level verification and producing sub-MB proofs.

cs.CR

版本更新 · v3arXiv:2604.21909

Directional Confusions Reveal Divergent Inductive Biases Through Rate-Distortion Geometry in Human and Machine Vision

Leyla Roksan Caglar, Pedro A. M. Mediano, Baihan Lin

原文摘要

Humans and modern vision models can reach similar classification accuracy while making systematically different kinds of mistakes -- differing not in how often they err, but in who gets mistaken for whom and in which direction. We show that these directional confusions reveal distinct inductive biases that are invisible to accuracy alone. Using matched human and deep vision model responses on a natural-image categorization task under 12 perturbation types, we quantify asymmetry in confusion matrices and link it to the shape of the information-error trade-off. We characterize this trade-off geometry using three signatures extracted from the rate-distortion (RD) frontier: slope beta, curvature kappa and efficiency (AUC). We find that humans exhibit broad but weak asymmetries, whereas deep vision models show sparser, stronger directional collapses. Robustness training reduces global asymmetry but fails to recover the human-like breadth-strength profile of graded similarity. Mechanistic simulations further show that different asymmetry organizations shift the RD frontier in opposite directions, even when matched for performance. Together, these results position directional confusions and RD geometry as compact, interpretable signatures of inductive bias under distribution shift.

cs.CV · cs.IT · q-bio.NC

新论文 · v1arXiv:2611.17616

LLM-Guided Cluster Lifecycle Management: Deciding When and How to Evolve Behavioral Clusters

Himanshu Kulkarni, Siddharth Krishnamurthy, Jianhong Xin

原文摘要

Behavioral clusters learned over user or item interactions drift as behavior evolves: some fragment into sub-behaviors, some converge, some disappear, and new patterns emerge. Two paradigms dominate the maintenance of evolving clusterings. Threshold triggers fire a pre-specified action when a hardcoded statistic crosses a cutoff; refit-and-track (MONIC-style) re-clusters every window and infers transitions from how the new clusters align with the previous window's. Both hardwire the decision into a threshold or a re-clustering rule. We study an alternative in which a large language model (LLM) makes the lifecycle decision in place. Given a threshold-free, whole-population view of the current cluster set (statistical health, labels, member texts, residual mass), the LLM decides per cluster whether and how to act (split, merge, retire, create, or no-action) without re-clustering. Because the useful signal channel depends on how informative the labels are, we fix a richness-conditioned policy in advance: statistics when label distinctiveness is low, fused statistics+semantics when it is high. On three public datasets spanning label richness (YooChoose 0.17, MOOC 0.50, News-Category 0.70), the policy-selected LLM mode obtains the highest F1 on all three, with far fewer interventions and stronger restraint than tuned threshold heuristics and a MONIC steelman (paired Wilcoxon p <= 0.003, bootstrap 95% CIs excluding zero). The gain is concentrated more in precision than recall. The useful modality shifts from statistics to semantics/fusion as richness rises. Semantics hurt on YooChoose, fusion is roughly neutral on MOOC, and the semantic channel is required on News. One base prompt template and one fixed policy serve all three datasets, whereas the tuned baseline collapses when moved between them. We treat this shift as a practitioner diagnostic observed on three datasets, not a validated law.

cs.AI · cs.LG

版本更新 · v2arXiv:2609.11728

Reproducibility in the Age of Agentic AI: Context Engineering at the Timescale of a Codebase

Lorena A. Barba

原文摘要

Reproducible research practices are context engineering for AI coding agents. I argue that agents lower the cost of maintaining tests, commit histories, repository structure, instructions, and decision records while making their benefits immediate. Researchers remain responsible for verifying these artifacts and the scientific judgments they encode.

cs.SE · cs.CY

版本更新 · v2arXiv:2609.38540

When a Flatness Proxy Is Not a Function: Robustness Certificates and Training Interventions

Vicente Opazo

原文摘要

A valid curvature upper bound need not justify either a robustness certificate or an intervention on an intrinsic predictor property. We demonstrate this distinction for a last-layer relative-flatness proxy used in both settings. First, empirical-risk stationarity does not eliminate pointwise first-order loss terms: at a finite global empirical-risk minimum, the retained certificate expression underestimates a loss increase by over $210\times$. We derive a globally valid, gauge-invariant feature-space repair. Second, common-row softmax shifts preserve predictions and the exact contraction while making the proxy unbounded. Even standard reference-class choices double it on average relative to the centered representation. For a single fixed-feature example with at least three classes, scalar retuning generically cannot align the induced probability updates. Row centering gives the orbit-minimized bound and restores value and full-model gradient invariance under this symmetry. Across 45 paired one-step tests on algorithmic and image models, amplified shifts separate raw-regularized predictors while quotient-regularized predictors remain aligned. Long-horizon CIFAR-10 experiments show substantial, reversible suppression of generalization, while evidence for selective delay after memorization is less consistent. Together, these results show that validity as a curvature upper bound does not by itself justify either inversion into a robustness certificate or differentiation into an intrinsic training intervention.

cs.LG

版本更新 · v3arXiv:2609.18147

Dynamic Pooling and Regional Participation in Deceased-Donor Organ Allocation

Genta Okada

原文摘要

Moving from geographically fragmented to pooled waiting lists in deceased-donor organ transplantation can improve efficiency, but it raises concerns about regional fairness and participation incentives. This paper studies Pareto gains from such transitions in a multiclass queueing model with impatient agents, perishable items, and a tractable homogeneous compatibility friction. In contrast to standard approaches that emphasize static match quality or overlook regional incentives in dynamic contexts, this analysis identifies dynamic risk pooling as the primary source of Pareto improvements for regions. Pooling reduces organ waste resulting from stochastic supply-demand fluctuations, temporal mismatches, and random compatibility outcomes. Although this dynamic surplus theoretically enables Pareto improvements, a purely utilitarian policy that treats all patients equally across regions often fails to achieve these improvements when regions are asymmetric. In these situations, utilitarian redistribution removes an excessive number of organs from high-supply regions and violates their participation constraints. To address this conflict, it is demonstrated that the set of achievable utilities can be represented by mixtures of static priority index policies. Building on this structure, the Constrained Pareto Frontier Search (CPFS) is proposed as a polynomial-time procedure that computes an approximately optimal allocation policy with arbitrarily small participation-constraint violations, implemented as a single priority list with a lottery at registration. The results indicate that, by adjusting priority indices to ensure redistribution remains within the gains from pooled supply, demand, and compatibility risk, policymakers can achieve global efficiency while maintaining local participation incentives.

econ.TH · cs.GT

版本更新 · v3arXiv:2601.03064

Similarity-Sensitive Entropy under Representation Change and Inference

Joseph Samuel Miller

原文摘要

Similarity-sensitive entropy measures the uncertainty of a probability law relative to a similarity kernel that encodes the distinguishability of states. We develop the measure-theoretic treatment covering both finite similarity matrices and general probability spaces, and study how the law and similarity kernel transform under measurable maps, channels, and conditioning operations. This yields data-processing inequalities, so a reduction in entropy quantifies how much distinguishability is lost under representation change. We also define a conditional similarity-sensitive entropy theory, give a counterexample to a recent conjecture on concavity, and identify a practical one-dimensional Laplace kernel class where concavity holds.

math.PR · cs.IT

版本更新 · v2arXiv:2602.14961

稳定匹配的失真问题

The Distortion of Stable Matching

Aris Filos-Ratsikas, Georgios Kalantzis

AI 速读 基于摘要

本文开创性地研究稳定匹配中的失真问题,分析在有限获取基数偏好信息下,如何计算社会福利等聚合目标较优的稳定匹配。

cs.GT

查看原文摘要

We initiate the study of distortion in stable matching. Concretely, we aim to design algorithms that have limited access to the agents' cardinal preferences and compute stable matchings of high quality with respect to some aggregate objective, e.g., the social welfare. Following the recent agenda of Amanatidis et al. (2021), we seek to find the best possible tradeoffs between the distortion of an algorithm and the amount of information elicited via means of cardinal value queries. As a warm-up, we show that purely ordinal algorithms (i.e., algorithms that only use the preference rankings of the agents but no value queries), including the classic Deferred Acceptance (DA) algorithm of Gale and Shapley (1962), have unlimited distortion. Despite this strong impossibility, we observe that a simple randomized version of the DA algorithm achieves a distortion of $2$, and show that this is in fact optimal among all randomized stable matching algorithms. We then consider algorithms that also use value queries on top of the ordinal ranking information. Again, it is easy to see that the same bound of $2$ can be achieved with only $1$ value query per agent, and thus we focus on the question of improving upon this bound. To this end, we provide two strong lower bounds, namely that any stable matching algorithm requires $Ω(n)$ non-adaptive value queries or $Ω(\log n)$ adaptive value queries per agent to achieve a distortion smaller than $2$, where $n$ is the number of agents. Finally, we show an asymptotically tight bound of $Θ(\log (1+n\varepsilon)/\varepsilon)$ on the number of queries that are necessary and sufficient to achieve near-optimal distortion, i.e., a distortion of $1+\varepsilon$, for any $\varepsilon >0$.

新论文 · v1arXiv:2611.17298

基于显式对应关系的一致视频到视频翻译

Consistent Video-to-Video Translation via Explicit Correspondences

Gaurav Parmar, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, Srinivasa Narasimhan, Eli Shechtman, Yotam Nitzan

AI 速读 基于摘要

作者提出 vid2vid-long,利用输入视频中的 patch 级对应关系检索并复用历史生成结果,以在保持实时性的同时提升长程时序一致性。

cs.CV · cs.AI · cs.GR · cs.LG

查看原文摘要

Interactive video-to-video applications require real-time generation while maintaining long-range temporal consistency. However, recent methods achieve speed by restricting attention to a fixed-length causal window. This limits long-range consistency whenever relevant history falls outside the context window. To address this limitation, we introduce vid2vid-long, a correspondence-based approach grounded in a simple observation. Video-to-video translation provides an explicit cross-frame reference: the regions that match in the input video should match in the output video too. Concretely, we compute patch-level correspondences in the input, guiding retrieval of previously generated outputs in the corresponding regions, and condition the model on these patches through correspondence cross-attention. Our experiments demonstrate that vid2vid-long consistently improves long-range temporal consistency across recent video models while preserving generation quality and real-time performance.

新论文 · v1arXiv:2611.17294

Metal Sandbox:面向 Apple Silicon 上 GPU 编码智能体的隔离执行与命令调度

Metal Sandbox: Isolated Execution and Command Scheduling for GPU Coding Agents on Apple Silicon

Haozhe Wang, Lina Chen, Fanqi Wan, Qi Han, Yinmin Zhang, Zheng Ge, Daxin Jiang, Junchi Yan

AI 速读 基于摘要

提出 Metal Sandbox 基础设施,通过隔离文件访问、原生命令执行与跨 Mac 的命令级调度,减少 GPU 编码智能体 rollout 中的 GPU 空闲并提升命令吞吐。

cs.LG · cs.AI · cs.CL · cs.DC

查看原文摘要

On-device inference requires kernels that make effective use of local accelerators. Efficient training and evaluation of models that generate Apple Metal kernels benefit from native macOS tools and concurrent agent sessions. These sessions alternate between model requests, development commands, and GPU execution, leaving GPU capacity idle for much of a rollout. We present Metal Sandbox, infrastructure that combines restricted per-instance file access, native command execution, and command-level scheduling across interconnected Macs. Each agent retains its workspace and private development environment. Parallel commands can run concurrently, while serial commands share one execution slot per node; eligible waiting commands can migrate to available Macs and return results to the original agent. Integration with Harbor supports task execution, automatic verification, and rollout collection through a common workflow. Controlled experiments on four Mac mini M4 nodes achieve $1.68\times$--$2.05\times$ gains in command throughput under concentrated demand. Sixteen static agent traces give an estimated $2.14\times$ sustained-throughput gain for four sessions per node versus one, assuming continuously replenished sessions and unchanged mean durations. Replaying these measured traces under dynamic scheduling reduces mean tool waiting by 18.8% and batch elapsed time by 22.3%, assuming unchanged phase durations. Metal Sandbox and its Harbor integration are open-source on GitHub.

版本更新 · v2arXiv:2610.35748

基于贝尔曼锦标赛的离策略评估模型选择

Model Selection for Off-Policy Evaluation via Bellman Tournaments

Lars van der Laan, Vasilis Syrgkanis, Nathan Kallus

AI 速读 基于摘要

提出成对贝尔曼验证(PBV)方法族,将离策略评估中的模型选择与超参数调优转化为计算留出样本平均值的惩罚性贝尔曼锦标赛,并给出有限样本 oracle 不等式。

stat.ML · cs.LG · econ.EM

查看原文摘要

Model selection and hyperparameter tuning pose a central challenge in off-policy evaluation (OPE) because estimation errors in fitted $Q$-functions and occupancy ratios cannot be directly evaluated using held-out transition data. Existing Bellman-residual-based validation methods often require auxiliary regressions, while many minimax-based methods require optimization over separate critic classes. We propose pairwise Bellman validation (PBV), a family of penalized Bellman tournament methods that reduces validation to computing held-out sample averages. PBV constructs critics from pairwise candidate differences, on the log scale for occupancy ratios, and selects the candidate with the smallest worst-case penalized score. This construction approximates oracle critics given by $Q$-function errors and log ratios of candidate to true occupancy ratios, whose Bellman and adjoint Bellman moments control estimation error. Critic penalties account for approximation error under candidate-class misspecification. We establish finite-sample oracle inequalities relative to the best available candidate, even under candidate-class misspecification. For $Q$-function selection, unweighted PBV avoids importance weighting but requires a coercivity condition on a quadratic form induced by the Bellman operator. Importance-weighted PBV (IW-PBV) uses marginalized importance weighting to exploit Bellman contraction under the target-policy occupancy measure, avoiding this condition. For occupancy-ratio selection, adjoint PBV (A-PBV) exploits KL contraction of the adjoint Bellman operator to obtain oracle guarantees under the offline data law. On Hopper and DeepOPE, unweighted PBV is competitive with LSTD-Tournament, often achieving higher accuracy on Hopper, while importance weighting can further improve performance under controlled overlap.

新论文 · v1arXiv:2611.17191

最大化LoRA适配器容量利用率以缓解学习-遗忘权衡

Maximizing Capacity Utilization of LoRA Adapters for Mitigating the Learning-Forgetting Trade-off

Tomohiro Sawada, Kartik Goyal

AI 速读 基于摘要

作者提出一种无需SVD的Rényi-2有效秩正则项,通过提升LoRA适配器的有效秩来改善学习与遗忘之间的权衡。

cs.LG · cs.CL

查看原文摘要

Low-Rank Adaptation (LoRA) often underperforms full fine-tuning, especially in heterogeneous and continual-learning settings in which substantial forgetting occurs. In general, it suffers from an undesirable learning-forgetting trade-off across diverse fine-tuning settings. We identify a potential contributor: LoRA adapters, especially high-rank ones, frequently fail to realize the available capacity afforded by the configured rank. Specifically, we find that standard LoRA updates have effective rank far below their configured rank, limiting how broadly the update energy is distributed. Therefore, we propose training mechanisms that optimize the original objective while maximizing adapter effective rank. Our main method adds a simple, stable, differentiable, and SVD-free Rényi-2 effective-rank regularizer to the language-modeling loss. We also connect capacity maximization to norm-bounded updates. In mixed-domain rank sweeps on three models evaluated with multiple random seeds, a penalty weight of $λ=0.01$ lowers mean Wiki perplexity at every tested rank of at least $16$ relative to unpenalized LoRA. Mean training perplexity improves or increases by at most $0.02$ in all but one model-rank comparison. Single-task and scheduling experiments further show that the balance between learning and retention depends on the configuration. We also observe that several LoRA variants in the literature also suffer from the identified capacity issue, and our approach provides a complementary axis of improvement to LoRA-based parameter-efficient fine-tuning. These results suggest that effective rank is not only a post-hoc diagnostic of adapter quality, but a trainable objective for improving the learning-forgetting frontier. Our code is available at https://github.com/tomohiro-sawada/lora-capacity-utilization

新论文 · v1arXiv:2611.17145

利用眼动级联与多层组合融合增强偏好检测

Enhancing Preference Detection using Eye Movement Cascade and Multilayer Combinatorial Fusion

Yuanhong Wu, Mary Tsaryk, Sam Watson, Tahsin Ahmed, Christina Schweikert, D. Frank Hsu

AI 速读 基于摘要

作者报告,在成对面孔比较的眼动数据上,用多层组合融合(MCF)迭代整合多个分类器,可提升偏好预测性能。

cs.LG

查看原文摘要

Understanding how visual attention influences human preference formation is a fundamental problem in consumer behavior and cognitive science. In this work, we investigate how eye movement patterns can be used to predict preference decisions when subjects compare two alternatives. To address this problem, we analyze an eye-tracking dataset, where subjects view pairs of face images and their gaze behavior is recorded throughout the decision process. We model this problem using multiple machine learning classifiers and apply the Multi-layer Combinatorial Fusion (MCF) framework to iteratively combine diverse models. The MCF framework expands models to a large pool of model fusions and then reduces them based on cognitive diversity, repeating this process across layers until diversity diminishes. Experimental results show that MCF significantly improves performance over individual models. The best single model achieves a Pre@k of 0.90, which is improved to 0.9143 after the first layer of MCF, and further increased to 0.9286 in the second layer. This progression demonstrates that the second layer not only surpasses the performance of the first layer but also outperforms the best individual model, highlighting the effectiveness of leveraging diversity through multi-layer fusion.

版本更新 · v2arXiv:2610.08003

基于生成式假设选择的反应式任务导向机器人-人类交接

Reactive Task-Oriented Robot-Human Handovers via Generative Hypothesis Selection

Carmen Scheidemann, Andreea Tulbure, Pascal Burkhard, Marco Hutter

AI 速读 基于摘要

提出 GENESIS-Handover,利用视觉语言模型(VLM)图像生成产生任务特定的手-物交互假设,并实时匹配观测到的人手姿态,以推断合适的交接配置。

cs.RO

查看原文摘要

When humans hand each other objects, they incorporate both geometric and semantic information into this process. For example, passing a knife with the handle towards the recipient, rather than the blade, is both more ergonomic and safer. Recent state-of-the-art methods for task-oriented robot-human handovers have progressed from modeling object geometry to incorporating object affordances. However, they often forgo predicting the explicit, task-specific hand poses a human selects to utilize an object. Since many objects support multiple interaction modalities, e.g., a claw hammer used to strike or pull nails, this variability must be modeled to achieve robust task-oriented handovers. To tackle this, we propose a novel approach, GENESIS-Handover (GENErative HypotheSIS), which leverages VLM image generation to produce a variety of task-specific hand-object interaction hypotheses. These hypotheses are matched in real time to the observed human hand pose, enabling inference of the most suitable handover configuration. By leveraging VLMs as priors of plausible hand-object interactions, the method produces task-conditioned handover strategies for previously unseen object-task pairs. We evaluate the standalone interaction proposal module before deploying the full system on a mobile manipulator. In a user study with 12 participants across five task-object pairs, 83.3% perceived our method to have better task understanding than the previous state of the art.

新论文 · v1arXiv:2611.17123

保留漏洞、消除告警:用自然重写测试 CodeQL 污点追踪的鲁棒性

Preserve the Vulnerability, Break the Alert: Testing the Robustness of CodeQL Taint Tracking with Natural Rewrites

Zhezhen Cao, Weiyuan Ding, Bowen Xu

AI 速读 基于摘要

作者报告,用大语言模型对真实 npm 漏洞做保持漏洞语义的自然重写,可使 CodeQL 的 JavaScript 污点追踪告警消失,说明告警消失并不等于漏洞已修复。

cs.CR · cs.SE

查看原文摘要

Static application security testing (SAST) tools such as CodeQL serve as security gates in continuous integration and code review, and a gate is also read in reverse. When a previously reported alert disappears after a change, developers and the tools around them often take the vulnerability to be gone. That inference holds only if the analyzer is robust to changes that keep the vulnerability. We test this robustness for CodeQL's JavaScript taint tracking with natural, vulnerability-preserving rewrites. A large language model, given only the alert CodeQL exposes and no knowledge of its implementation, rewrites one function along a reported flow as a plausible maintenance change, and we verify by manual audit and controlled experiments that the flaw survives and the alert does not. On 172 flows that CodeQL detects in real npm vulnerabilities, three rewrites per flow silence 26.2% of them, at about USD 0.51 per silenced flow. The same generator, asked only to refactor the same functions with no knowledge of the alert, silences none of them. Every silencing rewrite traces to one of seven gaps at the library-modeling boundary, and 64 of the 70 rewrites cross a gap inside an API CodeQL already models. The largest is the WHATWG URL constructor, which propagates taint to a URL's query components but not to its pathname. The boundary is not specific to CodeQL. 74% of the silencing rewrites also silence an independently built taint analyzer, and 53% escape three analyzers combined. A disappearing alert after an ordinary-looking change is therefore weak evidence that a vulnerability has been fixed, the gaps point SAST developers to narrow and concrete repair targets, and robustness to natural rewrites belongs alongside detection rate in how taint analyzers are evaluated.

版本更新 · v2arXiv:2308.02666

用自动学习的谓词更快求解《见证者》三角谜题

Solving Witness Triangle Puzzles Faster with an Automatically Learned Predicate

Justin Stevens, Vadim Bulitko, David Thue

AI 速读 基于摘要

作者报告通过自动学习一个可解释的谓词来预测部分路径能否补全为解,从而在保持搜索完备性的前提下加速《见证者》谜题搜索。

cs.AI

查看原文摘要

The Witness is a game with combinatorial puzzles that are challenging for both human players and AI solvers. Search-based AI solvers can require large amounts of time to solve such puzzles. We accelerate search by automatically learning a predicate that predicts whether a partial path to a Witness puzzle is completable to a solution path. We demonstrate that our learned predicate is human-explainable, which makes it amenable to proofs, and we prove a key property that allows us to use it for pruning successor states in search. Doing so accelerates search by about six times while maintaining search completeness. Conversely, given a fixed time budget per puzzle, our predicate-accelerated search can solve more puzzles of larger sizes than a baseline search using a hand-coded predicate. Finally, we empirically demonstrate how accelerating search using an automatically learned predicate can outperform two competitors, weighted A* and Levin tree search with neural networks, in terms of time and number of nodes expanded.

新论文 · v1arXiv:2611.17020

最大化LLM效用并管理其易错性

Maximizing LLM Utility While Managing LLM Fallibility

Ekta U. Samani, Christopher G. Atkeson

AI 速读 基于摘要

这篇综述主张:系统应随着关于LLM表现的证据不断积累,动态调整对LLM的依赖程度,从而在利用LLM能力的同时管理其出错风险。

cs.RO

查看原文摘要

Large language models (LLMs) can supply autonomous systems with plans, predictions, and judgments, but these contributions are sometimes wrong. This review asks how a system can maximize an LLM's utility while managing its fallibility. Our answer is to adapt the system's reliance on the LLM as evidence about the LLM's performance accumulates. Systems built from imperfect components, such as noisy sensors and faulty software, have long worked in this way, and the classical methods they use can be applied to LLM-based systems as well. A system can change its reliance on an LLM in several ways, depending on the LLM's role and on the other components in the system. Each change needs an estimate of the LLM's reliability, and the LLM's role and the kind of contribution it makes determine what to estimate. Classical methods from decision theory, estimation, and online learning then turn these estimates into reliance decisions. These decisions can reduce how often LLM errors affect the system. However, some errors matter even when they are rare. An independently verified mechanism can prevent such errors from being executed. Without one, adapting reliance using reliability estimates can still keep their risk within a bound. Studies on adapting reliance on LLMs are emerging but limited, and the reviewed comparisons suggest that adapting reliance can improve system performance.

版本更新 · v4arXiv:2402.13989

FedADMM-InSa:面向联邦学习的不精确自适应ADMM

FedADMM-InSa: An Inexact and Self-Adaptive ADMM for Federated Learning

Yongcun Song, Ziqi Wang, Enrique Zuazua

AI 速读 基于摘要

提出一种不精确且自适应的FedADMM算法,通过不精确性准则和惩罚参数自适应调整,减少客户端本地计算并提升对超参数的鲁棒性。

cs.LG · cs.CR · cs.DC · math.OC

查看原文摘要

Federated learning (FL) is a promising framework for learning from distributed data while maintaining privacy. The development of efficient FL algorithms encounters various challenges, including heterogeneous data and systems, limited communication capacities, and constrained local computational resources. Recently developed FedADMM methods show great resilience to both data and system heterogeneity. However, they still suffer from performance deterioration if the hyperparameters are not carefully tuned. To address this issue, we propose an inexact and self-adaptive FedADMM algorithm, termed FedADMM-InSa. First, we design an inexactness criterion for the clients' local updates to eliminate the need for empirically setting the local training accuracy. This inexactness criterion can be assessed by each client independently based on its unique condition, thereby reducing the local computational cost and mitigating the undesirable straggle effect. The convergence of the resulting inexact ADMM is proved under the assumption of strongly convex loss functions. Additionally, we present a self-adaptive scheme that dynamically adjusts each client's penalty parameter, enhancing algorithm robustness by mitigating the need for empirical penalty parameter choices for each client. Extensive numerical experiments on both synthetic and real-world datasets are conducted. As validated by some numerical tests, our proposed algorithm can reduce the clients' local computational load significantly and also accelerate the learning process compared to the vanilla FedADMM. The source code is available at https://github.com/DCN-FAU-AvH/FedADMM-InSa.

新论文 · v1arXiv:2611.17018

探索面向包容性小组对话的社会可接受3D反馈设计

Exploring Socially Acceptable 3D Feedback Design for Inclusive Small-Group Conversation

Qianjie Wei, Yifan Li, Zhen Bai

AI 速读 基于摘要

该研究在XR小组对话场景中,探索如何通过幽默、降低社会注意和间接表达等策略设计公开3D反馈,使其既保持效果又提升社会可接受性。

cs.HC · cs.ET

查看原文摘要

Prior research has shown that providing feedback on group dynamics can improve the quality of small-group conversations. However, publicly delivered feedback that targets specific individuals may reduce social acceptability due to negative experiences such as social pressure, embarrassment, and resistance. This work investigates how public feedback can be designed to remain socially acceptable while maintaining its effectiveness in XR-based small-group conversations. Informed by social science and HCI literature, we identified three design strategies (incorporate humor, reduce social attention, and use indirectness) and proposed a set of metaphor- and agent-based 3D feedback probes. We then conducted a two-phase study: (1) an online survey with 50 participants to examine how such feedback designs are perceived under public and private delivery, and (2) follow-up interviews with 14 participants who completed the survey to better understand their interpretations and elicit additional insights. Results show that metaphor- and agent-based feedback can reduce social discomfort while maintaining effectiveness. Interview findings further highlighted the role of three strategies in making feedback easier to accept, while requiring careful balance. We also discussed design implications for creating socially acceptable 3D feedback to support inclusive small-group conversations in XR.

新论文 · v1arXiv:2611.17003

成熟度²:评估密码敏捷性成熟度模型的成熟度

Maturity$^2$: Assessing the Maturity of Crypto Agility Maturity Models

Leonie Wolf, Robin Leander Schröder, Sebastian Schinzel, Fabian Ising

AI 速读 基于摘要

作者依据既有设计原则评估三个业界驱动的密码敏捷性成熟度模型,发现其普遍缺乏可测量、可复现的评估标准与改进指导。

cs.CR

查看原文摘要

Crypto agility maturity models aim to support organizations in preparing for cryptographic transitions, such as migrating to post-quantum cryptography. Recognizing the importance of measurable maturity, NIST references several such models in its guidance. Given NIST's influence on cybersecurity practice, these models may shape organizational planning and governance mechanisms. However, their design quality has not been systematically evaluated. In this work, we assess three industry-driven maturity models against established design principles. Our analysis reveals recurring weaknesses, particularly the lack of measurable, reproducible assessment criteria and limited prescriptive guidance for improving crypto agility. At the same time, we highlight individual strengths that can assist practitioners in choosing among the models and derive concrete recommendations for strengthening future crypto agility maturity models.

版本更新 · v4arXiv:2509.05724

基于学习误差模型的稳健摊销仿真推断

Robust Amortized Simulation-Based Inference via Learned Error Models

Matthew O'Callaghan, Kaisey S. Mandel, Gerry Gilmore

AI 速读 基于摘要

提出RVNP,用重要性加权自编码器联合学习对模型误设稳健的后验代理与显式误差模型,以弥合仿真到现实的差距。

stat.ML · astro-ph.GA · cs.LG

查看原文摘要

Recent advances in neural density estimation have enabled amortized Bayesian inference for complex stochastic simulators. However, these methods rely on simulators accurately reflecting the true data-generating process and can degrade significantly under model misspecification. We consider the setting where multiple unlabeled observations are available and introduce robust variational neural posterior estimation (RVNP), an amortized Bayesian inference method that uses an importance-weighted autoencoder to jointly learn a misspecification-robust posterior proxy and an explicit error model that captures the simulation-to-reality gap. Our results show that RVNP can recover robust posterior inference in a data-driven and interpretable manner, outperforming previous methods on multiple metrics across misspecified benchmarks.

新论文 · v1arXiv:2611.16881

蛋白质语言模型在不变重标记下无法保持接触预测

Protein Language Models Fail To Capture Contact Predictions Under Invariant Relabeling

Paarth Batra, Aryan Keluskar

AI 速读 基于摘要

作者提出一种基于氨基酸字母表全局双射重标记的诊断框架,发现多种蛋白质语言模型(pLM)的接触图在该变换下崩溃,说明其依赖显式残基身份而非纯共进化统计。

q-bio.QM · cs.AI

查看原文摘要

Protein language models (pLMs) produce highly accurate contact maps from single-sequence inputs. People often take this accuracy as proof that these models implicitly learn invariant coevolutionary statistics, extracting the same signals as classical alignment-based methods like Potts. In this work, we introduce a diagnostic framework around a global bijective relabeling of the amino-acid alphabet. This transformation permutes residue letters while leaving all alignment-level information, column entropies, and pairwise edit distances unchanged. Pseudolikelihood Potts models and inverse-covariance estimators remain invariant under this transformation, but pLMs fail the test. Across multiple architectures (ESM-2, MSA Transformer, AMPLIFY) and model scales (8M to 3B parameters), pLM contact maps collapse under arbitrary relabeling. Using Hamming distance controls and biochemical grouping interventions, we attempt to isolate what likely causes this degradation and find that these models rely on explicit, canonical residue identities (``alphabet anchoring'') rather than pure coevolutionary statistics. Increasing scale makes models more responsive to biochemical classes, but their performance still degrades under relabeling. Our findings show a gap between how pLMs and classical coevolutionary models compute contacts. More broadly, our work shows how diagnostic perturbations that leave classical models provably unchanged can expose hidden representation biases and prevent over-reliance on neural black boxes in biological modeling.

版本更新 · v2arXiv:2610.31996

面向目标结构动态减振的多材料拓扑优化

Multi-Material Topology Optimization for Targeted Structural Dynamic Vibration Attenuation

Bir Bahadur Chaudhary, Bidhan Pandey, Bin Ouyang, Shiguang Deng

AI 速读 基于摘要

提出一种多材料拓扑优化框架,通过新型插值方案、基于界的优化列式和平滑频带约束,解决基于特征频率的减振优化中的数值困难,并系统比较三种动态减振优化列式。

cs.CE

查看原文摘要

Resonance-induced structural vibrations can compromise the performance, reliability, and service life of engineering structures. Multi-material topology optimization (MMTO) offers a promising approach to vibration attenuation by tailoring the spatial distributions of material constituents to optimize structural stiffness, mass, and natural frequencies. However, existing eigenfrequency-based MMTO methods face several challenges, including the need for flexible interpolation of multiple material properties, non-smooth optimization objectives associated with mode switching and repeated eigenvalues, and numerical difficulties in imposing differentiable constraints to exclude natural frequencies from prescribed operating frequency ranges. To address these challenges, we propose a novel MMTO framework for structural vibration attenuation based on several innovations: (1) a novel multivariate weight-based multi-material interpolation scheme to simultaneously represent material stiffness and mass density, (2) a bound-based optimization formulation to improve the smoothness and stability of gradient-based optimization by addressing mode switching, and (3) a smooth frequency-band formulation to smoothly approximate the discontinuous Heaviside function while enabling differentiable frequency-band constraints. Additionally, we systematically investigate and compare three different topology optimization formulations for dynamic vibration attenuation, including maximizing the fundamental eigenfrequency, maximizing the gap between adjacent eigenfrequencies, and excluding natural frequencies from prescribed frequency bands. Furthermore, we present the detailed derivation of analytical design sensitivities for the three formulations.