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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 04:33 — 2026-11-22 04:33(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.21586

超越职位名称:用稀疏自编码器与语义聚类解读早期职业招聘广告

Beyond Job Titles: Interpreting Early-Career Job Advertisements with Sparse Autoencoders and Semantic Clustering

Yisong Cao, Leah Kim, Brian Wright, Ali Rivera

AI 速读 基于摘要

该研究比较了基于深度学习与Transformer表示的两种方法,用于分析早期职业招聘广告中技术岗位在工作内容和行业应用上的差异。

cs.CL

查看原文摘要

Job titles and job descriptions alone provide limited insight into how technical roles differ in a changing job market. To assess how such roles differ in their work and industry applications, we design and compare two methods based on deep learning and transformer representations using 36,081 early-career job postings collected from LinkedIn in the United States between December 2025 and October 2026. We first apply PERC, short for Preprocessing (P), Embedding (E), Dimensionality Reduction (R) and Clustering (C). We employ GPT-6 Luna to classify job description passages into Team context, Role task and Qualifications. We then create combinations of these sections and examine whether embedding and clustering the segmented passages produce meaningful semantic clusters about different job roles. We use Maximum Mean Discrepancy (MMD) to rank observed differences between embedding distributions and employ a pretrained sparse autoencoder (SAE) to extract features from layer-19 representations of Llama-3.1-8B-Instruct. Lastly, we employ GPT-6 Luna to come up with hypotheses about job roles' feature patterns, and GPT-6.1 Terra to investigate whether those patterns exist in held-out job descriptions from unseen companies. Some example findings include Data Scientist advertisements placing more emphasis on machine learning model development, Data Analyst advertisements on reporting business performance, and Machine Learning Engineer advertisements on applying developed models in real-world settings. We also observe differences in the applications described by Data Analyst and Business Analyst advertisements across selected months, although our dataset's scale and uneven coverage limit their interpretation. Overall, we present a realistic application of SAEs and PERC to unstructured textual data and examine how automated insight extraction could support manual analysis of job descriptions.

新论文 · v1arXiv:2611.21584

CertiSum:跨平台与并行布局的逐位一致 MXFP4 训练

CertiSum: Bitwise-Identical MXFP4 Training Across Platforms and Parallelism Layouts

Steve Rhyner, Yubo Gao, Stefan de Lasa, Sankeerth Durvasula, Nandita Vijaykumar

AI 速读 基于摘要

CertiSum 利用 FP32 累加在多数求和顺序下已精确的特性,通过量化统计认证与精确重算,实现 MXFP4 训练在运行、并行布局和 GPU 厂商间的逐位一致。

cs.LG · cs.DC

查看原文摘要

Training with MXFP4, a 4-bit microscaling format, is non-deterministic: identical inputs can produce different results across parallelism layouts and GPU vendors. These differences complicate debugging and training audits and can cause training and inference engines to disagree. We present CertiSum to make MXFP4 training bitwise invariant across runs, parallelism layouts, and GPU vendors. Its key insight is that native FP32 accumulation of MXFP4 products is often already exact for every summation order. CertiSum collects statistics during quantization to certify native matrix multiplication results, recomputes uncertified outputs exactly, and uses exact kernels directly where certification rarely succeeds. CertiSum keeps quantization blocks unchanged across layouts and merges partial sums without rounding, including in attention and weight-gradient computation. In 200-step Qwen3-8B-Base experiments, CertiSum preserves training states bit for bit across AMD MI350X and NVIDIA GB200 and across changes in data, tensor, and context parallelism on MI350X. Across three 8B--14B models on FineWeb-Edu using MI350X, it adds 11.8--60.5% to training-step latency relative to its non-exact MXFP4 counterpart at the larger evaluated input shapes, with speedups of up to $1.24\times$ over BF16 and $1.70\times$ over deterministic BF16.

版本更新 · v2arXiv:2609.32116

逃离对齐:Best-of-N 越狱的物理陷阱模型

Escaping Alignment: A Physical Trap Model of Best-of-N Jailbreaking

Marco Biroli

AI 速读 基于摘要

作者提出一个物理陷阱模型,用五个可解释参数刻画Best-of-N越狱在N和M两个预算及温度下的攻击成功率曲面,并挑战了先前认为ASR随N呈幂律的结论。

cs.AI · cond-mat.stat-mech

查看原文摘要

Best-of-$N$ jailbreaking (BoN) bypasses safeguards of aligned models by drawing $N$ independent augmentations of an unsafe prompt and sampling $M$ completions of each. Previous works have shown that the attack success rate (ASR) seems to follow a power-law in $N$, which we challenge. The exponent drifts with $N$, and the reported exponential crossover is consistent with a finite-size effect of the adversarial dataset. Little work has been done to explore the entire two-budget ($N, M$) attack surface as well as its dependence on the generation temperature $T$. We introduce a simple barrier model where each prompt has a baseline safety level and each augmentation a random thermally activated barrier. Then five numbers, each backed by an interpretable safety mechanism, determine the entire ($N, M$) attack surface. They extrapolate predictions from $N \leq 100$ to $N = 10^4$, collapse five distinct models on the same scaling function and predict ASR at different temperatures from the one they were fitted at. The extrapolation holds under two automated judges and on held-out prompts.

版本更新 · v4arXiv:2511.11934

A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts

Claudio César Claros Olivares, Austin J. Brockmeier

原文摘要

We present a systematic benchmark of out-of-distribution (OOD) detection confidence scoring functions (CSFs) through a representation-centric lens. Our study spans CNN and ViT backbones, multiple training paradigms, four image-classification source datasets (CIFAR-10, CIFAR-100, SuperCIFAR-100, and TinyImageNet), and OOD datasets grouped into near, mid, and far regimes based on CLIP-derived semantic distances. To compare CSFs across these settings, we employ a rank-based pipeline of Friedman and Conover tests that identifies top cliques of statistically indistinguishable winners under threshold-free ranking metrics (AURC and AUGRC). The main empirical finding is that the family of CSFs that are competitive detectors correlates with characteristics of the learned representation. For both CNNs and ViTs, simple probabilistic scores dominate misclassification detection. On CNNs, margin-based scores are strongest in near-OOD regimes, while geometry-aware scores such as NNGuide, fDBD, and CTM become more competitive as shift severity increases. On fine-tuned ViTs, the top cliques are led mainly by reconstruction- and residual-based scores. To interpret these ranking shifts, we analyze the last-layer representation using Neural Collapse (NC) metrics. The resulting picture is consistent across architectures: prototype- and boundary-aware scores become stronger when the representation is more collapsed and better aligned with classifier weights, whereas weaker-collapse regimes favor gradient- and manifold-based scores. Building on these insights, we propose two contributions: a simple PCA-based projection-filtering procedure that improves detector performance, and an approach that uses only the NC measurements of a trained classifier to predict its competitive out-of-distribution detector shortlist, without OOD data for that classifier and without knowledge of the shift.

cs.LG · cs.CV

版本更新 · v2arXiv:2608.21761

CLIP在区域地理定位中学到了什么?适应后探测视觉线索与场景配置

What Does CLIP Learn for Regional Geolocalization? Probing Visual Cues and Scene Configuration After Adaptation

Changyu Lee, Yeonsoo Park, Abdullah Alfarrarjeh, Seon Ho Kim

AI 速读 基于摘要

作者报告,在洛杉矶大都市区街景区域定位任务中,CLIP编码器适应显著提升近邻区域区分能力,且性能提升与对完整场景配置的敏感性增强相关,但无证据表明仅靠粗结构即可充分预测。

cs.AI · cs.CE · cs.CV

查看原文摘要

Large collections of street-view imagery provide rich visual information about urban environments, but extracting fine-grained geographic information from such data remains challenging. In particular, fine-grained regional geolocalization is challenging because nearby areas often share coarse geographic cues. We study regional geolocalization within a metropolitan area and ask whether pretrained CLIP features are sufficient for regional discrimination, and what visual information supports performance after adaptation. Using 9,085 street-view images from eight Greater Los Angeles regions, we compare zero-shot CLIP, frozen-encoder readouts, partial encoder updating, Low-Rank Adaptation (LoRA), and full fine-tuning. Frozen readouts remain near the 39.03% zero-shot accuracy, whereas encoder adaptation achieves 75.94-82.10%. Full fine-tuning also reduces the mean distance to the predicted region center from 12.30 km to 3.86 km. We probe these gains through semantic cue removal, appearance reduction using edge maps and blur, and scene-configuration disruption using patch scrambling. Adapted models achieve higher edge and blur accuracy and switch 42.92-45.56% of predictions after scrambling, compared with 10.79-14.60% for frozen methods. However, adaptation does not improve the fraction of performance retained after appearance reduction, while vegetation and sky remain influential. A Caltech101 control further shows that scrambling sensitivity is not unique to geolocalization. Overall, encoder adaptation substantially improves nearby-region discrimination and is associated with greater sensitivity to intact scene configuration, without evidence that coarse structure alone becomes sufficient for prediction. These conclusions concern viewpoint variation near known locations rather than geographically disjoint generalization.

新论文 · v1arXiv:2611.21571

DynSurvX:动态生存预测的时间分辨解释

DynSurvX: Time-Resolved Explanations for Dynamic Survival Predictions

Van Tuan Nguyen, Agathe Guilloux

AI 速读 基于摘要

提出模型无关的可解释性框架 DynSurvX,用分层两阶段 Shapley 值方法为混合静态与纵向协变量的动态生存预测提供随时间更新的细粒度解释。

cs.LG

查看原文摘要

Recent survival models integrating longitudinal data achieve strong predictive performance, but their predictions are often difficult to interpret, limiting their clinical use. We propose DynSurvX, a model-agnostic explainability framework for dynamic survival prediction with mixed static and longitudinal covariates. Based on Shapley values, DynSurvX introduces a hierarchical two-phase strategy that first identifies influential longitudinal features and then adaptively refines their temporal importance, enabling fine-grained explanations while reducing computational cost. The framework provides time-resolved explanations that evolve as new patient data become available. Experiments on simulated and two clinical datasets show varying agreement with theoretical importance across prediction models, with closer agreement for better-performing models, alongside clinically interpretable insights in real-world settings. It remains robust across prediction settings and reduces computation time by 41--80\% relative to the temporal explanation baseline, making dynamic explanations practical.

版本更新 · v2arXiv:2607.01191

Perceive-to-Reason:解耦感知与推理的细粒度视觉推理

Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning

Hongxing Li, Xiufeng Huang, Dingming Li, Wenjing Jiang, Zixuan Wang, Haolei Xu, Hanrong Zhang, Haiwen Hong 等 14 位作者

AI 速读 基于摘要

P2R 将细粒度视觉推理解耦为“先定位证据、再基于证据作答”的两阶段框架,并用角色感知的强化学习策略对齐训练。

cs.CV

查看原文摘要

Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visual cues are buried in high-resolution images. Existing approaches rely on repeated cropping or test-time visual search to introduce local evidence, but they typically do not explicitly distinguish perception from reasoning. In this paper, we propose Perceive-to-Reason (P2R), a unified framework that formulates fine-grained visual reasoning as a two-stage process: the model first localizes question-relevant evidence as a Perceiver, and then answers the question as a Reasoner based on the annotated image and cropped regions. To better align training with this decoupled formulation, we further introduce Perception-Reasoning Alternating GRPO (PRA-GRPO), a role-aware reinforcement learning strategy that alternates between perception-focused and reasoning-focused updates using only final-answer supervision. Built on top of Qwen3-VL-Instruct-2B/4B/8B, P2R consistently improves performance across model scales. In particular, P2R-4B achieves 93.2% on V-Star, 81.9% on HR-Bench-4K, and 80.5% on HR-Bench-8K, substantially outperforming its corresponding backbone. Further experiments show that the benefits of P2R extend beyond high-resolution benchmarks to broader multimodal reasoning tasks. These results suggest that explicitly decoupling perception from reasoning provides an effective framework for fine-grained visual reasoning.

新论文 · v1arXiv:2611.21570

Trustworthy Numerical Software in the Age of AI: What Would Turing Do?

Kimon Fountoulakis, Maksim Melnichenko, Muhammad Fetrat Qharabagh, Georgios Alexandros Georgantzas, George Spyrou, Oleg Balabanov, Vasileios Georgiou, Riley Murray 等 9 位作者

原文摘要

AI coding agents can now produce numerical software faster than human experts can review it, raising serious concerns about usability and reliability. These and other AI tools are already transforming mathematics and software, and they will soon transform mathematical software. These concerns motivated us to assess AI-generated numerical linear algebra (NLA) kernels, which we did through an audit of a recent public GPU QR competition. All five leading kernels passed the competition's accuracy tests, and the winning kernel achieved a 107-fold speedup over the competition's baseline, which calls NVIDIA's QR routine. Yet each failed at least once on new inputs, even those from the competition's generator, under the same checker, while the baseline passed them all. In light of this, we want to develop reusable formalizations of numerical analysis methods, which remain sparsely represented in existing formal libraries. We describe VSCL, our Lean library of mathematical foundations for numerical computing. We also propose VERNA to connect these tasks by using formalized results to guide kernel assessment against explicit specifications. Drawing on Turing's work on rounding-error analysis and program checking, we discuss design principles for developing trustworthy numerical software when direct human checking is impractical.

math.NA · cs.MS

新论文 · v1arXiv:2611.21565

组织学基础模型何时需要几何测试时增强?

When Do Histology Foundation Models Need Geometric Test-Time Augmentation?

Lars Chen, Valentino F. Foit, Dorry Segev, Michal Mankowski

AI 速读 基于摘要

作者报告在组织学基础模型上,D4测试时增强的收益随模型规模增大而减小,熵路由可选择性应用TTA以降低计算开销,且块级TTA提升不迁移到全切片级MIL。

cs.CV · cs.LG

查看原文摘要

Test-time augmentation (TTA) aggregates model predictions across multiple transformed views of an input during inference. Because histology images lack a canonical orientation, $D_4$ TTA---pooling across the 8 rotations and reflections of a square---is a standard default in computational pathology. However, the rise of self-supervised histology foundation models (FMs) with inherent rotational invariance calls its continued utility into question. We benchmark 9 histology FMs and 6 general-purpose models across four patch-level and two whole-slide image (WSI) datasets. We find that $D_4$ TTA remains a reliable post hoc improvement, but benefits diminish from $+1.98$ percentage points (pp) for general-purpose backbones to $+0.50$ pp for histology FMs on TCGA-UT, and shrink further for the largest models. To eliminate computational overhead, our experiments demonstrate that entropy routing---applying TTA selectively to uncertain predictions---recovers most of the gain while augmenting only ${\sim}13\%$ of samples. Finally, we show that patch-level TTA improvements do not transfer to slide-level multiple instance learning (MIL). Code: https://github.com/lars-chen/histology-tta

新论文 · v1arXiv:2611.21563

Wildfire-SSR: Geolocation-Aware Multimodal Fusion for Structure-Level Wildfire Risk Assessment

Yu-Hsuan Ho, Yiming Xiao, Hao-En Lai, Ali Mostafavi, Samuel D. Brody

原文摘要

Structure-level wildfire vulnerability assessment is critical for reducing losses in wildland-urban interface communities, yet existing methods often fail to combine parcel-scale ignition pathways with community-scale geographic coverage. This study introduces Wildfire-SSR (Satellite and Street-view for wildfire Risk), a geolocation-aware multimodal framework that integrates macro-scale satellite context with micro-scale street-view evidence. A Vision-Language Model extracts wildfire-relevant building and site attributes from pre-event street-view panoramas and converts them into structured semantic text. These features are spatially aligned with satellite imagery through a decoupled cross-attention fusion decoder, while a frozen satellite-pretrained DINOv3 encoder captures overhead visual context. Alternative geolocation embedding strategies are evaluated to anchor text-derived features within each satellite patch. The framework is tested on approximately 37,000 structures affected by the 2025 Eaton and Palisades fires in Los Angeles, using wildfire risk labels derived from relative post-event damage patterns to better represent inherent structural vulnerability. Rotary Positional Embedding provides the strongest spatial grounding, achieving a building localization F1 score of 0.6735 and a harmonic mean F1 score of 0.2476 for five-class pixel-level risk classification, outperforming unimodal baselines and an unanchored multimodal configuration. The model also shows a conservative bias in higher-risk classes, reducing severe-risk underestimation, and completes end-to-end assessment of the study area in 37 minutes on a single GPU. Wildfire-SSR reframes cross-view fusion as localized semantic alignment and provides a scalable tool for mitigation prioritization, resilience planning, and insurance-oriented wildfire risk assessment.

cs.CV

新论文 · v1arXiv:2611.21559

参考强制:基于区域引导漂移校正的长视频生成

Reference Forcing: Long Video Generation with Region-Guided Drift Correction

Sheng Zhao, Haitian Zheng, Weikai Lin, Junjie Zhao, Yuhao Zhu

AI 速读 基于摘要

提出Reference Forcing方法,利用初始帧作为外观参考,通过教师蒸馏和值校正来减少长视频生成中的主体与背景漂移。

cs.CV

查看原文摘要

Long video generation should keep the subject and background consistent while supporting rich, natural motion. However, autoregressive models are often distilled with distribution matching distillation (DMD) over short windows, which does not train them to keep this consistency over long ranges. As a result, the subject and background can drift over time. Methods that manage the key-value (KV) cache retain or retrieve history to reduce drift. Yet this history may itself have drifted. We propose Reference Forcing, which uses the initial frames as an appearance reference. We first build a teacher that uses attention masks to force each region of a new frame to attend to the same region in the initial frames. The teacher finds these regions with off-the-shelf segmentation models. We then distill this behavior into a separate attention path of the student, which needs no external models at inference. We further introduce value correction, which corrects drifted values in the KV cache toward the matching values of drift-free initial frames. Experiments show that Reference Forcing achieves state-of-the-art subject and background consistency among long-video methods on different base models, and its advantage grows with video length. Ablations show both components are needed to gain consistency without losing motion. More visualizations and code are available at https://zhaosheng-thu.github.io/reference-force/

新论文 · v1arXiv:2611.21558

危机咨询中人类-AI协作的益处与障碍

Benefits and Barriers to Human-AI Teaming for Crisis Counseling

Ivy Pham, Akshay Swaminathan, Sebastian Garcia, Jaimie Lim, Gloria Ye, Divyanjali Verma, Alan Pham, Chastin Chung 等 15 位作者

AI 速读 基于摘要

一项在印度WhatsApp危机热线中部署咨询师辅助AI copilot的混合方法研究,作者报告了高接受度与效率提升,同时揭示了技能退化、真实性和过度依赖等障碍。

cs.HC · cs.CY

查看原文摘要

Background: AI systems are increasingly deployed to support mental health clinicians, yet real-world evidence remains limited. In crisis counseling, where clients often seek human connection, understanding whether AI augmentation preserves or undermines meaningful human engagement is essential. Methods: In a mixed-methods study of a counselor-facing AI copilot on a WhatsApp-based crisis hotline in India (Mar.-Oct. 2025), counselors could request, edit, and send AI messages. We analyzed 20 interviews, 8 shadowing sessions, 56 survey responses, and edits in 27,778 copilot messages from 108 counselors via thematic analysis (Technology Acceptance Model 2, plus inductive coding of emergent factors), and survey statistics. Results: Counselors reported high copilot acceptance (survey): 98.2% found it helpful; 89.3% likely to continue use; 80.4% reported efficiency gains. Interviews highlighted sentence scaffolding, empathetic phrasing, stress reduction, catching missed details, and efficiency. Barriers (survey) included repetitive outputs (23.2%), lack of context (17.9%), and authenticity concerns (10.7%). While 69.6% (survey) reported skill enhancement, interviews surfaced skill atrophy concerns. Counselors frequently accepted copilot suggestions, editing to remove questions, adjust tone, or personalize style. Conclusion: In one of the largest real-world deployments of a counselor-facing mental health AI copilot, counselors reported reduced cognitive load, empathetic communication, and greater efficiency, alongside concerns about skill atrophy, authenticity, and over-reliance. In settings like crisis counseling where clients seek human connection, AI tools must balance operational support with preserving clinical skill and genuine therapeutic engagement. Designs soliciting approval or editing of complete drafts may overweight efficiency at the expense of sustained human engagement.

新论文 · v1arXiv:2611.21554

Reading or Remembering? Measuring Temporal Contamination in Language Models

Arunkumar V, Gangadharan G. R., S. Senthilkumar

原文摘要

Language models are now used to read central-bank text for economic forecasting, but most were trained on text written after the documents they read. A model reading a 2021 FOMC statement may already know that inflation rose in 2022, so part of its apparent skill can be memory of the outcome, a temporal form of test-set contamination. We measure this memory on FOMC statements and minutes from 2000 to 2026 by comparing modern open models with chronologically consistent models, which are trained only on text from before a fixed date. Asked about past GDP outcomes given only a date, models that cannot know the answer still reach an AUC of up to 0.64 from priors on dates and eras, so chance is the wrong baseline. Against these memory-free models on the same questions, most modern models recall which years had strong growth. Membership-inference scores sort documents by era and document type rather than by whether a model saw them, as exact counts in an open pretraining corpus show. In real-time nowcasts, every lookahead premium we estimate on US GDP is smaller than the forecast comparison can detect at macroeconomic sample sizes, and none on GDP or inflation survives correction for multiple testing. Lookahead audits should therefore measure memory directly against memory-free models on the same items.

cs.LG · cs.CL

新论文 · v1arXiv:2611.21553

BLIP-Live:在主动式流媒体视频智能体中平衡及时性与触发精度

BLIP-Live: Balancing Timeliness & Firing Precision in Proactive Streaming Video Agents

Kanchana Ranasinghe, Honglu Zhou, Dominick Reilly, Le Xue, Shusheng Yang, Juan Carlos Niebles, Silvio Savarese, Ran Xu

AI 速读 基于摘要

作者提出围绕“主动响应决策”统一数据、指标、推理框架与训练的 BLIP-Live 框架,用于流式视频理解中兼顾及时响应与避免误触发。

cs.CV

查看原文摘要

Streaming video understanding is becoming increasingly important for real-world interactive systems. Such systems must be proactive for natural and useful human interaction: they should respond as soon as sufficient evidence becomes available while avoiding premature, redundant, or incorrect responses. We present BLIP-Live, a framework unifying data, metrics, harness, and training around a shared formulation of proactivity as effective causal response decisions balancing the two competing objectives of responding vs silence. First, we construct BLIP-Live-780K dataset containing human annotations of proactive response content and timing, which defines this desired behavior. We then propose PAUC-F, a metric to effectively measure our desired proactive behavior. PAUC-F combines existing response timeliness metrics with firing precision to reward early useful responses without rewarding excessive firing. With our desired behavior defined and measurable, we finally investigate model-agnostic inference harnesses that draw out proactive streaming capabilities of offline vision language models (VLMs), together with training pipelines that learn to further improve their proactive responsiveness. Across both settings, we find that combinations of sliding visual windows, online interaction memory, and structured response outputs consistently yield strongest proactive performance. Our experiments result in two models, with our BLIP-Live-Qwen model achieving state-of-the-art performance across four proactive streaming benchmarks, with gains up to 44% over baselines and outperforming multiple closed API models. Our code and data will be released publicly.

新论文 · v1arXiv:2611.21552

量子循环神经网络在时间序列预测中的记忆与非线性处理能力基准测试

Benchmarking memory and nonlinear processing capacity of quantum recurrent neural networks for time series prediction

José Daniel Viqueira, Andrés Gómez, David Mera

AI 速读 基于摘要

作者对变分量子循环神经网络(QRNN)在时间序列预测中的记忆与非线性处理能力进行了基准测试,并与经典循环基线比较。

quant-ph · cs.LG

查看原文摘要

Quantum machine learning has emerged as a promising approach to time series prediction. While quantum reservoir computing has been widely explored for this setting, variational quantum models tailored to sequential data remain comparatively understudied, largely because they are difficult to train. In this work, we present a rigorous benchmark of variational quantum recurrent neural networks (QRNNs) on time series prediction tasks, focusing on two key capabilities: memory and nonlinear processing. We introduce a task-driven methodology that quantifies model capacity, enabling an intuitive and fair comparison across architectures, including classical recurrent baselines. We evaluate the proposed framework on two generic benchmark tasks and on a synthetic dataset describing a chaotic system. Overall, the quantum models achieve performance comparable to their classical counterparts, but classical models scale better with the memory size within the range studied. Notably, one QRNN variant shows higher average capacity on the task designed to jointly probe memory and nonlinear capacity. Moreover, our results show that quantum models offer better capacity when we are able to find a good parameter initialization. However, the increasing sensitivity to initialization leads to a lower probability of finding good solutions as the model size increases. These results provide a principled starting point for designing richer quantum recurrent architectures and for assessing where they may offer practical benefits.

新论文 · v1arXiv:2611.21548

TRACE: Topological Representations for Anomaly detection through Contrastive Embeddings

Sydney Johns

原文摘要

Intrusion detectors must recognize evolving malicious behavior even when confirmed attack labels are scarce or incomplete. We present TRACE, a topology-aware graph contrastive learning framework for label-efficient intrusion detection. TRACE learns from benign system-activity graphs by combining message-passing and topological representations, then assigns anomaly scores in the same projected embedding space optimized by the contrastive objective. This design captures both local interactions and graph-scale structural deviations without using attack labels during representation learning. A labeled validation set containing benign and malicious graphs is used only to calibrate the anomaly threshold. We evaluate TRACE on StreamSpot, GraSec-IoT, and Unicorn Wget against a supervised graph neural network and the benign-only GraphCL baseline. TRACE obtains F1 scores of 0.923, 0.790, and 0.583, respectively. Compared with GraphCL, this is higher on StreamSpot (0.450) and Unicorn Wget (0.203), but lower on GraSec-IoT (0.975). The supervised model leads on StreamSpot and GraSec-IoT, whereas TRACE has the highest F1 on Unicorn Wget. The mixed results show that topology-aware benign-only learning can improve detection in some graph settings but does not provide a uniform advantage.

cs.CR · cs.AI

新论文 · v1arXiv:2611.21547

Fundamental Tradeoffs in Sampling, Transmission and Information Freshness: Instantaneous Feedback

Subhankar Banerjee, Sennur Ulukus

原文摘要

We study a time-slotted generate-at-will status-update system over an erasure channel with transmission success probability $q$, subject to average sampling- and transmission-rate constraints $f_s$ and $f_r$, respectively. The sampler-transmitter pair jointly decides whether to idle, retransmit a stale packet, or replace it with a fresh sample. We derive a universal lower bound on the optimal average age of information, analyze a class of stationary randomized policies, and obtain an optimal policy within this class that provides a $4$-approximation guarantee. The joint problem reduces to the sampling-constrained problem when $f_s\leq qf_r$ and the transmission-constrained problem when $f_s\geq f_r$. For $qf_r<f_s<f_r$, we formulate a constrained Markov decision process (CMDP) and introduce the class $\barΠ$ of $(W,R)$ policies, where $W$ specifies a waiting threshold for transmission and $R$ specifies a packet-replacement threshold. We prove that, for every choice of Lagrange multipliers, the corresponding Lagrangian-relaxed Markov decision process admits an optimal policy in $\barΠ$. We then formulate a linear program (LP) over distributions of $(W,R)$ policies and prove that choosing a policy according to an optimal LP solution yields an optimal CMDP policy. Moreover, there exists an optimal LP solution assigning positive probability to at most three $(W,R)$ policies. Since $\barΠ$ is countably infinite, for every $ε>0$ we construct a finite subset $\barΠ_ε\subset\barΠ$ and show that the LP restricted to this set yields an $ε$-optimal policy. Finally, we derive a stronger pair of lower bounds by considering systems with only the sampling-rate or transmission-rate constraint. Using these bounds, we construct a policy randomizing among four $(W,R)$ policies with a $2$-approximation guarantee for $qf_r<f_s<f_r$.

cs.IT · cs.NI · eess.SY

版本更新 · v3arXiv:2611.09822

Discovering formally verified quantum programs with AI

Sergey Shirobokov, Ben Jaderberg, Katerina Hristova, George Tsoukalas, Johannes Bausch, Eric Wieser, Francisco J. H. Heras, Nicholas C. Rubin 等 25 位作者

原文摘要

The timeline by which quantum computers can solve breakthrough problems in science depends on improved quantum algorithms as much as on better hardware. Such algorithmic advances are typically achieved through many years of expert human collaboration. In mathematics and computer science, large language models have accelerated progress through automated discovery loops. However, quantum algorithms can only be evaluated by classical computers on restricted or small instances. Here we demonstrate automated discovery of quantum programs beyond these regimes including order-of-magnitude improvements on scientific applications. To achieve this, we build a quantum program library in the Lean theorem prover in which Gemini 4 agents synthesize novel programs against formal problem specifications and verify their correctness and cost. Agent teams collaborate, sharing results and knowledge through wikis and discussing ideas at organized conferences. Our results improve on prior baselines for parallel search (up to 2.57x), quantum arithmetic (290x), and simulations relevant to fusion, photochemistry and drug-metabolism by 12x, 8x and 2.5x respectively. Combining human and artificial intelligence at scale, under the rigor of mathematical proof, lets researchers design algorithms that today's classical and quantum computers cannot test, shortening the path to practical quantum computation.

quant-ph · cs.AI · cs.PL

新论文 · v1arXiv:2611.21542

强制长期覆盖的代价:在线共形预测中的相变

The cost of enforcing long-run coverage: a phase transition in online conformal prediction

Yu Gui, Rina Foygel Barber, Cong Ma

AI 速读 基于摘要

作者证明在线共形预测中,对长期经验覆盖的约束强度存在相变:当偏差要求为 O(T^{-β}) 且 β≤1/2 时可兼顾 i.i.d. 下的瞬时覆盖最优性,而 β>1/2 时则需付出代价。

math.ST · cs.LG · stat.ML

查看原文摘要

Consider an online prediction setting, where at each time, we are given a new feature vector and asked to provide a prediction interval or prediction set that will likely contain the corresponding response. In this setting, if the data points are i.i.d. (or more generally, exchangeable), conformal prediction provides a mechanism for building valid prediction sets around the output of any trained model, offering coverage probability $\geq 1-α$ at each time $t$. In practice, however, issues such as distribution drift, changepoints, or other challenges may cause violations of the i.i.d. assumption. In this adversarial setting, online conformal prediction methods can still offer guarantees on long-run empirical coverage. However, there is a trade-off between these two types of goals: enforcing tight constraints on long-run empirical coverage to protect against the adversarial setting can lead to unstable oscillations in the instantaneous training-conditional coverage in the i.i.d. setting. In this work, we seek best-of-both-worlds algorithms that aim to minimize cumulative error in instantaneous training-conditional coverage when in the i.i.d. setting, while also offering long-run empirical coverage guarantees in the adversarial setting. Specifically, consider a condition that requires long-run empirical coverage to deviate from the target level $1-α$ by at most $\mathcal{O}(T^{-β})$, for some $β\in[0,1]$. We prove that this family of conditions can be described with a phase transition. For $β\in[0,\frac{1}{2}]$, it is possible to construct algorithms satisfying such a constraint in the adversarial setting, while offering the same instantaneous coverage performance as split conformal prediction if the data is in fact i.i.d. On the other hand, for $β\in(\frac{1}{2},1]$, this type of condition comes at a cost, and does not achieve best-of-both-worlds behavior.

新论文 · v1arXiv:2611.21541

SciResearch-Eval:评估自主实验智能体的科学判断力

SciResearch-Eval: Evaluating Scientific Judgment in Autonomous Experimental Agents

Brian T. Weston, Alondra Torres Contreras, Aldair E. Gongora

AI 速读 基于摘要

作者提出一个交互式基准,让智能体自行设计热学实验、使用可能欠分辨或物理错误的模拟器,并对带95%区间的材料性质估计进行校准评分。

cs.AI · cs.LG · physics.comp-ph

查看原文摘要

We introduce SciResearch-Eval, an interactive benchmark of scientific judgment built on a standard laboratory problem: measuring a material's thermal properties by heating it and fitting a heat-conduction simulator. An agent designs its own experiments, uses a supplied simulator that may be under-resolved or physically wrong, and reports each property with a 95% interval. To our knowledge it is the first benchmark to combine agent-designed experiments, a deliberately flawed simulator, and proper scoring of calibrated intervals against exact ground truth. On a held-out split (93 tasks, 9 models, 2,511 episodes), models handle procedural traps. When the simulator is missing physics, most report wrong values while stating they are 95% sure: their ranges contain the truth in 20-62% of cases, against 94% for GPT-6 Astra and 99% for Claude Fable 5.2. At default effort the failing Claude 5.5 models rarely diagnose the missing physics (Opus in 35% of episodes, against 66% for Astra), and even when they do, their ranges often miss; Astra and Fable design experiments in which the flawed simulator is accurate, such as gentle heating, which keeps Astra calibrated even when it does not name the cause. Asking for wider intervals does not help; stating the strategy improves interval scores 1.6-2.5-fold, replicated on a pre-registered fresh split, but coverage barely moves. A pre-registered effort ablation shows that the correction is latent in the Claude 5.5 models: at maximum effort Opus improves more than tenfold and is no longer detectably behind Astra at default, but only with 13-31 times more reasoning; older and open-weight models gain nothing. Fable 5.2 is the most accurate model at default effort (interval score 1.9 times better than Astra's) but writes 6 times as many tokens, and at Astra's token count it falls short. We release the environment, graders and harness.

新论文 · v1arXiv:2611.21539

看见却未言说:视觉语言模型中的跨图像比较定位与修复

Seen but Unsaid: Locating and Repairing Cross-Image Comparison in Vision-Language Models

Zhaoning Zhang

AI 速读 基于摘要

作者报告视觉语言模型在跨图像匹配任务中存在两个失败点,并发现一小群注意力头承载比较功能,仅微调其查询和键投影即可显著提升性能。

cs.CV · cs.CL · cs.LG

查看原文摘要

Vision-language models (VLMs) often fail to match a point or an object across two images, even when the answer can be decoded from their own hidden states. We trace this failure from the visual tokens to the answer letter, in Qwen3-VL (2B-32B), InternVL3.5-8B, and Gemma-3-12B, on synthetic shape matching, same-instance point correspondence (HPatches), and semantic correspondence (SPair-71k), and find two distinct failure points, a small set of attention heads that carries the comparison, and a repair that touches 0.02% of the parameters. Two failure points: exact copies are compared but not read out. An answer-position probe exceeds the calibrated output by 15 to 25 points in every family, for nameable and unnameable shapes alike, and steering along the probe's direction moves no more answers than random directions. Semantic correspondences are present in the visual tokens but never reach the answer. One pathway: redistributing the cross-image attention of 16-32 heads, with its mass preserved, removes 17-22 points of synthetic and 15-32 points of HPatches accuracy, against at most 7 for random or attention-matched heads. A lever that training finds on its own: training only these heads' query and key projections raises SPair-71k accuracy by 28.3 points (Qwen3-VL-8B) and 25.1 points (InternVL3.5-8B), beats both layer-matched and attention-matched heads, and transfers to HPatches and BLINK. An unconstrained all-layer adapter routes 21-51% of its gain through the attention of the same heads, against at most 7% for random heads, and does so by changing what they read (83-86% of the effect) rather than their weights. Every decision rule was frozen before its run, and every reported number is recomputed by independent verification scripts.

版本更新 · v2arXiv:2611.17466

面向环境辅助生活的用例驱动本体建模与NeOn方法

Use-case-driven ontology modeling with the NeOn methodology for ambient assisted living

Daniele Spoladore, Marco Sacco, Alberto Trombetta, Edoardo Battisti Sironi

AI 速读 基于摘要

作者报告了在意大利Design For All项目中,为虚拟家庭框架开发语义数据层本体的工作,该本体基于两个用例需求,采用NeOn方法构建,并复用现有本体。

cs.DB · cs.AI

查看原文摘要

Research on smart homes and ambient assisted living (AAL) has grown steadily over the last decade, driven largely by the ageing of the population. A smart home has to coordinate heterogeneous smart objects in order to offer services tailored to its dwellers, and this requires a shared formal description of both the dwellers and the devices. We present the ontology developed as the semantic data layer of the Virtual Home Framework in the Italian Design For All project. Its requirements are derived from two use cases: a frail elderly woman who exercises at home on a cycle-ergometer, and a designer who configures a kitchen for users with different impairments. The requirements are collected in an Ontology Requirements Specification Document and the ontology is built with the NeOn methodology, reusing and reengineering existing ontologies where possible. The resulting modular ontology describes users through the International Classification of Functioning, Disability and Health (ICF) and through their cardiorespiratory fitness; it also describes smart objects, their programs, the measurements they produce, and the comfort dimensions of the home. SWRL rules classify fitness levels, suggest exercise loads, assess indoor comfort, and identify the smart objects suited to a given impairment.

新论文 · v1arXiv:2611.21533

中国电力数据资产的激励对齐:区块链赋能的贡献信用框架

Incentive Alignment for Electricity Data Assets in China: A Blockchain-Enabled Contribution-Credit Framework

Jiazheng Zhang, Shouwei Li, Yutian Deng, Wei Wei, John Cartlidge

AI 速读 基于摘要

提出区块链赋能的贡献信用框架,利用延迟证据、动态信用、托管和报告关联惩罚促进电力市场中真实报告贡献并实现激励分配。

cs.CY · cs.DC

查看原文摘要

Modern electricity markets increasingly rely on reported operational contributions to allocate incentives, recognise cooperation, and coordinate activities across multiple organisations. However, supporting evidence for many reported contributions becomes available only after subsequent metering, dispatch, settlement, or auditing processes, making it difficult to reward genuine contributions while discouraging strategic over-reporting. Existing approaches largely address data sharing, performance verification, blockchain record management, or incentive allocation in isolation, providing limited support for integrating delayed evidence into a unified incentive mechanism. This paper proposes a blockchain-enabled contribution-credit framework for truthful reporting under delayed evidence. The framework links authenticated evidence to contribution recognition through dynamic credit updating, escrow, report-linked penalties, and automated incentive execution. Developed using the Chinese electricity market as the primary setting, it is demonstrated through two representative coordination scenarios, with adaptations illustrating its applicability to UK and US electricity-market structures. A controlled heterogeneous-agent simulation evaluates the behavioural effects of the proposed mechanism, while security analysis, public-data workflow analysis, and blockchain implementation experiments assess its practical feasibility. The results show that integrating delayed evidence with dynamic credit, escrow, and report-linked penalties promotes truthful reporting while providing a transparent and auditable process for translating verified operational contributions into incentive allocation. The proposed framework offers a practical mechanism for improving accountability, coordination, and incentive compatibility in collaborative electricity markets.

版本更新 · v2arXiv:2607.25244

CADENCE: A Cardiac Atom Dictionary for Interpretable Neural Concept Extraction from ECG Foundation Models

Yixuan Duan, Arjun Naik, Sadeer Al-Kindi, Wei Qiu

原文摘要

Foundation models for 12-lead electrocardiograms (ECGs) transfer well across clinical tasks, but the physiological knowledge encoded in their representations remains opaque. We present CADENCE, a framework that decomposes an ECG foundation model into a human-interpretable, queryable dictionary of physiological concepts. Using a BatchTopK sparse autoencoder, CADENCE factorizes Layer-6 embeddings from more than nine million ECG tokens into 8,192 sparse cardiac atoms. These atoms align better than individual dense embedding dimensions with clinical phenotypes and waveform morphology, recovering arrhythmias, conduction abnormalities, infarction and repolarization patterns, chamber and axis findings, and lead- and beat-phase-specific waveform primitives. At Layer 6, the best atoms achieve mean AUROCs of 0.88 for clinical phenotypes and 0.90 for morphology, versus 0.78 and 0.83 for the best dense dimensions. Sparse atom probes match or outperform dense probes for phenotype, morphology, and age prediction while attributing each prediction to a small set of interpretable atoms; phenotype AUROC improves from 0.93 to 0.95. Atom-space geometry recovers physiologically coherent relationships, and targeted atom ablation selectively changes frozen downstream outputs. An automated LLM pipeline generates and quantitatively validates atom descriptions by predicting held-out activations. On independent external ECG datasets, CADENCE recovers overlapping concepts and maintains consistent phenotype-prediction performance. CADENCE provides a scalable framework for discovering and auditing the physiological knowledge encoded by ECG foundation models.

cs.AI

版本更新 · v2arXiv:2604.11250

TEMPER: Reducing Attribute Leakage from Face Recognition Embeddings

Ünsal Öztürk, Vedrana Krivokuća Hahn, Sushil Bhattacharjee, Sébastien Marcel

原文摘要

Face recognition embeddings encode soft-biometric attributes such as gender and ethnicity, which can be inferred from templates. This paper proposes TEMPlate Entropy Regularisation (TEMPER), a post-hoc method that removes an attribute. TEMPER learns a linear map of the embedding in a split-latent variational autoencoder. The map is initialised at the principal component analysis (PCA) solution of the embeddings and trained to maximise the predictive entropy of an auxiliary attribute classifier. A relational term keeps the similarities of mated pairs close to the embedding similarities. We evaluate the removal of gender and a four-group ethnicity label from ArcFace embeddings against ten prior post-hoc methods and two label-free controls. Every method is trained on VGGFace2 and tested on IJB-C and RFW at false match rates down to $10^{-4}$. Leakage is the balanced accuracy of the strongest of four attacker families trained on transformed VGGFace2 templates. TEMPER retains the highest IJB-C true match rate at a false match rate of $10^{-3}$ at every leakage threshold for both attributes. TEMPER retains a true match rate of 82.4% at a gender leakage of at most 52.5%, close to chance, against 76.7% for the best prior method. In the ablation, this improvement comes from the PCA initialisation and the relational term.

cs.CV

新论文 · v1arXiv:2611.21529

Procedure without Judgment: What Small Language Models Learn under an Exact Verifier

Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R., Arun Prakash, S. Senthilkumar

原文摘要

When an authorization policy blocks an agent's tool call, the audit log should name the facts that forced the decision and nothing more. For an executable policy over an enumerable context space this minimal sufficient reason can be computed exactly, so an explanation is scored against ground truth rather than a proxy for it. We use that exactness to ask what a model can learn from a verifier that has no error in it. The explainer sees one request and one decision, never the policy, and has thirty turns in which it may call the policy on altered requests and ask whether a candidate set of facts is sufficient. Frontier models find the exact reason about half the time with the tools alone, and one sentence telling them to shrink the answer lifts Haiku 4.5 from 58% to 75%. A 4B model fine-tuned on 2000 traces of the deletion algorithm reaches 92% on the policy it was trained on. Teacher kind is what moves this: at matched data size the algorithm-taught student leads the frontier-taught one in all three training seeds, and the two arms never overlap. What the student learns is a fixed schedule of sufficiency checks, and the schedule does not travel. On three public policies it never saw, its answers stay sufficient (94%) and stop being minimal (48%), while Haiku under the same sentence is exact on all 47 episodes. Reinforcement learning from the exact reward leaves held-out accuracy where it was and inverts the strategy, from probing the policy to spending the entire budget on sufficiency checks. The oracle made the effect of training legible, but it did not make training better.

cs.AI · cs.CL · cs.LG

版本更新 · v3arXiv:2510.12915

Toward LLM-Supported Automated Assessment of Critical Thinking Subskills

Marisa C. Peczuh, Nischal Ashok Kumar, Ryan Baker, Blair Lehman, Danielle Eisenberg, Caitlin Mills, Payu Wittawatolarn, Kushaan Naskar 等 14 位作者

原文摘要

As the world becomes increasingly saturated with AI-generated content, disinformation, and algorithmic persuasion, critical thinking - the capacity to evaluate evidence, detect unreliable claims, and exercise independent judgment - is becoming a defining human skill. Developing critical thinking skills through timely assessment and feedback is crucial; however, there has not been extensive work in educational data mining on defining, measuring, and supporting critical thinking. In this paper, we investigate the feasibility of measuring "subskills" that underlie critical thinking. We ground our work in an authentic task where students operationalize critical thinking by writing argumentative essays. We developed a coding rubric based on an established skills progression and completed human coding for a corpus of student essays. We then evaluated three distinct approaches to automated scoring: zero-shot prompting, few-shot prompting, and supervised fine-tuning, implemented across three large language models (GPT-5, Llama 3.1 8B, and ModernBERT). Fine-tuning Llama 3.1 8B achieved the best results and demonstrated particular strength on subskills with highly separable proficiency levels with balanced labels across levels, while lower performance was observed for subskills that required detection of subtle distinctions between proficiency levels or imbalanced labels. Our exploratory work represents an initial step toward scalable assessment of critical thinking skills across authentic educational contexts. Future research should continue to combine automated critical thinking assessment with human validation to more accurately detect and measure dynamic, higher-order thinking skills.

cs.CY · cs.CL · cs.LG

新论文 · v1arXiv:2611.21528

Post-Quantum Migration of Wi-Fi Key Establishment: A Hybrid ML-KEM Design for OWE and FILS, Validated on OWE with hostapd

Jesús R. Abascal, Ana I. Gómez, Domingo Gómez-Pérez

原文摘要

The key agreements that protect a Wi-Fi connection rely on Diffie-Hellman, which a sufficiently capable quantum computer would break; an adversary can therefore record an association today and decrypt its traffic years later. Key establishment is thus the part of IEEE 802.11 that has to be migrated first. This work targets the two protocols that perform that agreement inside the frames used to set up the link: Opportunistic Wireless Encryption (OWE), which encrypts otherwise open networks, and Fast Initial Link Setup (FILS), designed for fast connection in dense and mobile deployments. We propose replacing their Diffie-Hellman exchange with a hybrid one that runs the classical elliptic-curve agreement alongside ML-KEM (FIPS 203) and derives the master key from both secrets, so the connection stays protected as long as either component remains unbroken. The exchange reuses the frames each protocol already sends and adds no extra round trip; an access point can advertise the hybrid mode alongside classical OWE, and a station configured to require it refuses to associate without a completed post-quantum exchange. Binding the advertised capabilities to the derived key is specified as a design extension and is not part of the prototype. We validate the design with a working implementation on hostapd and wpa_supplicant: both endpoints derive the same key in every measured connection, with the two smaller parameter sets each enlarged association frame fits in a single frame even under a conservative 1500-byte fragmentation threshold, and the added connection time and computation stay below half a millisecond. The measurements are obtained on OWE; the design carries over to FILS, whose frame budget is left for specific measurement. Of the three ML-KEM parameter sets, the intermediate one offers the best balance between security level and size.

cs.CR · cs.NI

版本更新 · v2arXiv:2611.12307

PACE-ECG: Patient-Aware Contrastive ECG Pretraining; Leveraging Longitudinal Structure for Transferable Representations

Riccardo Cavarra, Lupo Lovatelli, Shaheim Ogbomo-Harmitt, Jakub Grzelak, Adelaide De Vecchi, Andrew King, Oleg Aslanidi

原文摘要

Foundation models for physiological signals are commonly evaluated on in-domain interpretation tasks, but their ability to transfer to longitudinal clinical prognosis across healthcare systems remains uncertain. We developed PACE-ECG, an ECG pretraining framework that combines contrastive learning across temporally neighbouring recordings from the same patient with clinically guided multitask supervision. We evaluated frozen ECG representations for post-myocardial-infarction all-cause mortality and incident heart failure prediction across MIMIC-IV and two external HEEDB cohorts, comparing the proposed representation with DeepECG-SSL, a state-of-the-art model, and two control baselines. Across both downstream tasks, the proposed model outperformed DeepECG-SSL in-domain (AUROC +1.9% for mortality and +4.0% for heart failure) and on external populations in HEEDB-Boston (+5.6% for mortality +10.3% for heart failure) and HEEDB-Atlanta (+6.9% for mortality +11.0% for heart failure) while using an encoder 41 times smaller and a fraction of the pretraining data. A matched ablation showed that patient-temporal pairing improved external mortality and heart failure AUROC over generic self-supervision by 7.0% and 9.4% on HEEDB-Boston and 8.9% and 9.3% on HEEDB-Atlanta. These findings indicate that pretraining-objective design greatly influences downstream transfer alongside model and data scale, and that in-domain performance alone is insufficient to establish the clinical generalisability of ECG foundation representations.

cs.AI

版本更新 · v3arXiv:2602.17737

NestRL:面向人机团队相互适应的嵌套训练机制

NestRL: A Nested Training Regime for Mutual Adaptation in Human-AI Teaming

Upasana Biswas, Durgesh Kalwar, Subbarao Kambhampati, Sarath Sreedharan

AI 速读 基于摘要

NestRL 将人机团队建模为有限层级 I-POMDP,通过嵌套训练让智能体与下层自适应智能体对抗,从而避免过拟合特定伙伴并提升与人类队友的协作表现。

cs.RO · cs.LG · cs.MA

查看原文摘要

Mutual adaptation is a central challenge in human-AI teaming, as humans naturally adjust their strategies in response to an AI agent's behavior. Existing approaches attempt to approximate human behavior by diversifying training partners; however, these partners are typically static and fail to capture the adaptive nature of human teammates. When agents are trained jointly in standard multi-agent settings, they often converge to opaque coordination strategies that work only with their co-trained partners, leading to poor generalization. To model adaptive human behavior, we formulate human-AI teaming as an Interactive Partially Observable Markov Decision Process (I-POMDP). We propose NestRL, a nested training regime that learns the solution to a finite-level I-POMDP by training agents at each level against adaptive agents from the level below. This exposes agents to adaptive behavior while preventing emergence of opaque coordination strategies. We provide theoretical analysis showing that NestRL agents avoid convergence to partner-specific strategies, and validate this empirically in the Overcooked domain against state-of-the-art baselines. NestRL achieves higher task performance with both unseen adaptive agents and real human teammates, while exhibiting significantly greater adaptability over the course of interaction.