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

+1295新增论文
+1026其中 AI 相关
+111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 16:10各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 16:40 — 2026-11-17 16:40(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 16:10库内论文最新更新时间:2026-11-17 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。

25,122 已收录论文20,967 AI 相关7,309 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 25,122 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)
版本更新 · v2arXiv:2606.30058

Emergence of a Shared Canonical Object Frame from In-the-Wild Videos

Tom Fischer, Martin Sundermeyer, Adam Kortylewski, Eddy Ilg

原文摘要

Comparing object orientations and positions across different instances requires their poses to be expressed in a shared canonical frame. Establishing such frames has traditionally required manual annotation, creating a scaling bottleneck that limits category and instance diversity. We show that a shared canonical frame can instead emerge from self-supervised training on object-centric videos of rigid objects captured in the wild, using only noisy camera poses from Structure-from-Motion. Our key idea is to route all training sequences through a shared geometric bottleneck: a coarse canonical mesh that carries no category-specific detail. By learning dense correspondences from image pixels to this mesh, and estimating per-sequence alignments from noisy SfM geometry, a common canonical frame emerges from multi-view consistency and the semantic priors of the feature extractor, without any canonical pose labels or category conditioning. Trained in a self-supervised manner on ${\sim}160{,}000$ in-the-wild object videos, our method achieves competitive accuracy on category-level pose estimation benchmarks compared to methods that rely on canonical pose supervision. The code and checkpoint are available on \href{https://github.com/Fischer-Tom/Emergent-Canonical-Frame/}{github.com/Fischer-Tom/Emergent-Canonical-Frame/}.

cs.CV

版本更新 · v2arXiv:2605.07878

Black-box model classification under the discriminative factorization

Hayden Helm, Merrick Ohata, Carey Priebe

原文摘要

Access to modern generative systems is often restricted to querying an API (the ``black-box'' setting) and many properties of the system are unknown to the user at inference time. Recent work has shown that low-dimensional representations of models based on the relationship of their embedded responses to a set of queries are useful for inferring model-level properties. However, the quality of these representations is highly sensitive to the query set. We introduce the \emph{discriminative factorization} to distinguish between high- and low-quality query sets in the context of black-box model-level classification. Under this framework, the probability of chance-level classification is bounded by a term that decays exponentially in the query budget. On three auditing tasks, estimated factorization parameters predict the empirical performance decay rate. We conclude by showing that query sets selected using the estimated factorization reproduce the empirical ordering of oracle query sets.

cs.LG · stat.ML

版本更新 · v2arXiv:2605.25120

Evidence-Linked Radiology Reporting: A Human-Supervised Reference Architecture for Structured Imaging Intelligence

Houman Kazemzadeh, Kamyar Naderi

原文摘要

Radiology reports remain the primary mechanism by which imaging findings are communicated to clinical teams. However, much of the structured information behind these reports, including measurements, image evidence, prior comparisons, lesion identity, uncertainty, and terminology, often remains trapped in free text or fragmented across picture archiving and communication systems, radiology information systems, reporting workstations, worksheets, advanced visualization tools, and electronic health records. This paper proposes a human-supervised, evidence-linked reference architecture for structured radiology reporting. The framework combines exam-specific templates, speech-to-structure processing, measurement and segmentation capture, controlled AI-assisted drafting, and standards-based interoperability using DICOM, DICOM Structured Reporting, DICOM Segmentation, HL7 FHIR, RadLex, SNOMED CT, LOINC, and UCUM. The system is positioned not as an autonomous report generator, but as a structured intelligence layer for enterprise imaging that supports reviewed reporting, longitudinal comparison, clinical data reuse, governance, and integration with PACS, RIS, EHR, analytics, and registry workflows. The paper also discusses modality-specific deployment considerations, clinical safety risks, validation requirements, cybersecurity, privacy, quality management, and regulatory boundaries for AI-assisted radiology reporting systems.

cs.CL · cs.AI · cs.HC

新论文 · v1arXiv:2611.08657

JEPAhead: From Inpainting to Causal Forecasting for Urban Driving

Daniel G. P. Petrini, Davi Pincinato, Fabio Grassiotto, Pedro L. F. Prado, Alexandre F. S. Osorio, Raphael V. Ramos, Felipe Pamboukian

原文摘要

We fine-tune a pre-trained V-JEPA1 predictor from bidirectional latent inpainting to action-free causal forecasting while keeping the encoder frozen. Using contiguous past observations, horizon-aligned targets, and group-level causal attention, the model forecasts eight future token groups, corresponding to sixteen frames, in one forward pass. On CARLA Town12, it retrieves the correct future among 591 candidates in 69.0% of cases, compared with 55.3% for persistence, with greater gains at longer horizons and on tokens exhibiting greater change. It also outperforms a compact predictor trained from scratch with six times fewer parameters. Semantic analysis indicates driving-relevant information in predicted features: a fixed linear probe trained on real encoder tokens achieves 0.16 mIoU on patches undergoing semantic-class changes, versus 0.13 for persistence. Vehicle-conditioned retrieval improves over persistence by 15 percentage points at the longest horizon. Pixel-space evaluation shows modest L1 gains but little improvement under LPIPS, motivating direct evaluation through latent and semantic measures alongside an oracle reconstruction reference. These findings support further investigation of latent forecasting for driving perception, while downstream utility remains unverified.

cs.CV · cs.AI

新论文 · v1arXiv:2611.08656

Higher Order Component Attribution via Learned Surrogates in High Energy Physics

Lauri Laatu, Aritra Bal, Benedikt Maier, Markus Klute, Michael Spannowsky

原文摘要

Experimental High Energy Physics (HEP) has adopted the transformer architecture for identification of jets, particularly the state-of-the-art Particle Transformer (ParT) which injects explicit information about particle correlations into the attention mechanism. While able to achieve state-of-the-art results in accuracy, interpretability to its effectiveness has been limited. In this paper we propose component attribution methods using Kolmogorov-Arnold Networks (KANs) that directly tie back to the physical descriptors of jets, to probe whether mechanisms such as Multi-Head Attention (MHA), or the ParT architecture, are able to learn these as discriminating features.

cs.LG · hep-ex · hep-ph

版本更新 · v5arXiv:2602.22710

Same Words, Different Judgments: How Preferences Vary Across Modalities

Aaron Broukhim, Nadir Weibel, Eshin Jolly

原文摘要

Preference-based reinforcement learning (PbRL) is the dominant framework for aligning AI systems to human preferences. However, evaluation protocols for such data were designed for text and have not been validated for speech. We present the first intraclass correlation coefficient (ICC)-based, controlled cross-modal study of human and synthetic preference annotations, comparing text and audio evaluations of identical semantic content across 100 prompts. We show that achieving \textit{good} (audio) to \textit{near good} (text) agreement within either modality (ICC(2,$k$) $\approx$ .81 audio, .74 text) requires $\sim$9 raters and modalities show marked differences in how people report preferences: audio raters exhibit narrower decision thresholds, reduced length bias, and more user-oriented evaluation criteria, with near-chance cross-modality agreement. We demonstrate that synthetic ratings can be used to effectively predict inter-rater agreement, thus serving as an early signal for stimulus selection and proxy for human annotations. Together, these findings argue that evaluation protocols for audio preference data require modality-specific design rather than direct adaptation from text. Code, data, and the audio corpus are available at: https://huggingface.co/datasets/sciminds/same-words-different-judgements

cs.SD · cs.AI · cs.HC

版本更新 · v3arXiv:2609.00634

Beyond Landmark Extraction: A Framework for Robust Geometric Feature Evaluation in Structured Image Classification

Saravana Mauree, Sakshi Arya

原文摘要

Much of the literature on structured image recognition has disproportionately focused on the comparison of classification algorithms. Rather than investigating which classifier performs best, this paper instead asks: what should a classifier know before it ever makes a prediction? In structured vision problems such as gesture recognition, facial expression categorization, and medical image analysis, discriminative information lies less in individual pixels and more in spatial relationships between semantic parts. Raw pixel spaces are high-dimensional, sensitive to nuisance variation, and often obfuscate the geometric structures that make visual tasks interpretable. Landmark extraction provides one form of dimension reduction, but it does not by itself determine the information preserved. This paper studies the post-landmark feature map as the central object of analysis and proposes a systematic framework for constructing and interpreting landmark-derived representations as an, informed, feature-based "dimension reduction" step. Using static hand gesture recognition as a case study, we evaluate coordinate, distance, angle, and hybrid representations through perturbation and ablation experiments. The results show that visually variable data exposes substantial gaps between raw coordinate features and their geometrically invariant counterparts, while hybrid representations achieve the strongest overall performance by combining complementary geometric components. These findings frame feature construction as a fundamental modeling decision and ultimately suggests that the question of what representation should a classifier learn from is one worth asking. The code used for feature construction and evaluation is available at https://github.com/ShivMaureeCWRU/Feature_based_dimension_reduction

cs.CV

版本更新 · v2arXiv:2605.11135

Control Charts for Multi-agent Systems

Hayden Helm, Carey Priebe, Brandon Duderstadt

原文摘要

Generative agents have proven to be powerful assistants in a wide variety of contexts. Given this success, users are now deploying agents with minimal restrictions in open ended, multi-agent environments. Current methods for monitoring the dynamics of open-ended multi-agent systems are limited to aggregate statistics, qualitative inspection, or detecting change between two fixed timepoints. In this paper, we extend the process-theoretic notion of adaptive control charts to multi-agent systems to enable automated monitoring. Using simulation, we demonstrate that adaptive control charts are necessary for monitoring multi-agent systems that can learn from their environment. We further demonstrate, both empirically and theoretically, that adaptive control charts are susceptible to adversarial agents that defect sufficiently slowly. These results suggest a fundamental tradeoff in multi-agent system control: monitors with fixed baselines flag legitimate learning, while monitors with adaptive baselines admit slow adversaries. We conjecture this holds for any monitor.

cs.MA · cs.AI · cs.LG

新论文 · v1arXiv:2611.08655

Scoring, Not Learning: Decomposing Catalog-Consolidation Gains in Web-Scraped Retail Product Recognition

Kaden Leis, Xiang Ma

原文摘要

Retail product catalogs assembled from web image search are cheap to build and pervasively noisy: queries return packaging shots instead of products, and entries proliferate under names that cannot be distinguished visually. Consolidating such a catalog can look like an alternative to scaling the model. We show this is not a comparison between two ways of improving a recognizer, but between improving a recognizer and changing what counts as correct. We study a public archive of 165,769 cheese images across 1,824 query-named entries. A packaging filter and near-duplicate removal reduce it to a 998-class recognition set on one fixed, group-aware split. Canonicalizing entries to their base type (844 classes) raises top-1 accuracy by 4.0 points. Scoring the unchanged model against the merged label space, by summing its predicted probability within each canonical group, recovers +4.27 points with no retraining (+4.25 over six seeds). Retraining on the consolidated catalog then adds -0.10$\pm$0.53, +0.08$\pm$0.65 and -0.10$\pm$0.65 points at 28, 50 and 88 M parameters, indistinguishable from zero at every capacity ($\pm$ is the across-seed standard deviation). That component is specific, not mechanical: random merges with the identical size profile yield only +0.68 points, and the three backbones agree to within 0.1 points. But it is overwhelmingly category coarsening, not alias correction: across the 37 merged groups, type coarsenings supply 94% of the gain and alias collapses only 7%. We also detect no interaction between consolidation and backbone size: tripling backbone parameters is worth +1.50$\pm$0.57 points on the raw catalog and +1.42$\pm$00.44 on the canonical one, a within-seed interaction of -0.08 [-0.79,+0.63]. On this archive, the reported consolidation gain primarily reflects the evaluation label space, and separating that out costs one evaluation

cs.CV · cs.AI

新论文 · v1arXiv:2611.08654

CS-Pi: Constraint-Satisfying Flow Policy Sampling

Soumojit Bhattacharya, Oliver Kroemer, Shubham Tulsiani

原文摘要

A flow-matching policy deployed in the field must often satisfy a constraint that was absent from its demonstrations, such as avoiding an obstacle it has never seen. Retraining for every new constraint is impractical, so the constraint must be enforced at inference time. Enforcing it must not discard what the policy learned: an action the policy would rarely sample may avoid the obstacle yet fail the task. We therefore want actions that are both safe, satisfying the constraint, and plausible, remaining likely under the policy. Gradient guidance, the most common approach, steers noisy states, so it must evaluate its cost on the policy's running estimate of the clean action; when the policy is uncertain between passing left or right of an obstacle, this estimate is their average and can pass straight through it. We instead build on rejection and projection. Rejection redraws actions until one is safe: every output is plausible, but the wait is intractable when safe actions are rare. Projection moves an action to the nearest safe one: it is efficient, but the result need not be plausible. Our key insight is that flow-matching sampling lets us combine the two, keeping projection's efficiency and rejection's plausibility. CS-Pi, our draw-project-renoise sampler, projects each draw to the nearest safe action, adds noise back scaled to how far the projection moved it, and re-runs the unmodified policy until a draw is safe. Replacing only the projection step extends CS-Pi to continuous costs. Across a 2D diagnostic, a 7-DoF shelf pick-and-place, an orientation preference, and a zero-shot Franka deployment, CS-Pi reaches 81% safe success on the shelf and 55% on hardware, against 55% and 40% for projection, while staying plausible.

cs.RO

版本更新 · v2arXiv:2609.38377

PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos

Max Ku, Jiaojiao Fan, Zekun Hao, Francesco Ferroni, Heng Wang, Wenhu Chen, Ming-Yu Liu, Prithvijit Chattopadhyay

原文摘要

Evaluating the physical consistency of generated videos remains a fundamental challenge. Existing approaches rely on off-the-shelf vision-language models, which can often be myopic to physical dynamics, or fine-tuned evaluators trained on human annotations, which overfit to dataset-specific cues and fail to generalize. A key challenge is that existing supervision sources provide either relative ordering or absolute scores, but not both reliably and consistently across varied settings. To this end, we introduce PhyProbe, an evaluator that extracts features from a frozen pretrained spatio-temporal encoder and maps them to a scalar physical consistency violation score via a lightweight scoring head. PhyProbe is trained through a unified objective combining pairwise ranking, regression on noisy scalar annotations, and anchor-based calibration over a curated set of heterogeneous supervision sources. Experiments show that PhyProbe outperforms prior methods on most pairwise benchmarks spanning real-generated and generated-generated pairs under varying correspondence, with the largest gains in no-correspondence and generated-generated settings where existing fine-tuned evaluators degrade sharply. PhyProbe achieves strong correlation with human judgments, with close agreement between rank-based and linear metrics, indicating that scores are both well ordered and anchored to a stable [0, 1] scale. Further, despite being trained on supervision indicative of physical consistency, without explicit general-preference labels, PhyProbe also performs competitively on human preference benchmarks: consistent with the observation that physics violations are entangled with broader quality degradations.

cs.CV

版本更新 · v2arXiv:2610.38076

Prompt Lottery in LLM-as-a-Judge: Measuring and Mitigating Sensitivity to Syntactic Rephrasing

Ilija Subasic, Brett Levert, Andrew Rabinovich, Sajjad Pakdamansavoji, Zhao Chen

原文摘要

LLM-as-a-Judge has become a standard for evaluating large language models, yet most approaches implicitly assume that a single judge prompt functions as a stable evaluation instrument. Prior work has primarily explored deliberate prompt modifications such as scoring rubrics, role descriptions, or chain-of-thought reasoning in order to optimize accuracy. In contrast, we investigate whether validated prompt variants intended to preserve evaluation semantics while differing in surface realization (\textit{paraphrastic rephrasings}) yield consistent judgments under a fixed evaluation task. We introduce \textit{Prompt Lottery}, a phenomenon in which paraphrastic rephrasings produce different LLMaJ judgments. Across a large-scale study spanning diverse evaluation tasks, judge families, and model backbones, we find that these variations can alter evaluation outcomes and, in some settings, reverse relative model rankings. A user study with 10 human annotators shows that LLMaJ judges exhibit 6-9$\times$ larger agreement degradation under prompt rephrasings than humans, falling below the generally accepted threshold in usability studies. This indicates that single-prompt evaluation is insufficiently robust for model ranking. Finally, we show that multi-prompt aggregation substantially improves robustness by emphasizing judgments that remain consistent across prompt variants.

cs.CL · cs.AI

新论文 · v1arXiv:2611.08652

An Anatomy-guided 3D Segmentation Pipeline for Prostate Surgical Phantoms from CT Scans

Iven Chen, Kuan-I Chung, Ayberk Acar, Susheela Sharma Stern, Alejandro O. Chara, Jie Ying Wu, Daniel Moyer

原文摘要

Full autonomy has been a long-term goal in robotic surgery and a near-to-medium-term goal for prostatectomy. Due to the relatively closed structure of the procedure, its standard-of-care robotic/laparoscopic solutions, and procedure economics, prostate procedures are an optimal early target for surgical automation. Prototyping and testing of possible solutions is done in constructed laboratory phantoms, either synthetic tissues or animal phantoms. To enable measurement of perceptual and robotic motion error, phantoms undergo volumetric imaging; these images are critical to both a potential deployed automatic system, used in planning motion and treatment (cutting, ablation, suturing, etc.), as well as post-hoc assessment of system performance. Rapid iteration on these phantom models yields small, inconsistent datasets, while the current workflow for human annotation is often anatomically unreliable and prohibitively time-consuming, rendering deep learning unsuitable at reasonable scales. To address these limitations, we present an automated 3D segmentation pipeline that uses classical medical image-processing techniques to encode the known anatomy of the phantoms as explicit geometric and intensity priors, which requires no training corpus and is transferred to each new phantom revision without re-annotation. Across 57 scans spanning multiple phantom revisions, our pipeline recovers the capsule interior at 0.83 median Dice on 11 contrast-suppressed scans and detects all 32 annotated focal lesions without false positives, completing a full scan in 2-8 minutes on commodity CPU hardware versus 1-2 hours by hand.

cs.CV

新论文 · v1arXiv:2611.08651

Turkish Multimodal Video Fact-Checking: A New Dataset and a Comparison of Zero-Shot Agentic and Fine-Tuned Systems

Azra Açıl

原文摘要

Video-based misinformation spreads rapidly on social media, but almost all existing fact-checking systems focus exclusively on English text. Tools for low-resource languages such as Turkish are severely limited. In this work, we present TeViD (Turkish Video Fact-checking Dataset), to the best of our knowledge the first multimodal video fact-checking dataset for Turkish. We compiled the dataset from articles published by Teyit.org, an IFCN-certified organisation, and enriched it with translated Snopes articles and synthetic examples to reduce class imbalance. Building on TeViD, we develop two verification pipelines that share the same open-source base model. First, in 3MFact-TR (Pipeline 1), we adapt the multi-role 3MFact framework to Turkish with the Qwen2.5-7B large language model and the Qwen2-VL-7B vision-language model, and add three modules of our own: a semantic inconsistency checker, a 5W1H question manager, and a bilingual evidence retriever that excludes fact-checking sites to prevent leakage. Second, as our Fine-Tuned Model (Pipeline 2), we fine-tune a single Qwen2.5-7B with Low-Rank Adaptation (LoRA) to produce closed-book verdicts from the claim and the video's textual description. We report accuracy, macro F1, True class F1, and True class recall for both systems, together with ablation studies.

cs.CV · cs.CL

版本更新 · v2arXiv:2611.04171

Descending Everest, Part II: Oracle Complexity of Minimizing a Sum of Convex $(L_0,L_1)$-Smooth Functions

Mikhail Rudomanov, Ivan Fomin, Alexander V. Gasnikov, Fedor S. Stonyakin

原文摘要

We study the minimization of the average of $n$ convex $(L_0,L_1)$-smooth functions: the Hessian norm of each function is bounded by an affine function of its gradient norm. We assume known upper bounds $R$ on the distance from the starting point to a minimizer and $δ$ on the difference between the minimum of the average and the average of the infima of the components. We derive upper and lower bounds on the oracle complexity of reaching accuracy $\varepsilon$ in function value in expectation. Up to logarithmic factors, both bounds are of order $n(1+(L_1R)^{2/3}) +\sqrt{\frac{n(L_0+L_1^2δ)R^2}{\varepsilon}+n(L_1R)^2}$. The upper bound is attained by the proposed method YETI. The method combines ideas of accelerated proximal methods and variance reduction methods with a heuristic for choosing additional points. The number of oracle calls made by the heuristic is bounded, which preserves the upper bound on the total number of queries needed to reach the target accuracy. In the experiments, YETI is compared with first-order methods on synthetic problems and Poisson regression problems. We also examine the stopping criterion and the effect of the heuristic separately. The lower bound is obtained by an explicit construction of families of instances that are hard for any first-order method.

math.OC · cs.LG · stat.ML

新论文 · v1arXiv:2611.08650

Differentially Private All-Pairs Min Cut Values

Anders Aamand, Justin Y. Chen, Mina Dalirrooyfard, Slobodan Mitrović, Sandeep Silwal, Yinzhan Xu

原文摘要

We study the problem of privately releasing the min cut values of all pairs of vertices in a given $n$-node weighted graph, under the edge-neighboring model. Straightforward application of advanced composition yields an approximate DP algorithm that outputs all min cut values up to $\tilde{O}(n)$ additive error. Prior works [Dalirrooyfard, Mitrovi{ć} and Nevmyvaka, 2023; Aamand et al., 2026] have established that $\tildeΘ(n)$ is the correct bound if the algorithm also needs to output cuts that realize the approximate min cut values. On the other hand, simply outputting the values could be an easier problem, but prior algorithms have been stuck on the $\tilde{O}(n)$ bound. In this work, we give an approximate DP algorithm outputting all-pair min cut values with $\tilde{O}(\sqrt{n})$ additive error, beating the linear error barrier. Our algorithm applies the sparse vector technique [Dwork and Roth, 2014] to maintain a hierarchical decomposition of the vertices based on the min cut structure. We also prove an $Ω(\log^{3/2} n)$ lower bound for this problem.

cs.DS

新论文 · v1arXiv:2611.08649

VoluCompose: Constructing Compact Volumetric Visual Representations for Medical Image Understanding

Zanting Ye, Yunrui Lin, Shengyuan Liu, Jing Hao, Chen Hu, Yefeng Zheng, Lijun Lu

原文摘要

Medical vision--language models can interpret volumetric images, but processing full volumes is costly because hundreds of slices produce long, redundant visual-token sequences. Existing compression methods often couple content selection with budget determination. We observe that neighboring slices share visual features and that attention concentration varies across visual encoders. We propose VoluCompose, a training-free, model-agnostic framework that separates what visual content to retain from how many tokens to allocate. Its hyperbolic token composition module groups contiguous slices into ordered support units and uses the Lorentz distance to account for feature magnitude and direction during token allocation, anchor selection, and refinement. Its capacity control module uses visual-encoder attention entropy to allocate more tokens when attention is more dispersed. We evaluate VoluCompose on two tasks across three datasets and four backbones. Across nine calibrated settings, VoluCompose attains the highest mean quality--retention hypervolume among the compared methods. It achieves a mean relative quality of 121.68\% against the uncompressed references while retaining 22.78% of visual tokens on average. Compression remains robust even at a 10% token budget. Across settings, the lowest ROUGE-L ratio to the uncompressed reference is 96.4\% for VoluCompose. The corresponding minima for the compression baselines range from 15.0% to 70.5%. Code is available at https://github.com/yezanting/VoluCompose.

cs.CV · cs.AI

版本更新 · v2arXiv:2607.13346

PRISM: Stress-Testing Alignment-Faking Claims

Aman Mehta

原文摘要

We judge whether AI systems are safe largely by watching how they behave. Alignment faking would break this: a model that behaves well only when it believes it is watched, or that complies now to avoid being changed by training, can pass every behavioral test. Such behavior has been reported in a frontier model, and open-weight models that comply more under a monitoring prompt are now read as showing it, with hidden-state probes proposed as detectors. We test both inferences, and neither holds. Of 18 model configurations, 11 comply more when told they are monitored. Yet a prompt factorial on four models shows that the training threat has no detectable effect: removing it changes compliance by -3.3 to +1.6 points. The prompt's wording and framing drive the gap instead. Probes fare no better. They separate monitored from unmonitored compliant answers (AUROC 0.96-0.99), but they separate refusals just as well: they read the prompt, not the faking. A steering direction learned only from refusals moves behavior as much as the "faking" direction. We release PRISM, five checks and a toolkit that catch each of these failures before they become claims.

cs.CR · cs.AI · cs.CL

新论文 · v1arXiv:2611.08647

IWIBench: Evaluating Gradient-Free Model Driven Intra-weight Injection

Chris von Csefalvay, Pranav Doma, Achyuthan Unni Krishnan, Tamás Földi

原文摘要

Intra-weight injection lets one model change another model's behaviour by editing its weights directly, without gradients. Such edits can range from altering lexical associations to enforcing output formats or updating factual knowledge. Despite growing interest in these approaches, there has been no systematic way to evaluate how well models perform them. We introduce IWIBench, which measures a large editor model's ability to modify the weights of a smaller target model (typically Gemma 3 4B IT) to achieve one of ten classical text-editing objectives while preserving its other capabilities. Editors are limited to four tools for reading and writing weights, with bounded tensor access and a fixed budget for generating and inspecting rollouts. A validator applies each proposed patch in a clean environment and compares the edited model against the unmodified target. Evaluating frontier closed- and open-weight models reveals sharply diverging capabilities, both across models and across tasks. A small number of models, most notably Astra and GPT-6.1 Sol, perform far ahead of the rest. The recency of this ability (little of it is evident in GPT-5.6 Sol, for instance), together with qualitative analysis, suggests it has been acquired through recent training. Tasks also vary widely: structured response resisted every attempt, and answer-length control yielded only one successful solution, whereas alias acquisition and recoding proved most amenable. Success in one task family correlated poorly with success in others, indicating an early and uneven capability frontier. We discuss strategies that editors repeatedly adopted and conclude with an outlook on intra-weight injection as an emerging but already potent approach to gradient-free behaviour modification.

cs.AI

版本更新 · v2arXiv:2605.15018

Generalized Priority-Aware Shapley Value

Kiljae Lee, Ziqi Liu, Weijing Tang, Yuan Zhang

原文摘要

Shapley value and its priority-aware extensions are widely used for valuation in machine learning, but existing methods require pairwise priority to be binary and acyclic, a restriction spectacularly violated in real-data examples such as aggregated human preferences and multi-criterion comparisons. We introduce the generalized priority-aware Shapley value (GPASV), a random order value defined on arbitrary directed weighted priority graphs, in which pairwise edges penalize rather than forbid order violations. GPASV covers a range of classical models as boundary cases. We establish GPASV through an axiomatic characterization, develop the associated computational methods, and introduce a priority sweeping diagnostic extending PASV's. We apply GPASV to LLM ensemble valuation on the cyclic Chatbot Arena preference graph, illustrating that priority-aware valuation is not a one-button operation: different balances of pairwise graph priority versus individual soft priority produce substantively different valuations of the same data.

cs.LG · cs.AI

新论文 · v1arXiv:2611.08645

From Geometry to Function: A Multi-Task LiDAR Benchmark Dataset for Semantic and Functional Parsing of Urban Facades

Abdiaziz Muse, Tooba Javed, Tao Pu, Jiju Poovvancheri, Dong Chen

原文摘要

Understanding building facades is central to urban digital twins, heritage modelling, and sustainable city analysis, yet existing LiDAR benchmarks stop at geometry and semantic segmentation and offer little support for reasoning about the functional role of each architectural element. We introduce HFX3D, a large-scale urban facade benchmark of approximately 492 million LiDAR points from 26 buildings in Halifax, Canada, captured across four seasons, day and night, and varied weather. Each facade is annotated at three tiers, semantic, instance, and per-instance functional attributes, making it, to our knowledge, the first facade dataset to pair geometry and semantics with functional labels. Annotations are produced by a semi-automatic pipeline that combines geometry-guided heuristics with expert validation. We benchmark representative point-based, graph-based, convolutional, and transformer architectures and find that semantic segmentation is already challenging under severe class imbalance, while instance separation of repetitive structures and functional reasoning from geometry are substantially harder. The benchmark establishes a new foundation for function-aware 3D urban understanding. Project page: https://jijup.github.io/hfx3d-benchmark/ ; code: https://github.com/jijup/hfx3d-benchmark

cs.CV · cs.AI · cs.GR · cs.LG

新论文 · v1arXiv:2611.08644

Decision Context: Persistent Behavioral Learning for AI Agents

Nima Vahdat, Pashootan Vaezipoor

原文摘要

LLM agents do not learn from corrections across sessions. A user fixes the same mistake at the start of every conversation. Existing agent memory systems primarily handle facts, such as preferences, entities, and conversational history, rather than procedural knowledge. We present Forge Decision Context (forge_dc), a system that captures behavioral signals from human corrections and self-assessed tool-call failures, compiles them into imperative RULE directives, and injects them at the decision points where they apply. We evaluate forge_dc alongside four predecessor approaches on DC-Bench, a new benchmark of 71 scenarios across nine behavioral dimensions, built from real executed agent traces in a deterministic mocked-tool environment. forge_dc reaches 95% compliance, up from 55% with naive retrieval, while injecting approximately 10 times fewer tokens per query. Across the five-stage progression, the strongest systems represent behavioral memory as explicit directives and deliver it at the decision points where it applies. The results identify representation, activation, and placement as central design choices for persistent behavioral learning.

cs.AI

新论文 · v1arXiv:2611.08643

FinEvolveKG: Controlled and Attributable Prompt Evolution for Financial Knowledge Graph Construction

Abhinav Arun, Jayita Bhattacharyya, Fabrizio Dimino, Bhaskarjit Sarmah, Stefano Pasquali

原文摘要

Financial institutions construct knowledge graphs (KGs) from shared SEC 10-Ks to serve risk analysis, portfolio management, and investment research, whose analytical needs differ. Extraction must adapt without fragmenting shared grounding, typing, and temporal rules. Hand-authored persona prompts and fine-tuning add cost. Weight-free prompt optimization offers an alternative, but unconstrained evolution of a monolithic prompt can rewrite shared rules alongside persona guidance, obscuring changes and complicating review. We introduce FinEvolveKG, a KG-construction harness separating reusable general and persona-policy blocks and mechanically confining GEPA, a reflective prompt optimizer, to the designated block. During persona adaptation, the approved general block remains byte-stable and every optimizer edit is localized to a separately versioned persona policy. A dual objective balances generic temporal-KG quality with persona-relevant facts, motifs, and multi-hop connectivity. We evaluate five mutation scopes on ticker-disjoint 10-K splits, with three seeds for the persona-conditioned arms (v3-v5) across three personas. On the three-seed mean, the complete two-stage block-constrained workflow (v4) improves over the frozen prompt baseline (v1) by 19.4-30.9% and over the tested unconstrained full-prompt workflow (v5) by 2.2-6.4%, leading v5 on both objective components and winning all nine paired-seed comparisons with the lowest seed variance in every persona. Without further optimization, v4 also exceeds v5 across all evaluated out-of-distribution (OOD) shifts. An SME audit supports using the generated triplets as ground truth; a blinded two-SME audit favors v4 over v5 in 70.1% of contrast-enriched judgments. These results show that mechanically attributable evolution can coexist with strong empirical performance, without attributing the gains causally to the boundary.

cs.CL · cs.AI

版本更新 · v2arXiv:2611.04473

Treating the Symptom, Missing the Cause: Anatomy of a Scientific Reasoning Failure

Anna Gogleva, Thomas Charman, Martin Balla, Karl Gemayel

原文摘要

Scientific agents can find interventions that work without understanding why they do. We study this failure mode in controlled synthetic regulatory systems, where agents must experimentally identify a hidden fault and rescue the resulting phenotype. Across seven LLMs, every model restores the healthy phenotypes more often than it identifies the fault. Claude Opus 4.6 and Sonnet 4.6 rescue every organism while diagnosing only 55% and 35% of them. This failure is not simply due to insufficient exploration or unavailable evidence. In most cases, the cause is experimentally identifiable, and agents encounter evidence that distinguishes competing causes in 91% of relevant sessions, and still frequently misdiagnose the system. Targeted probes reveal where experimental reasoning breaks down. Models reliably interpret decisive evidence and revise hypotheses when the causal comparison is explicit, and can locate that evidence within a full experimental record. However, they struggle to predict the outcome of the experiment under each competing cause, a necessary step in using the observed result to distinguish between them. Agents can therefore gather the right evidence and still infer the wrong cause. As AI systems take on a growing role in synthesising scientific evidence, these findings highlight the need to evaluate how they use evidence to reach causal conclusions, alongside whether their interventions succeed.

cs.AI

版本更新 · v4arXiv:2604.27266

AutoREC: A reinforcement learning platform for equivalent circuit model generation

Ali Jaberi, Yonatan Kurniawan, Robert Black, Shayan Mousavi M., Kabir Verma, Zoya Sadighi, Santiago Miret, Jason Hattrick-Simpers

原文摘要

This paper introduces AutoREC, an open-source Python platform for developing, training and evaluating reinforcement learning (RL) agents that automatically generate equivalent circuit models (ECMs) from electrochemical impedance spectroscopy (EIS) data. Although ECMs are widely used to interpret EIS measurements, their identification typically relies on manual trial-and-error, requiring domain expertise and limiting scalability, particularly in autonomous experimental pipelines such as self-driving laboratories. In AutoREC, ECM generation is formulated as a Markov decision process in which an RL agent sequentially modifies a circuit topology based on the current state, available actions and feedback from the resulting model. The platform supports an end-to-end workflow encompassing EIS preprocessing with selectable impedance representations, agent setup and training, ECM generation for new measurements and visualization-based evaluation and analysis of agent decision-making. AutoREC implements a configurable Double Deep Q-Network agent with prioritized experience replay and a dedicated deadloop mitigation strategy for navigating the complex circuit-generation action space efficiently. To demonstrate the platform, we trained a representative agent on 1350 synthetic spectra from five reference circuit families, evaluated it on 150 held-out synthetic spectra and applied it to 32 previously unseen experimental spectra from battery, corrosion, oxygen evolution reaction and CO2 reduction systems. These case studies illustrate the end-to-end capabilities of AutoREC while revealing challenges associated with experimental complexity and limited training-data coverage. The demonstrated agent serves as a reference implementation; AutoREC provides an extensible foundation through which users can develop and evaluate agents tailored to their specific electrochemical systems and research objectives.

cs.LG · cond-mat.mtrl-sci

版本更新 · v2arXiv:2611.03100

LUCA: A Synthetic World for Experimental Reasoning

Anna Gogleva, Thomas Charman, Martin Balla, Karl Gemayel

原文摘要

An experimental agent can succeed for the wrong reasons. Evaluations, however, often focus on the outcome, not the experiments, evidence, and inferences that produced it. We introduce LUCA, a configurable synthetic world for evaluating this process under fully known ground truth. Agents learn unknown regulatory systems through budgeted experimentation, then predict unseen interventions, diagnose hidden faults, and attempt rescues. This setup allows us to evaluate experiment selection, prediction, diagnosis, and intervention separately. Across seven frontier LLMs and three baselines, these capabilities dissociate sharply. Agents frequently rescue malfunctioning systems while diagnosing the wrong fault; diagnosis varies 7x across models while prediction varies only 1.4x. Models also adopt surprisingly different experimental strategies, and greater exploration does not reliably yield better performance. In one failure mode, agents often perform the experiment needed to distinguish competing causes, but still fail to use the resulting evidence. LUCA turns these hidden failures into measurable behaviours, providing a controlled environment to study where experimental agents succeed and fail. Code: https://github.com/RelationRx/luca.

cs.AI

新论文 · v1arXiv:2611.08640

Aspect-wise Pairwise Tournaments for Test-Time Selection

Hannah Guan, Yilun Du

原文摘要

Scaling test-time compute has proven highly effective at improving LLM reasoning. A popular method is best-of-n sampling, where a model generates many candidate solutions and one is selected. This motivates the question: how can we select the best candidate? When humans make choices, we find it more natural to compare two options than judge each in isolation. Additionally, when the options become complex, we like to judge the options one aspect at a time, such as comparing two job candidates on experience, communication, etc. In the test-time setting, candidate solutions should be judged in the same way. Here we introduce Aspect-wise Pairwise Tournaments (APT), which verifies by comparison and compares by aspect. Each matchup of a single elimination tournament is decided by a vote over multiple off-the-shelf aspect verifiers, each expressing a pairwise preference along its own aspect. Across five domains and three generator LLMs, APT improves over binary multi-aspect approval, self-consistency and reward model verification, with the largest gains on open-ended tasks. We find that both components matter; neither binary approval over the same aspects nor a generic pairwise judge at a matched budget matches APT. Because aspects are specified in natural language, APT also lets users steer selection toward properties they care about, better aligning with user preferences without needing to regenerate solutions. No component is trained, so APT transfers to new domains by simply rewriting prompts.

cs.AI

新论文 · v1arXiv:2611.08639

Forcing a Letter Suppresses Refusal: Mechanistic Evidence from WMDP

Stepan Epifantsev, Anna Antipova, Oleg Chernikov, Leon Strelkov, Alexey Dontsov

原文摘要

Safety benchmarks for large language models (LLMs) commonly use multiple-choice question (MCQ) format. However, prior studies documented that MCQ format reduces refusal rates, which may significantly affect the safety behavior of the model. We provide a first mechanistic explanation of this effect on the Weapons of Mass Destruction Proxy (WMDP) dataset across two models - Llama-3.1-8B and Qwen3-8B. First, we use the tuned lens technique to show that when processing MCQ the model commits to an answer-letter token very quickly, which is in contrast to the gradual refusal build-up in open-ended formats. Additionally, we observe that activations on the MCQ format lie roughly 3x further from the refusal direction, compared with their open-ended counterparts. Moreover, ablating the attention heads that carry the MCQ format answer increases the refusal, which is a direct evidence that the MCQ answer-selection competes with refusal. These findings indicate that MCQ safety scores primarily measure knowledge capabilities and do not assess the safety-mechanisms.

cs.CL · cs.LG

新论文 · v1arXiv:2611.08638

MORTIS: Compiler-Guided KV-Cache Management for LLM Agent Programs

Xiaoyu Ma, Jayanaka L. Dantanarayana, Savini Kashmira, Baichuan Li, Lingjia Tang, Jason Mars

原文摘要

Existing agent serving systems divide each prompt into a reusable prefix and an opaque suffix, managing the KV-cache at this coarse granularity without distinguishing the components within each part. We observe that prompt components differ in which LLM calls share their values and how long those values remain reusable, a property we term intra-prompt heterogeneity. Our key insight is that, in frameworks that generate prompts from typed LLM function calls, these components correspond to program variables, allowing compiler analysis to recover their sharing patterns and lifetimes. We present MORTIS, a compiler-serving co-design that combines this analysis with runtime observations to improve KV-cache management. MORTIS reorders prompt components to expose additional prefix reuse and uses their predicted reuse and lifetimes to guide cache retention, eviction, and prefetching. Our evaluation shows that MORTIS achieves up to 1.99x job completion time (JCT) speedup and 1.97x throughput improvement over SGLang, with geometric-mean speedups of 1.45x and 1.49x, respectively.

cs.OS

新论文 · v1arXiv:2611.08637

Branch-Extended Automatic Differentiation

Jan Hückelheim, Jeffrey Larson, Matt Menickelly

原文摘要

We present branch-extended automatic differentiation (BEAD), a software package that provides information about inactive branches of piecewise-differentiable functions, intended for use in nonsmooth optimization algorithms. BEAD is implemented in Python, building on the popular JAX framework. For supported nonsmooth operations such as abs and max, BEAD identifies alternative branches within tolerance from the given input, and computes gradients of the resulting branches extended to the given input. Such information has been previously used for robust optimization methods, but has required error-prone and tedious manual differentiation, unlike BEAD, which is fully automated for functions written in NumPy-like JAX code. Our experiments show that our approach is as accurate as manually written derivative code, and offers more flexibility in modifying the function and choosing between branch-discovery rules. While we were originally motivated by the manifold sampling algorithm for nonsmooth composite objectives, we also integrate BEAD branch-extension gradients into a nonsmooth BFGS-SQP solver. On two small nonsmooth test problems, the resulting path-aware search resolves failures or substantially reduces the number of evaluations required by the BFGS-SQP solver.

math.OC · cs.MS