跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1030新增论文
+790其中 AI 相关
+128已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-12 03:52 · 全站最近入库：2026-11-11 22:47各信源进度 →

统计口径与数据新鲜度

统计 2026-11-11 04:16 — 2026-11-12 04:16（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：2026-11-12 03:52最近发现新增版本：2026-11-11 22:47库内论文最新更新时间：2026-11-11 08:00

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

21,673 已收录论文18,321 AI 相关6,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 5,266 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-12 03:50（北京时间）
新论文 · v1arXiv:2611.12622

Reconfiguring System-Level Protection Through Bounded Delegation in RISC-V MCUs

Luís Cunha, José Martins, Manuel Rodríguez, Tiago Gomes, Uwe Moslehner, Kai Dieffenbach, Georg Schmalz, Kajetan Nuernberger 等 10 位作者

原文摘要

MCU-based embedded and cyber-physical systems increasingly require protection policies to change at runtime as resources, software, and system composition evolve. Yet widely used COTS MCU protection mechanisms are still largely designed around statically established policies. While they can restrict which domains modify protection primitives, they generally do not constrain what policy an authorized domain may create. As a result, domains may expand protection rules beyond their intended scope or interfere with boundaries established by other domains. We identify bounded configuration authority as a missing primitive for secure dynamic policy evolution and introduce an ownership-aware model in which explicit ownership and rule containment bound both configuration authority and recursive delegation. Changes to active protection-rule ranges are validated before commit, preserving protection boundaries without extending the normal access-checking datapath. We implement the model in an open-source RISC-V World Checker integrated into a CVA6-based SoC. Our FPGA evaluation shows no degradation in access latency or operating frequency, with 7.1% LUT and 1.2% FF overhead for eight rules. In an OTA update case study, direct reconfiguration under delegated authority reduces policy-transition latency by 89.5% over hypervisor mediation and 94.6% over trusted firmware mediation, while preserving established authority boundaries. All artifacts will be open-sourced to support the evolution of RISC-V specifications and system-level protection designs.

cs.CR · cs.AR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2204.00920

Deep Algebraic Fitting for Multiple Circle Primitives Extraction from Raw Point Clouds

Zeyong Wei, Honghua Chen, Hao Tang, Qian Xie, Mingqiang Wei, Jun Wang

原文摘要

The shape of circle is one of fundamental geometric primitives of man-made engineering objects. Thus, extraction of circles from scanned point clouds is a quite important task in 3D geometry data processing. However, existing circle extraction methods either are sensitive to the quality of raw point clouds when classifying circle-boundary points, or require well-designed fitting functions when regressing circle parameters. To relieve the challenges, we propose an end-to-end Point Cloud Circle Algebraic Fitting Network (Circle-Net) based on a synergy of deep circle-boundary point feature learning and weighted algebraic fitting. First, we design a circle-boundary learning module, which considers local and global neighboring contexts of each point, to detect all potential circle-boundary points. Second, we develop a deep feature based circle parameter learning module for weighted algebraic fitting, without designing any weight metric, to avoid the influence of outliers during fitting. Unlike most of the cutting-edge circle extraction wisdoms, the proposed classification-and-fitting modules are originally co-trained with a comprehensive loss to enhance the quality of extracted circles.Comparisons on the established dataset and real-scanned point clouds exhibit clear improvements of Circle-Net over SOTAs in terms of both noise-robustness and extraction accuracy. We will release our code, model, and data for both training and evaluation on GitHub upon publication.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.08446

AssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly

Zhiyuan Qi, Jierui Li, Yifan Shen, Cheng Qian, Jiateng Liu

原文摘要

Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physical environment remains difficult. Furniture assembly requires not only recovering step-level operations from diagrammatic manuals, but also translating semantic attachment relations into 6D pose updates that enable parts to physically interact with the environment and previously assembled components. To study this problem, we propose AssemState, a zero-shot framework for manual and physical-state-guided furniture assembly. It firstly employs anchor-guided boundary assembly states to decompose manual pages into single-part operations and recover an assembly-tree. Then, it uses iterative after-state feedback refinement to guide successive (SE(3)) updates and corrections, and validates their physical plausibility through simulation-based release tests. Experiments show that compared with the strongest prior baseline, AssemState improves F1 from 38.58\% to 62.80\% and Tree Exact Match from 28.24\% to 53.92\% for assembly-tree recovery. On 243 independently evaluated part-level operations, our proposed iterative refinement improves judge-accepted operations from 0 to 5.3\% and reduces mean Chamfer distance from 5.4111 to 1.7744. However, visually plausible candidate poses may still suffer from collision, floating, mirror-orientation errors, incomplete seating, and wrong-side attachment. These results show that AssemState improves operation-structure recovery and selected local pose metrics, while MLLMs remain limited for spatial relationship reasoning.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12600

Reducing Provers in Distributed Quantum Verification

Alex Della Schiava, Atsuya Hasegawa, François Le Gall, Harumichi Nishimura

原文摘要

In the distributed quantum Merlin-Arthur ($\mathsf{dQMA}$) model introduced by Fraigniaud, Le Gall, Nishimura, and Paz (ITCS 2021), a network of quantum computers verifies a global property with the aid of a quantum proof supplied by an untrusted prover. While the nodes are computationally unbounded, the challenge is to limit proof size and the communication required for verification. In this paper, we consider the model of Hasegawa, Kundu, and Nishimura (PODC 2024), where the proof must be unentangled across nodes, and define its extension to $k$ unentangled provers, denoted by $\mathsf{dQMAS}(k)$. In this setting, we investigate the proof size per node and the communication costs of reducing the number of provers. Our first result reduces the number of provers from $k$ to two, doubling the proof size without additional communication. Moreover, with four additional rounds, we can reduce the number of provers from $k$ to one, using at most three times the original local proof size plus a logarithmic term in the number of nodes. Finally, we establish amplification for perfectly complete protocols. In this regime, a single prover suffices with a constant-factor overhead in our reductions, yielding $\mathsf{dQMAS} = \mathsf{dQMAS}(k)$.

quant-ph · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.20068

Marginal utility, matrix factorization, and the Key-Value (KV) cache: a unified information-economic framework for sovereign geo-mining inference

Caroline Gans Combe

原文摘要

This paper builds a theoretical bridge between the economic notion of marginal utility and two machine-learning constructs, matrix factorization and the Key--Value cache of transformer language models. The singular value spectrum of a rating matrix is shown to be a diminishing marginal utility schedule for latent factors, the eigenvalue spectrum of the projected covariance operator to be the marginal utility schedule of a model's learned representation, and cache eviction and low-rank cache compression to be instances of constrained utility maximization under a memory budget. The three collapse into a single allocation rule: retain the top dimensions whose eigenvalue exceeds the shadow price of the binding constraint. The framework is applied to the automated extraction of structured information from geo-mining documents, where it motivates a multi-pass inference protocol, a layer-wise TIES model merging procedure, and a selection policy combining extraction quality, localization drift and energy, scalarized with a Conditional Value-at-Risk term on drift. Two empirical contributions are reported. An 11.2-million-parameter hierarchical classifier, trained in about five minutes on a single GPU, reaches 90.0 per cent level-1 accuracy on a held-out test set from a 973-document uranium-exploration corpus, against 92.0 per cent for a proprietary model on a fifty-document human audit of the same corpus, at a latency of 2.62 ms per card against approximately 2,000 ms for the API and at negligible cost. A diagnostic of uniform-density TIES merging exposes a reproducible degenerate mode in which the merged model returns token-identical outputs across five geographically distinct districts while declaring high confidence; re-executing the merge under layer-wise calibrated densities removes that signature on the diagnostic sample. The full-scale extraction benchmark, including LoRA fine-tuning, is reported as projected rather than measured and remains an empirical extension of this work.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12597

Unmasking Four Knapsack Problems in the Traveling Thief Benchmark

Mohammed Mizan Alanazi, Mahdi Khemakhem

原文摘要

The traveling thief problem (TTP) asks a thief to choose a tour and a packing together, and the benchmark of 9,720 instances of Polyakovskiy et al. (2014) is the standard test set for comparing TTP heuristics. We show that four of these instances are not TTP instances at all. Their files give a renting rate of 0.00, so the tour has no effect on the objective and each instance reduces to a 0-1 knapsack problem. One of them belongs to the 60 categorized instances on which new methods are usually compared, and on it five of nine published methods report exactly the same value. The cause is the format of the files, which keep the renting rate with two decimals, while the rule of the generator gives a rate close to 0.003 on these instances. The same rounding may shift the rate of 949 other instances by more than 1%. Since the tour and the packing used by the generator were not published, the original rates cannot be recovered. We therefore define new rates with the same rule, applied to a fully specified reference solution that we publish, and we show with a published heuristic that the corrected instances behave as TTP instances again. We also give reference results on the corrected instances and recommendations for future studies. Finally, we present ttplib, a new open-source Python library that loads any of the 9,720 instances, including the corrected ones, without downloading the whole benchmark.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.07900

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents

Zhi Chen, Zhensu Sun, Yuling Shi, Chao Peng, Xiaodong Gu, David Lo, Lingxiao Jiang

原文摘要

Large Language Model (LLM) code agents increasingly resolve repository-level issues by iteratively editing code, invoking tools, and validating candidate patches. In these workflows, agents often write tests on the fly, but the value of this behavior remains unclear. This raises a central question: how does agent-written testing relate to task outcomes and resource use during repository-level issue resolution? To better understand the role of agent-written tests, we analyze 5,000 recorded agent runs produced by six strong LLMs on SWE-bench Verified using the lightweight mini-SWE-agent scaffold. Our results show that test writing is common for most models. GPT-5.2 is an exception: it rarely writes new test files while achieving a resolution rate close to the top-ranked model. Test-writing frequency varies widely across models. Within a given model, it differs less between resolved and unresolved tasks. When tests are written, their files contain substantially more statements that print runtime values than assertions that check conditions. We then compare baseline prompts with revised prompts that encourage or discourage writing new test files for four models. Agents start or stop writing test files as requested on 36.8%-93.2% of tasks. Resolved-task totals differ by 0-13 out of 500 per model, with no statistically significant difference, while API calls or token use differ substantially for three models. Similar resolution totals can therefore hide substantial differences in how agents test and how many resources they use.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2507.17988

Synthesis of timeline-based planning strategies avoiding determinization

Dario Della Monica, Angelo Montanari, Pietro Sala

原文摘要

Qualitative timeline-based planning models domains as sets of independent, but interacting, components whose behaviors over time, the timelines, are governed by sets of qualitative temporal constraints (ordering relations), called synchronization rules. Its plan-existence problem has been shown to be PSPACE-complete; in particular, PSPACE-membership has been proved via reduction to the nonemptiness problem for nondeterministic finite automata. However, nondeterministic automata cannot be directly used to synthesize planning strategies as a costly determinization step is needed. In this paper, we identify a fragment of qualitative timeline-based planning whose plan-existence problem can be directly mapped into the nonemptiness problem of deterministic finite automata, which can then synthesize strategies. In addition, we identify a maximal subset of Allen's relations that fits into such a deterministic fragment.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12572

Text2NGAC: a multi-LLM pipeline for NGAC policy extraction with mutation-based verification

Ayesha Habib, Huixiang Zhang, Dan Zhu, Waiz Haider

原文摘要

Access-control policies are written in natural language but enforced as formal models, and translating them into NIST Next Generation Access Control (NGAC) graphs remains unsolved: prior systems cover only subsets of the NGAC model, and none verify the graphs they extract. We present Text2NGAC, a pipeline of cooperating large language models that disambiguates each sentence before extraction, escalates uncertain sentences to a multi-model ensemble, and checks the resulting graph with a five-strategy verifier whose own effectiveness is measured by controlled mutation testing. To our knowledge it is the first system to extract all four NGAC relationship types - associations, prohibitions, event-response obligations, and assignments - from real-world policy documents. Three results anchor the evaluation. The verifier detects 99.7% of 918 injected mutants and every structural fail-open fault, and the fault classes it misses are characterized and weighted by security consequence rather than left unexamined. The extracted graphs are enforceable: one corpus's graph loads unmodified into the NIST reference implementation, which reproduces all 55 access decisions the graph entails and fires an extracted obligation end-to-end. Extraction reaches 97.3-99.6% exact-tuple-match accuracy on the 714 scored sentences of four real corpora, far above three reproduced baselines on matched metrics, and paraphrase probes with semantic re-scoring bound the pipeline's sensitivity to rewording. Reported accuracy is wording- and benchmark-specific, adversarial input is outside the verifier's guarantees, and the intended deployment is extraction plus structural verification feeding expert review. A complete two-tier reproducibility artifact accompanies the paper.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12564

GHiML: VLM-Guided Hierarchical Multi-Label Learning with Applications to Benthic Imagery

Isaac Xu, Devi Ayyagari, Martin Gillis, Benjamin Misiuk, Craig J. Brown, Thomas Trappenberg

原文摘要

Vision language models (VLMs) encode substantial expert knowledge within their weights, yet their direct application to specialised classification domains such as benthic imagery remains limited. Meanwhile, vision transformers trained on these tasks rely predominantly on low-level visual latents (colours, textures, and shapes) that lack the higher-level reasoning humans employ for identification. We propose Guided Hierarchical Multi-Label (GHiML) learning, a pipeline that extracts conceptual latent variables from a VLM conditioned on training data, generates sample-relevant captions grounded in those variables, and fuses the resulting textual embeddings with image embeddings via cross-attention and a per-node gated router. We also introduce the inverted HML score ($d_{\mathrm{inv}}$), a similarity score that evaluates hierarchical multi-label predictions through graph traversal distance and a cardinality penalty, providing an interpretable alternative to existing measures, which are insensitive to realistic degradations in sparse, deep hierarchies. Experiments on BenthicNet, FathomNet and iNaturalist show that the router improves macro $F_1$ over the vision-only baseline by up to 6.7 pp and $d_{\mathrm{inv}}$ by up to 21.1 pp on in-domain benthic data, with gains persisting under distribution shift. Ablations locate the contribution of the text itself: on the multi-label biotic hierarchies, removing the per-sample text signal degrades $d_{\mathrm{inv}}$ while leaving macro $F_1$ unchanged, consistent with text acting through prediction cardinality rather than node discrimination, whereas iNaturalist, whose annotations are single-label, loses 18.7% of macro $F_1$. Our results support the hypothesis that VLMs contain exploitable specialised knowledge that, when appropriately elicited, can augment classification in domains where direct visual learning is insufficient.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2508.13288

Hierarchical Conformal Classification

Floris den Hengst, Inès Blin, Majid Mohammadi, Syed Ihtesham Hussain Shah, Taraneh Younesian

原文摘要

Conformal prediction (CP) is a powerful framework for quantifying uncertainty in machine learning models, offering reliable predictions with finite-sample coverage guarantees. When applied to classification, CP produces a prediction set of possible labels that is guaranteed to contain the true label with high probability, regardless of the underlying classifier. However, standard CP treats classes as flat and unstructured, ignoring domain knowledge such as semantic relationships or hierarchical structure among class labels. This paper presents hierarchical conformal classification (HCC), an extension of CP that incorporates class hierarchies into both the structure and semantics of prediction sets. We formulate HCC as a constrained optimization problem whose solutions yield prediction sets composed of nodes at different levels of the hierarchy, while maintaining coverage guarantees. To address the combinatorial nature of the problem, we formally show that a much smaller, well-structured subset of candidate solutions suffices to ensure coverage while upholding optimality. An empirical evaluation on three new benchmarks consisting of audio, image, and text data highlights the advantages of our approach, and a user study shows that annotators significantly prefer hierarchical over flat prediction sets.

cs.LG · cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.22787

Conformal PM2.5 Mapping Under Spatial Covariate Shift: Satellite-Reanalysis Fusion for Africa's Green Industrial Transition

Yaw Osei Adjei, Davis Opoku, Ephraim Abotsi, Kwadwo Owusu Amanqua, Oliver Kornyo, Elisha Soglo-Ahianyo, Cephas Anertey Abbey, Ransford Oppong

原文摘要

Africa's green industrialization imperative demands reliable infrastructure for monitoring air quality. We present a satellite-reanalysis PM2.5 fusion system trained on 2,068,901 records from 404 monitoring locations in 29 African countries (OpenAQ, 2017-2022), combining LightGBM with leakage-resistant spatial cross-validation and conformal prediction to quantify predictions and their geographic applicability limits. Under 5-fold location-grouped spatial cross-validation, LightGBM achieves RMSE = 30.83 +/- 5.07 ug/m3, MAE = 14.54 +/- 1.66 ug/m3, R2 = 0.134 +/- 0.023, and macro F1 = 0.336 +/- 0.018. This R2 is substantially below random-split benchmarks (>0.90) but reflects true geographic generalisation difficulty rather than model failure. Split conformal prediction targeting 90% marginal coverage reveals severe East Africa degradation (actual PICP = 65.3% vs. nominal 90%), consistent with medium-strength covariate shift (humidity KS = 0.2237, sat_pblh KS = 0.2558). We operationalise these findings through regional reliability flags (High/Medium/Low/Unreliable) and a monitor prioritisation score directing infrastructure expansion toward highest-burden unmonitored populations, directly supporting Africa's green industrial transition and SDGs 3.9, 7.1.2, 9, 11.6.2, and 13.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.27149

Temporally Ordered Region-Token Mamba with Logit-Space Diffusion for Remote Sensing Change Detection

Maneet Chatterjee, Aparup Ghosh, Anuvab Sen, Udayon Sen, Arnav Aditya, Yixin Zhang

原文摘要

Change Detection (CD) in remote sensing requires jointly modeling bitemporal context and fine-grained spatial details to accurately localize changed regions. While dense attention effectively captures bitemporal relationships, its computational cost limits scalability to high-resolution imagery. In contrast, conventional feature fusion and coarse decoding often struggle to distinguish true changes from appearance variations and preserve object boundaries. To overcome these limitations, we propose Bitemporal Mamba-Diffusion for Change Detection (BMD-CD), a framework that integrates temporally structured state-space modeling with logit-space diffusion refinement. BMD-CD first converts deep bitemporal features into region tokens and organizes them into explicit temporal partitions for bidirectional state-space propagation. It then employs a Learnable Trigonometric Fusion (LTF) module to integrate temporal information and a Conditional Diffusion Decoder that refines coarse predictions in logit space with a short DDIM schedule to generate fine-grained, high-resolution change maps. Extensive experiments on LEVIR-CD, WHU-CD, DSIFN-CD, CDD, and S2Looking demonstrate the effectiveness of the proposed approach. BMD-CD achieves IoU scores of 0.923, 0.957, 0.882, and 0.979 on WHU-CD, DSIFN-CD, LEVIR-CD, and CDD, respectively, and further exhibits strong zero-shot robustness on ValaisCD and B-FLAIR-test.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.23676

Web World Models

Jichen Feng, Yifan Zhang, Chenggong Zhang, Yifu Lu, Shilong Liu, Mengdi Wang

原文摘要

Language agents increasingly require persistent worlds in which they can act, remember, and learn. Existing approaches sit at two extremes: conventional web frameworks provide reliable but fixed contexts backed by databases, while fully generative world models aim for unlimited environments, but the world is constructed primarily through generation, making it harder to maintain a fixed, deterministic global framework and reducing controllability. In this work, we introduce the Web World Model (WWM), a middle ground where world state and ``physics'' are implemented in ordinary web code to ensure logical consistency, while large language models generate context, narratives, and high-level decisions on top of this structured latent state. We build a suite of WWMs on a realistic web stack, including an infinite travel atlas grounded in real geography, fictional galaxy explorers, web-scale encyclopedic and narrative worlds, and simulation- and game-like environments. Across these systems, we identify practical design principles for WWMs: separating code-defined rules from model-driven imagination, representing latent state as typed web interfaces, and utilizing deterministic generation to achieve unlimited but structured exploration. Our results suggest that web stacks themselves can serve as a scalable substrate for world models, enabling controllable yet open-ended environments.

cs.AI · cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12544

Learning inexact alternating minimization for convex problems with quadratic coupling

Paul Häusner, Jevgenija Rudzusika, Jens Sjölund, Ozan Öktem

原文摘要

Alternating minimization is a standard tool for optimization problems with two coupled variable blocks. Its cost is dominated by the inner subproblem solvers, which rarely have a closed-form solution. In this paper, we propose to learn an inexact alternating scheme in which neural networks approximate the subproblem solution at each iteration. For convex problems with quadratic couplings between the variable blocks that satisfy a quadratic growth condition, we derive a worst-case bound on the optimality gap that exposes the per-iteration error that each network is trained to minimize in a greedy fashion. Combining the bound with a PAC-Bayes argument, we obtain a fixed-horizon, high-probability bound on the expected optimality gap over the distribution of problem instances. We apply the learned scheme to robust matrix completion and low-dose CT reconstruction with dictionary regularization where we achieve a 5x-13x speedup over the inexact first-order baseline at matched accuracy. A brief end-to-end fine-tuning stage extends this up to 30x and outperforms other learned schemes. The code is available at https://github.com/paulhausner/learned-alternating-minimization.

math.OC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12526

Galilean Robots, Aristotelian Sensors: Joint Spatiotemporal Trajectory Estimation and Extrinsic Calibration

Abhishek Goudar, Jonathan Kelly, Timothy D. Barfoot

原文摘要

Multi-sensor state estimation requires accurate spatial and temporal calibration between heterogeneous sensors. Existing spatiotemporal calibration methods typically represent sensor extrinsic parameters as a rigid-body transformation together with a scalar temporal offset, causing the spatial and temporal parameters to enter the estimation problem through separate mechanisms. While the spatial transformation composes directly with the robot pose, accounting for the temporal offset requires evaluating the trajectory at a shifted time, typically through motion compensation, interpolation, or a continuous-time trajectory representation. In this work, we formulate joint trajectory estimation and spatiotemporal calibration using the special Galilean group for the robot trajectory and the Aristotelian subgroup for sensor extrinsics. This representation incorporates the coupling between motion and temporal offset directly through the group structure, avoiding the need for a separately parameterized continuous-time trajectory. We develop twist- and IMU-driven motion priors, accommodate both ideal and non-ideal clocks, and evaluate the framework with camera, position, and range measurements. Simulated and real experiments demonstrate calibration and trajectory-estimation performance comparable to established methods across heterogeneous sensor configurations. Our simplified framework therefore offers a quality-of-life improvement over existing methods without compromising performance.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12524

EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground Truth

Jens Parslov, Marco Schouten, Dim P. Papadopoulos

原文摘要

Vision-language models (VLMs) are increasingly used as automated judges for image-editing benchmarks, yet their reliability is poorly understood. Auditing these judges is difficult because real edited images lack controlled ground truth and entangle the requested changes with model artefacts, unintended side effects, and ambiguous degrees of success. In this paper, we introduce EditJudge-Bench, a diagnostic benchmark of 1,382 synthetic before/after image pairs rendered in Blender, with edits parameterised across nine categories derived from real user requests and exact ground truth from known 3D scene parameters. Because every edit is generated by a known intervention on a controlled scene, EditJudge-Bench evaluates VLM judges as binary verifiers of whether an instruction was correctly executed, isolating judge perception from editor quality. Across 25 judge configurations, we find substantial reliability gaps: (a) the widely adopted VIEScore template reaches only 69.0% AUROC with GPT-4o; (b) fine-tuned judges score 51.7-66.3%; spatial edits such as rotation and shape remain challenging; (c) prompt-formatting choices like image-text ordering shift performance by up to 14.1 points. Despite using only synthetic data, judge rankings on EditJudge-Bench correlate strongly with two real-image human-preference benchmarks ($ρ$=0.95 and $ρ$=0.71), indicating that controlled audits surface failure modes relevant to real evaluation.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12521

Can the Confidence and Decisions of System 1 Models Be Trusted? An Explainability and Perturbation Audit of Jev-Style Decision Models

Julien Delaunay

原文摘要

"System 1" decision models (pioneered by TypeSafe AI's Jev) replace autoregressive text generation with a single forward pass returning typed probability distributions over declared schemas (Choice, Score, Noul). While deployed for low-latency routing and automated triage, their statistical calibration and post-hoc explainability remain uncharacterized. We introduce an open, deterministic audit benchmark evaluating System 1 decision models across calibration under label-preserving perturbations, cross-question interference, and post-hoc attribution faithfulness. Evaluating five open-weight models (0.8B to 27B) alongside generative System 2 baselines -- both single-token logprob scoring and structured JSON/CoT decoding -- across NLI (e-SNLI), adversarial syntactic shortcuts (HANS), synthetic clinical triage (N=900), prompt injection defense (Tensor Trust, N=250), and an 86-case logic-gate trigger suite yields five findings: (1) provider confidence is an exact closed-form dispersion transform (1 - H(p)/ln K on sub-10B models; normalized margin on Clef-27B) rather than empirical accuracy; (2) bundling multiple questions in one request induces directional cross-question interference (11.7% to 22.4% binary flips on Tev1-0.8B, vs. 0.1% to 0.2% on Tev1-4B); (3) System 1 models with >= 4B parameters are faster and better calibrated under syntactic shifts (ECE_w = 0.030 to 0.087) than logprob (0.144) and JSON (0.378) baselines; (4) for prompt-injection defense (N=250), >= 4B models achieve 0.988 to 0.998 AUROC with up to 95.2% recall and 0.0% false alarms at 48 to 60 ms; and (5) single-pass inference makes 512-coalition XAI interactive (1.3 to 3.2 s/input), while KernelSHAP with a logit link (S1-SHAP) mitigates softmax saturation on disjunctive OR gates (89.3% to 100.0% gate recovery vs. 57.1% to 82.1% in prob space; p_adj = 0.004).

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.10009

Towards Multi-Source Domain Generalization for Sleep Staging with Noisy Labels

Kening Wang, Di Wen, Yufan Chen, Ruiping Liu, Junwei Zheng, Jiale Wei, Kailun Yang, Rainer Stiefelhagen 等 9 位作者

原文摘要

Automatic sleep staging is a multimodal learning problem involving heterogeneous physiological signals such as EEG and EOG, which often suffer from domain shifts across institutions, devices, and populations. In practice, these data are also affected by noisy annotations, yet label-noise-robust multi-source domain generalization remains underexplored. We present the first benchmark for Noisy Labels in Multi-Source Domain-Generalized Sleep Staging (NL-DGSS) and show that existing noisy-label learning methods degrade substantially when domain shifts and label noise coexist. To address this challenge, we propose FF-TRUST, a domain-invariant multimodal sleep staging framework with Joint Time-Frequency Early Learning Regularization (JTF-ELR). By jointly exploiting temporal and spectral consistency together with confidence-diversity regularization, FF-TRUST improves robustness under noisy supervision. Experiments on five public datasets demonstrate consistent state-of-the-art performance under diverse symmetric and asymmetric noise settings.

cs.LG · cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12509

UniHam: A Large-Scale SOC-Complete Dataset and Benchmark for Hamiltonian Learning in Materials

Yuewen Huang, Pin Chen, Yutong Lu

原文摘要

Accurate prediction of electronic Hamiltonians would enable broad property inference while avoiding the high computational cost of Density Functional Theory (DFT). However, progress toward general-purpose materials foundation models is limited by a data bottleneck: existing Hamiltonian datasets are typically small, lack structural diversity, and often omit essential relativistic physics such as spin--orbit coupling (SOC). We therefore construct UniHam, a large-scale Hamiltonian dataset and benchmark suite comprising 100,000+ DFT-computed complex-valued Hermitian Hamiltonians with full SOC, covering 72 elements and a wide range of crystal geometries and symmetries (spanning diverse lattice types and space-group families). Building on UniHam, we benchmark two representative state-of-the-art models under a standardized protocol and introduce complementary evaluation metrics that jointly assess three dimensions: (i) Hamiltonian reconstruction accuracy, (ii) out-of-distribution (OOD) generalization across composition/symmetry shifts, and (iii) the ability to support downstream property prediction from the predicted Hamiltonians. Experiments on UniHam demonstrate that the proposed benchmark and metrics effectively differentiate model capabilities, revealing intrinsic SOC- and element-dependent failure modes, large variations in compositional OOD robustness, and the necessity of spectral-level evaluation to assess whether Hamiltonian predictions reliably support downstream electronic-structure properties. Overall, UniHam provides a reproducible, SOC-complete benchmark that can sharpen model comparisons and accelerate the development of next-generation foundation models for quantum materials.

cs.LG · cond-mat.mtrl-sci

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.27644

ANCORA: Learning to Question via Manifold-Anchored Self-Play for Verifiable Reasoning

Chengcao Yang

原文摘要

We propose a paradigm shift toward open-ended curriculum self-play: rather than learning to answer on a fixed prompt set, a unified policy learns to question: generating verifiable problems, solving them, and turning verifier feedback into self-improvement. We introduce ANCORA, in which the policy alternates between a Proposer that synthesizes novel specifications and a Solver that produces verified solutions, anchored by three mechanisms: a two-level group-relative update coupling Proposer advantages across specifications with Solver advantages across solution attempts; iterative self-distilled SFT projecting the base model onto its valid-output manifold before RL; and a UCB-guided Curriculum DAG whose policy-induced problem set can provably expand under self-composition. Without these stabilizers, sparse verifier feedback drives Proposer collapse even under MLRL-aligned rewards; with them, ANCORA bootstraps a verifiable curriculum from curated seeds. Instantiated in Verus, ANCORA lifts Dafny2Verus pass@1 from a 26.6% SFT baseline to 81.5% in test-time training (TTT, 0-shot), outperforming PSV self-play (1-shot) by 15.8 points; in a transfer setting, training from Dafny2Verus seeds yields 36.2% and 17.2% pass@1 on MBPP and HumanEval.

cs.LG · cs.AI · cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12491

Out-of-the-Box Tabular Foundation Models for Bayesian Optimization in Materials Discovery

Klemens Flöge, Simon Bing, Leo Grinsztajn, Eliott Kalfon, Lennart Purucker, Noah Hollmann, Frank Hutter

原文摘要

Bayesian optimization is widely used in active learning loops for materials science. Gaussian processes serve as the de-facto surrogate model family, but require task-dependent kernel choices and can lack the modeling capacity for complex relationships. Tabular foundation models (TFMs) have recently emerged as the state-of-the-art for predictive tasks on structured data, without requiring bespoke kernels or hyperparameter tuning. We evaluate two TFMs, TabPFN and TabICL, as out-of-the-box surrogate models on two standard materials science benchmarks, comparing against a large field of baselines encompassing Gaussian processes, random forests, and CatBoost. Our findings indicate that TFMs are highly competitive surrogate models across the two benchmarks, without task-specific training for active learning or GP kernel selection. Our results motivate developing TFMs further as surrogates for active learning in materials discovery.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.22600

Transformers converge to invariant algorithmic cores

Joshua S. Schiffman

原文摘要

Training selects for behavior, not circuitry: many weight configurations can implement the same function. Studying any single trained neural network thus risks describing accidents of one training run rather than the computation itself. This work shifts focus from what transformers happen to do to what they must do by extracting algorithmic cores, compact subspaces that are necessary and sufficient for a task and that recur across independently trained models. Here, Algorithmic Core Extraction (ACE) is introduced to isolate these subspaces, causally validate them, and recover the algorithms they implement, from synthetic tasks to large pretrained models. Markov-chain transformers embed 3D cores in nearly orthogonal subspaces yet recover identical transition spectra. Modular-addition transformers form compact cyclic cores at grokking that later inflate under continued regularization, redundantly distributing the same computation across many functionally equivalent modes. This functional redundancy accelerates the transition from memorization to generalization, yielding an inverse scaling law for grokking time. In six language models spanning two orders of magnitude in scale (GPT-2 Small/Medium/Large, LLaMA-3.1, Gemma-2, and Qwen2.5), subject-verb agreement is governed by a single, steerable axis that aligns across architectures. Flipping this axis inverts grammatical number throughout open-ended generation. For indirect object identification, a multi-step task, the same six models route computation through compact multi-dimensional cores at two sites, linked by a linear operator that transfers across model families. Together these results suggest that beneath the apparent complexity of trained transformers lies a simpler, shared computational structure, and that targeting invariants rather than parameterizations may offer a more tractable path to mechanistic understanding and control.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2502.03503

Why Transformers Struggle with Distribution-Independent In-Context Learning

Omar Naim, Jerome Bolte, Nicholas Asher

原文摘要

With in-context learning (ICL), transformer models adapt to new tasks from illustrative examples at inference time without updating their parameters. A common interpretation is that transformers implement implicit learning algorithms in their forward pass. We test this interpretation and ICL capability under distribution shift in noiseless polynomial regression, where the context uniquely determines the target function. Models that are near-perfect in distribution exhibit sharp performance degradation under shifts in the input or target-function distribution. This behavior persists across polynomial degrees and multiple training interventions, and in higher-dimensional nonlinear regression. We identify two architectural mechanisms that explain this breakdown: output saturation at finite boundary values linked to final normalization, and attention concentration on a small subset of the context, which can limit context-dependent adaptation required for ICL. Controlled experiments, architectural ablations, targeted interventions, and theoretical analysis provide strong evidence for both mechanisms and their consequence: strong in-distribution ICL does not imply distribution-independent ICL, which calls for caution when using ICL instead of explicit retraining or adaptation under distribution shift.

stat.ML · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.08438

Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety

Fazl Barez, Tung-Yu Wu, Hunar Batra, Gabriele Dominici, Florent Draye, Yanai Elazar, Damiano Fornasiere, Antía García 等 27 位作者

原文摘要

Neural networks are likely to be among the most consequential artefacts in human history. As these systems become more capable and autonomous, their potential to cause societal harm also grows, making AI safety one of the defining challenges of our time. Yet we continue to build increasingly powerful systems without fully understanding how they work, how they will behave in unfamiliar situations, or how to reliably control them. Mechanistic interpretability offers a path towards understanding these systems by studying their internal representations and computations, with the aim of evaluating, predicting, and controlling behaviour. We survey mechanistic interpretability for AI safety in order to answer the question: Does understanding how models work actually make them safer? We place mechanistic interpretability in the broader context of interpretability research and compare its mechanistic evidence with behavioural evaluation. We introduce the foundations of mechanistic interpretability, including features, polysemanticity, transformer computation, and circuits, and survey methods for feature extraction and analysis, circuit discovery and causal verification, explaining intermediate representations in natural language, learning dynamics, and training-data attribution. Beyond surveying existing methods, we propose a unified framework for evaluating mechanistic interpretability claims and characterise six research orientations by their goals, assumptions, and trade-offs. Finally, we examine how mechanistic understanding can support AI safety, including knowledge editing, steering, and monitoring, and assess its limitations, failure modes, open problems, and relationship to behavioural safety measures. We also release a repository of code notebooks with worked examples that reproduce key findings from surveyed methods, allowing readers to build intuition through hands-on experimentation.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2511.21245

FIELDS: Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision

Chen Ling, Henglin Shi, Hedvig Kjellström

原文摘要

Monocular 3D face reconstruction estimates the parameters of a 3D morphable face model (3DMM) from a single image, providing an explicit geometric representation for facial expression analysis. Owing to the scarcity of paired 2D images and 3D facial meshes, most methods are trained in a self-supervised manner by rendering the predicted face and minimizing image-level reconstruction losses, such as photometric and landmark errors, against the input image. However, these losses enforce visual alignment but do not ensure that the predicted parameters preserve affective information. Recent methods add image-level emotion consistency loss, but it can be satisfied by exaggerating facial deformations. To address these issues, we propose FIELDS (Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision), which learns affect-informative expression representations in the FLAME parameter space. Specifically, FIELDS augments 2D self-supervised reconstruction with scan-derived expression anchoring and a parameter-space emotion loss. During training, scan-fitted targets directly constrain expression-related FLAME parameters to discourage exaggerated deformations, while a jointly trained emotion head uses discrete emotion and continuous valence--arousal annotations to make the predicted parameters informative for affect analysis. Experiments show that FIELDS improves affective utility from the predicted parameters in both within- and cross-dataset settings. Notably, it also achieves lower reconstruction errors overall and across most facial regions than the comparison baselines under both rigid and similarity alignment.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.19940

A Non-Dichotomy for CSPs of Stable $ω$-Categorical Structures

Manuel Bodirsky, David Bradley-Williams, Ehud Hrushovski, Christoph Spiess

原文摘要

We construct countable, stable, $ω$-categorical structures with at most two binary relations whose CSPs exhibit three complexity regimes: NP-complete, decidable but not in NP, and undecidable. The templates arise from a controlled Hrushovski construction of stable $ω$-categorical graphs $M_α$ for suitable irrational parameters $α>1$. Some of these graphs have NP-complete CSPs. Expanding the graphs $M_α$ by the non-edge relation turns age membership into a restriction of the CSP. For every time-constructible bound $t$, there is such an expansion whose CSP is decidable but not in DTIME$(t)$. For an explicit parameter $α$, the restriction to complete instances belongs to $\mathrm{coNP}$ and the full CSP belongs to $Σ_2^{\mathrm P}$. Separating the ages of the $M_α$ using graphs with large girth and prescribed density yields $2^{\aleph_0}$ distinct CSPs of these expansions, all but countably many of which are undecidable.

cs.LO · math.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.07417

Bayesian Optimization on Function Spaces via Sparse RKHS Manifolds

Davide Sartor, Meghan E. Huber, Donghyun Kim, Nathan Wycoff

原文摘要

Bayesian Optimization (BO) has become an established methodology for minimizing black-box functions of a vector input. Often, however, this parameter vector arises from the discretization of an inherently functional relationship. Several recent articles have considered the Functional Bayesian Optimization (FBO) setting, in which the variable to be optimized is not a member of a finite dimensional vector space, but rather an infinite dimensional function space. In this work, we propose $L^0$ Manifold Optimization (L0MO), a simple approach to FBO which searches the subset of a Reproducing Kernel Hilbert Space (RKHS) consisting of functions with a sparse representation in the kernel functions, optimizing both the kernel locations and their coefficients. We discuss in detail the relationship between our method and existing ones, providing a unifying lens through which to view prior works. To assess our method against the state of the art, we conduct an extensive computational study, and along the way develop a novel set of benchmark test functions which port standard finite-dimensional ones to the infinite dimensional domain. Our experiments demonstrate that, on balance, the proposed method achieves superior performance across a wide range of test benchmarks.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.08932

Shape-based Figure-Ground Organization in Vision Transformers

Matthias Tangemann, Benjamin Lo, Zygmunt Pizlo, Kaleem Siddiqi, Dirk B. Walther, Sven Dickinson

原文摘要

Rich perceptual structure emerges in modern vision encoders. Several studies have shown that the internal representation in many vision transformers separates foreground objects from the background, however, little is known about the visual cues that have been learned by these models. In this work, we study whether figure-ground organization in a broad range of 25 vision transformers relies on generalizable shape cues, rather than on superficial texture statistics. To do so we train linear probes to classify patches as figure or ground, and evaluate them zero-shot on synthetic stimuli where individual cues are systematically manipulated. For a broad range of vision encoders, we find that probes are robust to the random replacement of textures in the input image, suggesting that the emerging figure-ground organization relies on shape cues. Probes also generalize in a zero-shot fashion to synthetic images where individual shape cues, recognizability and spatial priors are controlled for. Our experiments reveal a strong influence of surroundedness and convexity cues, while results for parallelism and symmetry are more nuanced. More detailed analyses reveal stronger evidence for shape-based cues in larger models, that models trained for object-recognition tend to be less robust to texture changes and that figure-ground information emerges most prominently in middle layers. Taken together, our study demonstrates that emerging figure-ground organization in recent vision encoders relies strongly on generalizable shape cues, advancing our understanding of the internal processing in vision transformers, and opening an exciting avenue for computational research on human visual perception. Code and data is available at https://github.com/mtangemann/mlvbench.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12444

Sampling Colorings on $G(n, d/n)$ via Glauber Dynamics

Leon Schiller

原文摘要

We study the mixing time of Glauber dynamics for sampling uniformly from the proper $q$-colorings of sparse Erdős-Rényi random graphs $G(n,d/n)$. Our main result establishes that with probability $1-o(1)$ over the draw of $G$, Glauber dynamics is rapidly mixing for every $q\geq d+d^{1/2+\varepsilon}$, given any fixed $0<\varepsilon\leq1/2$ and any sufficiently large fixed $d$. In particular, the surplus of colors above $d$ is sublinear and close to $\sqrt{d}$. The achieved color range therefore approaches the tree uniqueness threshold and improves over the previously best achievable number of colors $q > 1.763 d$ due to Efthymiou, Hayes, Stefankovic, and Vigoda [SODA 2018]. Moreover, our mixing-time bound is $O(n^{2+o_d(1)})$, and hence almost quadratic as $d\rightarrow\infty$. Our proof is based on establishing a spectral gap for block dynamics resulting from a suitable decomposition of $G(n,d/n)$ into blocks and singleton vertices, ensuring that every high-degree vertex is encapsulated within a block. Our main technical contribution is a novel way of establishing rapid mixing of block dynamics via an integrated Bochner-Bakry-Émery approach, which we expect to have applications beyond sampling colorings. We further devise a new block decomposition of $G(n,d/n)$ that strengthens and simplifies similar constructions used in previous work. Finally, to compare block and Glauber dynamics, we establish a novel recursive separator decomposition of tree-like blocks, together with a coupling argument that avoids the need for nearly uniform color marginals at vertices adjacent to hubs. This comparison argument might be of independent interest.

math.CO · cs.DS · math.PR

查看论文
arXiv ↗PDF ↗