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

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

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

统计口径与数据新鲜度

统计 2026-11-15 06:34 — 2026-11-16 06:34（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-16 01:34最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

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

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

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 23,348 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33（北京时间）
新论文 · v1arXiv:2611.15658

Embedded Sim-to-Real Visual Servoing: Learned Reaching and Force-Guided Placement

Dezhi Sun, Duy Khang Banh, Kenan Niu

原文摘要

Embedded perception-to-control systems must combine visual targeting with reliable contact handling under tight computational constraints. We present a shared architecture on an NVIDIA Jetson AGX Orin controlling a Franka Research 3 through Cartesian impedance control. RealSense D435i observations, YOLO11-seg segmentation, depth back-projection, and hand--eye calibration provide metric robot-frame targets. We compare two strategies: compact proximal policy optimization (PPO) policies transferred from simulation for object- and hole-region reaching, and force-guided Cartesian placement using approximately 2 N normal contact and spiral search. The PPO policies achieved 87.2% and 83.1% success over 1000 simulation episodes each. Across 50 real-robot trials per strategy, the learned hybrid and force-guided analytical pipelines achieved 70.0% and 74.0% completion, respectively. Mean perception latency with TensorRT was 34.55 ms. These results support an embedded architecture combining learned free-space reaching with explicit contact correction.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15655

Can Agents Relive Past Experiences? Diagnosing Event-Affect Decoupling in Affective-Episodic Retrospection

Tingna Xie, Ming Wang, Shi Feng, Yongkang Liu

原文摘要

As memory-augmented agents increasingly support long-term and personalized interactions, reliable recall of emotional experiences while preserving their associated affect becomes necessary. However, existing evaluations usually assess emotion accuracy and factual memory grounding separately, overlooking event-affect correspondence. In this work, we formulate Affective-Episodic Retrospection (AER) as a task that explicitly evaluates the recovery of past events, associated affects, and their correspondence, and define Event-Affect Decoupling as a failure mode where the correct emotion is recalled but associated with the wrong episode. To diagnose Event-Affect Decoupling, we propose EM-TRACE, a stage-wise framework that decomposes AER into retrieval, affect recovery, and realization. On a controlled GoEmotions-based benchmark, Emotion-only retrieval achieves 28.65% affect recovery but retrieves the target episode for only 4.44% of queries, yielding a UAR of 24.21%. Further analysis reveals that event retrieval and affect assignment introduce distinct binding failures. These findings show that reliable AER requires grounded recall of emotional experiences, where episode retrieval, affect recovery, event-affect binding, and generation quality should be evaluated jointly. Our code is available at https://anonymous.4open.science/r/A412/.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15653

A Mechanistic Interpretability Study of an Astronomy Foundation Model

Rachel C. Zhang, Alberto Bietti, Wes Gurnee, Alessandro Favero, Miles Cranmer

原文摘要

Foundation models are increasingly used across the sciences, but whether their internal computations correspond to known scientific operations or proceed through different mechanisms remains unclear. Understanding these mechanisms is essential for assessing reliability, identifying failure modes, and learning new science from the models. We present, to our knowledge, the first causal mechanistic interpretability study of an astronomy foundation model, AION-1, focusing on its multimodal advantage in redshift prediction, where combining imaging with photometry outperforms photometry alone. We find that this advantage is largest for spatially extended and dust-attenuated galaxies, and that most of it is localized to the first of the encoder's twelve blocks. Within that block, how well a property is linearly decodable does not predict whether it can be localized. Spatial extent is causally used, and one attention head dominates linear probing for it, yet ablating that head has negligible effect on redshift prediction: the information is distributed across heads and is decodable again one layer after we erase it. Dust attenuation shows the opposite pattern: it is only weakly decodable anywhere in the encoder, yet a single head is necessary for most of the multimodal advantage, particularly for the most dust-attenuated galaxies, and keeping that head as the only active head in its block preserves nearly all of the advantage. None of the astrophysically motivated operations we tested explains what this head computes. Whether this reflects a limitation of current interpretability methods or a computation that does not correspond to any known astrophysical operation remains open, and resolving it is a prerequisite for using interpretability as a tool for scientific discovery.

cs.LG · astro-ph.IM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15652

Taming Neural Fields with a Frequency-Lipschitz Curriculum for Sparse-View CT Reconstruction

Songtao Hu, Jingrui Wu, Hong Ding, Fanhao Zhu, Yunhao Liu, Suyang Xi

原文摘要

Sparse-view computed tomography (SVCT) reduces radiation dose by acquiring fewer projection views, but the resulting under-determined inverse problem requires careful regularization to prevent reconstruction algorithms from fitting streak artifacts and hallucinated structures. Existing implicit neural representation (INR) methods rely on implicit spectral bias or iterative external denoising, yet they provide limited control over when high-frequency capacity is exposed during optimization. To address this limitation, we propose FLIC (Frequency-Lipschitz INR Curriculum), a capacity-controlled self-prior INR framework that makes the network's representational capacity explicit and schedulable. The core of our method is a joint frequency-Lipschitz curriculum that couples random Fourier feature encoding with spectrally normalized MLP decoding under non-uniform Lipschitz budgets, guiding reconstruction along a coarse-to-fine trajectory from stable global anatomy to fine details. The terminal capacity is automatically calibrated from FBP gradient statistics, enabling scan-adaptive regularization without per-scan manual tuning of the terminal Lipschitz budget. We further introduce a prior-guided adaptive ray sampling strategy that concentrates integration samples near high-gradient anatomical boundaries, improving forward-model fidelity. The entire framework operates in a single training stage without iterative denoising, enabling efficient per-image reconstruction. Extensive experiments on four public CT datasets under noise-free and low-dose settings show that our method achieves state-of-the-art unsupervised reconstruction quality with consistent performance across diverse anatomical structures.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15651

Recover, Don't Just Continue: Learning from Feedback for Physical Failure Understanding and Correction

Miao Pan, Kaixiang Yao, Xiaohe Zhou, Xu Wang, Qinfeng Li, Wenqi Zhang, Xuhong Zhang

原文摘要

Multimodal large language models are regarded as the cognitive foundation of embodied intelligence, but planning from instructions alone cannot make them reliable. During execution, actions deviate from intended effects, constrained by the embodiment and environment. An embodied brain must understand why execution deviates, identify what can be reliably realized, and revise decisions using interaction experience. These correspond to causal failure localization, capability-constrained adaptation, and experience-driven revision. Current embodied foundation models largely lack these capabilities. To address this, we introduce Embodied-Corrector. We construct failure-recovery data by injecting perturbations at subtask boundaries of successful trajectories, replaying affected subtasks, and keeping failures that are observable from public evidence and recoverable from the current state. We align actions, consequences, failure causes, and recoveries into Judge-Cause-Sub-Fine supervision. Training uses evaluation-first SFT: the model learns Judge and Cause first, then Sub and Fine conditioned on accurate prefixes. Since deployment uses self-generated prefixes, evaluation errors propagate into recovery planning, and response-level rewards are too coarse to locate affected planning tokens. We therefore use OPD to internalize the planning distribution under accurate prefixes into that under self-generated ones: the model generates plans from self-generated prefixes, while a contrastive forward pass with accurate prefixes compares token probabilities to reinforce or suppress planning tokens. At deployment, this branch is removed. Experiments show stronger failure analysis and corrective planning: with a frozen VLA, composite task success improves by 6.1 percentage points; with fixed GPT-5.5 execution, manipulation and navigation tasks improve by 13.9 percentage points.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15650

Single-View RGB-D Force--Deformation Estimation for Robotic Manipulation of Elasto-Plastic Materials

Dezhi Sun, Marijn van Hilten, Kenan Niu

原文摘要

Persistent deformation complicates elasto-plastic manipulation by coupling physical interaction with spatially distributed shape changes. We investigate the force--deformation relationship using a standard robot, a single eye-in-hand RGB-D camera, and intrinsic force estimates. A 7-DoF Franka Emika FR3 performs normal indentations while an Intel RealSense L515 captures pre- and post-contact surfaces. Point-cloud processing localizes deformation and estimates displaced volume. Force--volume characterization includes 27 measurements over nine force levels. A compact multilayer perceptron (MLP), trained on 52 force--volume pairs at four levels, achieves a held-out RMSE of 1.857 N and $R^2=0.440$. A separate comparison shows lower error for a quadratic model at 16 N and for the MLP at 19 and 23.5 N. An eight-step experiment at 4 N per interaction demonstrates cumulative deformation localization from the second indentation onward. These results establish a practical measurement basis for deformation-aware manipulation using intrinsic force estimates and single-view geometry.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2604.02721Berkeley BAIR

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

Ornith Team, Xiaoya Li, Guoyin Wang, Songqiao Su, Jiwei Li, Chris Shum

原文摘要

Competitive programming remains one of the last few human strongholds in coding against AI. The best AI system to date still underperforms the best humans competitive programming: the most recent best result, Google's Gemini~3 Deep Think, attained 8th place even not being evaluated under live competition conditions. In this work, we introduce GrandCode, a multi-agent RL system designed for competitive programming. The capability of GrandCode is attributed to two key factors: (1) It orchestrates a variety of agentic modules (hypothesis proposal, solver, test generator, summarization, etc) and jointly improves them through post-training and online test-time RL; (2) We introduce Agentic GRPO specifically designed for multi-stage agent rollouts with delayed rewards and the severe off-policy drift that is prevalent in agentic RL. GrandCode is the first AI system that consistently beats all human participants in live contests of competitive programming: in the most recent three Codeforces live competitions, i.e., Round~1087 (Mar 21, 2026), Round~1088 (Mar 28, 2026), and Round~1089 (Mar 29, 2026), GrandCode placed first in all of them, beating all human participants, including legendary grandmasters. GrandCode shows that AI systems have reached a point where they surpass the strongest human programmers on the most competitive coding tasks.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.02025

Hippasus: Accurate and Cost-Efficient Feature Augmentation over Relational Tables

Serafeim Papadias, Kostas Patroumpas, Dimitrios Skoutas

原文摘要

ML models critically depend on feature quality, yet in real-world settings, useful features are often distributed across multiple relational tables rather than a single dataset. Feature augmentation addresses this problem by automatically discovering and joining additional tables to enrich a base table with predictive features. However, scaling feature augmentation to complex schemas with many tables and multi-hop relationships is challenging. It requires exploring a large space of join paths, executing costly joins, and selecting useful features from noisy results. Existing approaches suffer from either limited effectiveness or efficiency. Restricting exploration to simple joins limits predictive performance, while more expressive methods rely on expensive training data, lack scalability, or fail to fully exploit schema-level semantics. We present Hippasus, a cost-aware, LLM-guided feature augmentation framework over relational schemas, that addresses these challenges. Hippasus ranks candidate join paths before executing any join, by combining lightweight statistical signals with adaptive semantic analysis, invoking an LLM only when necessary. It further introduces efficient multi-way join execution with cross-path feature consolidation, and a hybrid feature selection strategy that integrates statistical relevance with semantic refinement. Experiments on 13 real-world datasets show that Hippasus improves predictive performance by up to 15.7% on average over state-of-the-art methods, while running on par with the fastest of them and keeping its LLM token cost low.

cs.DB · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15645

Ultrasound Elastography: Excitation Methods and Low-Cost Alternative

Corin F. Otesteanu

原文摘要

Ultrasound elastography (or elasticity imaging) is a method that characterizes the tissue mechanical properties with the purpose of aiding the diagnosis of certain pathologies. Many novel clinical applications use the assumption that these tissue properties are changed in the presence of pathological processes. Characterization of tissue mechanical properties is achieved by imaging the response of the tissue to an induced stress or excitation. A plethora of approaches have been used in the scientific community to induce excitation in tissue, which usually require additional tools or devices than are costly. Furthermore these are usually integrated in the imaging pipeline using additional software or hardware for control. An alternative that is simpler, faster to integrate (and low-cost) is proposed in this work, by using readily available smartphones as a source of mechanical excitation. The induced displacements are used to solve the elasticity inverse problem (IP) using a finite element method (FEM) approach. Preliminary elasticity reconstructions of a phantom that mimics tissue are similar to when using a dedicated actuator as means of inducing harmonic displacements, illustrating the feasibility of our low-cost ultrasound elasography approach.

cs.CV · eess.IV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15644

When Agents Need to Consolidate Memories: What RRR Consolidation Explains, and What It Does Not Explain, in Conversation ESAA

Elzo Brito dos Santos Filho

原文摘要

Language-model agents can share conversational history across sessions, but persistence does not guarantee retrieval of current decisions and their provenance. This engineering study presents Memory-TCG, a Conversation ESAA extension inspired by ringing, resonance and renormalization (RRR), and an exploratory synthetic evaluation comparing chronological retrieval, two simplified baselines (B, recency-aware, and B', authority-aware), full RRR, and variants under three output budgets. With 480 facts and 1,024 tokens, full RRR recalled 0.44 of current decisions, versus 0.06 for chronological retrieval and 0.58 for the oracle ceiling; with 4,096 tokens it recalled all of them. B' and the no-resonance variant matched full RRR in decision recall across all nine scale-budget combinations, as expected when the active decision set and the adapter ordering are the same. The isolated contribution of ringing to decisions was not measured: comparator D1 cuts facts before the graph is built, and the product retains active decisions by rule. Before the output limit, full-RRR conflict F1 was 0.615 at all three scales; after it, at 480 facts and 1,024 tokens, it was 0.000. Reserving 20% of the budget for conflicts raised that F1 to 0.431 in that scenario, at the cost of lowering decision recall from 0.44 to 0.34, and to 0.930 at 4,096 tokens without decision loss. Fixtures are repetitive, comparators are simplified, and the evaluation was not independently replicated; the results support an engineering analysis, not a claim of selectionist superiority.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2604.08410

BLaFA: Bridging Language to 3D Functional Affordances for Dexterous Robotic Grasping in Tool Use

Fan Yang, Wenrui Chen, Guorun Yan, Ruize Liao, Wanjun Jia, Dongsheng Luo, Jianwen Hu, Jiacheng Lin 等 11 位作者

原文摘要

In industrial assembly, equipment maintenance, and everyday tool-use scenarios, robots need not only to grasp objects stably but also to establish task-appropriate contact configurations according to task intentions and tool functionality. However, existing methods lack explicit mappings from open-vocabulary instructions to 3D functional contact structures and dexterous grasp configurations, limiting robots' adaptability to diverse tools and functional tasks. To address this limitation, we propose BLaFA (Bridging Language to 3D Functional Affordances for Dexterous Robotic Grasping), a structured framework for language-driven functional dexterous grasping. First, a Knowledge-guided Language Parsing (KLP) module leverages structured knowledge to transform natural-language instructions into semantic sextuples of manipulation constraints. Second, a 3D Gaussian Splatting based hierarchical semantic representation and a Triangular Functional Point Localization (TriLocation) module are developed to localize 3D functional contact keypoints under task-tool topology constraints. Finally, a 3D Keypoint Grasp Matrix Transformation (KGT3D+) module maps the localized keypoints and semantic constraints to executable wrist poses and finger-level joint and force commands. Evaluations on 100 open-vocabulary language instructions, 14 task-tool combinations covering four functional intents, and real-world robotic experiments in representative scenes demonstrate that BLaFA can effectively translate natural-language instructions into task-aligned 3D functional contact structures and corresponding dexterous grasps, thereby enabling language-driven robotic tool use across diverse tasks. The source code will be made publicly available. Code will be publicly available at https://github.com/PopeyePxx/BLaFA.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15642

Differential Backpack Language Models: Sense Inhibition via Signed Contextualization Weights

Konstantinos Skianis, Giannis Nikolentzos, Polykarpos Meladianos, Michalis Vazirgiannis

原文摘要

Backpack language models predict with a strictly linear combination of non-contextual per-word sense vectors, weighted by non-negative contextualization scores. We show that non-negativity conflates two properties: the linear readout, which carries the interpretability, and the conic combination, which merely restricts it. We relax the latter by computing the sense weights with differential attention, a difference of two softmax maps with a learned per-sense gain, so context can actively inhibit a sense; we call the result a differential Backpack. At equal parameters on WikiText-103 this cuts the Backpack's perplexity gap to a Transformer by 31%, improves over the softmax Backpack at every sense count, persists with a shrinking margin up to 350M parameters on OpenWebText, and is localized at the sense layer by ablations and controls. The learned inhibition is directly interpretable (a financial context drives the river sense of bank to -0.50), and the preserved per-sense attribution predicts counterfactual removals exactly. We tested a number of combination rules, showing the linear interface is nearly free. Making the readout nonlinear gains only 0.43 perplexity points while invalidating two thirds of the decomposition. The differential Backpack's senses are also better representations, improving zero-shot sentence similarity by up to 33%.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15641

Contour-Assisted Evolutionary Computation: Estimating Peaks From the Contour Lines of Evaluated Solutions

Jun Zhang, Tong Qian, Hua Ding, Zhi-Hui Zhan, Wei-Jie Yu, Jian-Yu Li

原文摘要

Evolutionary algorithms (EAs) evaluate many candidate solutions but use them mainly to rank individuals. This paper treats the evaluated solutions as the spot heights of a topographic survey and draws the contour lines they imply. The contour map decomposes the evaluated region into peaks: in two dimensions a contour tree with persistence separates significant peaks from interpolation ripples, and in more dimensions hill climbing on the interpolated surface locates the peaks and ray-cast level sets describe them. A memory of the explored peaks directs the search to new ones. The data-supported contours of each peak are extrapolated to zero size by an area law, exact for quadratic peaks and second-order accurate for smooth ones, that estimates a peak's location, height and shape before it is sampled. A contour-assisted EA (CA-EA) inserts contour steps with local search and peak memory into a genetic algorithm (GA), differential evolution or particle swarm optimization. A contour-assisted surrogate-assisted EA (CA-SAEA), for expensive problems, spends each evaluation on surrogate-screened offspring or on sampling around a peak, entered at the maximum of the interpolated surface. On 2-D benchmarks, CA-EA reduces the evaluations a plain GA needs by factors of 12 to 112; controls attribute its gain over classical memetic search to restarting local search on distinct peaks. On the CEC 2015 expensive suite in 10 and 30 dimensions, CA-SAEA has the second-best average rank, behind DYCORS and ahead of lq-CMA-ES and the competition winner MVMO, although in 30 dimensions MVMO wins significantly on 9 functions and loses on 6; there the map beats sampling around the best point on 5 of 15 functions and loses on 3. Entering the peaks at their extrapolated locations brought no gain at these budgets, although, with enough samples, it improves the estimated heights on most two-dimensional functions.

cs.NE · cs.AI · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04670

Sheaf-MPNN: A Library for Sheaf Neural Networks as Message Passing

Alessio Borgi, Mario Severino, Luke Braithwaite, Steve Azzolin, Rémi Bourgerie, Olga Zaghen, Emanuele Mule, Riccardo Ali 等 18 位作者

原文摘要

Standard Graph Neural Networks (GNNs) implicitly assume that neighboring nodes share the same feature space, which contributes to oversmoothing and poor performance on heterophilic graphs. Sheaf Neural Networks (SNNs) remove this assumption by giving each node and edge its own vector space and learning restriction maps that transform features as they move between neighbors. These maps define a sheaf Laplacian that drives diffusion over the graph, but existing implementations often assemble it explicitly as a global sparse block matrix, which adds memory and computational overhead and can hinder scalability. In this paper, we introduce Sheaf-MPNN, a PyTorch Geometric library that reformulates sheaf diffusion as local incidence-wise transport and aggregation, eliminating the need to construct the global Laplacian. Sheaf-MPNN implements fifteen families of SNNs under a unified message-passing framework, each supporting both homogeneous and heterogeneous graphs, and directed and undirected settings, with diagonal, general, orthogonal, and low-rank restriction maps and attention-based predictors. We further provide a unified benchmarking suite covering node- and graph-level tasks, heterogeneous graph learning, and computational efficiency, enabling systematic and reproducible comparisons across architectures. We establish theoretical equivalence between these message-passing formulations and their original counterparts and identify the architectural mechanisms needed to preserve their propagation dynamics. This unified perspective provides a principled foundation for implementing, comparing, and extending sheaf-based architectures within standard graph learning frameworks. Source code is available at https://github.com/alessioborgi/sheaf-mpnn.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15640

MemInStream: Memorizing or Merely Recognizing? Rethinking Streaming Video Memory Evaluation

Zhenqi He, Dunyuan Xu, Yang Bo, Kien T. Pham, Yanghao Wang, Shuhan Li, Xintong Guo, Yuyang He 等 13 位作者

原文摘要

Streaming video understanding aims to continuously process incoming visual observations, making the retention and retrieval of relevant information increasingly important as the video history grows. Although existing benchmarks include memory-related questions, question-answering accuracy alone does not reliably measure memory capabilities. Incorrect predictions may arise from failures in visual understanding rather than forgetting, whereas correct predictions may rely on linguistic priors or recent observations without requiring historical memory. To address these ambiguities, we introduce MemInStream, a benchmark dedicated to evaluating memory capabilities in streaming video understanding. We develop an evidence-controlled validation protocol that associates each question with temporally localized evidence intervals. The protocol validates evidence solvability and memory necessity by retaining questions that models can answer from the annotated evidence but cannot resolve using recent observations, post-evidence observations, or textual input alone. This helps disentangle memory limitations from understanding failures while reducing memory-independent shortcuts. MemInStream provides a systematic evaluation of memory capabilities through four major categories, covering Episodic Retrieval, State Tracking \& Updating, Multi-Evidence Integration, and Contextual Memory across diverse video scenarios. Overall, \textsc{MemInStream} provides a comprehensive and reliable benchmark for systematically evaluating memory capabilities in streaming video understanding.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15639

ChJGBench: A Comprehensive Benchmark for Chinese Legal Judgment Generation with Diagnostic Evaluation

Yinghao Hu, Linggang Kong, Qian Xiao, Yuting Huang, Yunlong Zhang, Yujie Zhang, Yiquan Wu, Fei Duan 等 12 位作者

原文摘要

With the rapid development of LLMs, increasing attention has been paid to whether they can reliably generate complete and legally valid judicial documents. This calls for a benchmark capable of evaluating whether models can accurately apply statutes and resolve outcome-critical issues, including claims, charges, penalties, and monetary obligations. However, existing benchmarks typically focus on isolated legal tasks or coarse-grained evaluation. We introduce ChJGBench, a benchmark for generating the reasoning and dispositive sections of Chinese judgments across civil, criminal, and administrative cases. Built from 3,462 real-world judgments, ChJGBench provides a case-type-aware diagnostic evaluation framework comprising 13 metric types and adopts a hybrid paradigm. Experiments reveal no uniform advantage for legal-domain models over general-purpose models, with model strengths varying across diagnostic dimensions. Performance is generally stronger on criminal cases, while civil and administrative cases continue to present substantial challenges.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15638

Helping Hand: A Continuum Robotic Grasper for Traction in Single-Channel Endoscopic Submucosal Dissection

Bendavid Maimon, Thompson Wong, Aedan Mangan, Sukjun Kim, Michael C. Yip, Tania K. Morimoto

原文摘要

Endoscopic submucosal dissection (ESD) is a minimally invasive approach for removing large polyps from the colon and offers many benefits compared to other surgical approaches. However, ESD is technically very challenging to perform, leading to limited adoption by physicians. We propose the Helping Hand, a two-segment continuum robotic grasper that, together with an electrosurgical knife, enables tissue traction and cutting within a single 3.7 mm working channel. We achieve this functionality by creating a slot at the base of the Helping Hand that lets the electrosurgical knife extend out, enabling countertraction and cutting through one instrument lumen. We evaluate the Helping Hand's workspace and its ability to provide traction forces from different starting configurations. Finally, we demonstrate the full workflow by isolating and removing tissue in an ex vivo chicken thigh, illustrating the potential for the Helping Hand to help improve ESD procedures.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.22841

How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models

Leonard Hackel, Tom Burgert, Begüm Demir

原文摘要

Large-scale foundation models (FMs) in remote sensing (RS) (denoted as RS FMs) are developed following paradigms established in computer vision (CV), yet the validity of transferring CV scaling laws to RS has not been systematically examined. We hypothesize that RS FMs enter an overparameterized regime at substantially smaller scales than their CV counterparts, with task-relevant information encoded redundantly across model dimensions. To test this hypothesis, we apply post-hoc slimmability, uniform width reduction of pretrained encoder transformer blocks, to measure representational redundancy across ten state-of-the-art RS FMs on classification, segmentation, and change detection. RS FMs retain on average over 85% relative accuracy on RS classification datasets under aggressive width reduction, while masked autoencoder (MAE) and DINOv2 pretrained on natural images (denoted as CV MAE and CV DINOv2) degrade sharply on ImageNet subsets of matched class count over the same range of computational requirements. A CV MAE evaluated directly on the same RS dataset narrows but does not close the gap, indicating that both dataset characteristics and domain-specific pretraining contribute to the differences between the models. Analyses of the representation space of the models indicate that task-relevant variance concentrates in few principal components and is redundantly encoded across model dimensions. We further show that learned slimmable training improves over post-hoc slimmability for contrastive objectives, but reconstruction-based objectives do not benefit consistently from current slimmable training protocols. Our findings establish post-hoc slimming as a practical deployment strategy for resource-constrained RS applications and as a diagnostic tool for representational redundancy in RS FMs. Code is available at https://github.com/hackelle/slimmable-remote-sensing-foundation-models.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.03766

Inaccessibility in public transit networks: A study of the London and New York City subway networks

Katherine Betz

原文摘要

The study of networks derived from infrastructure systems has received considerable attention, yet the accessibility of such systems, remains comparatively underexplored. This study examines infrastructure-based accessibility in two major legacy transit systems, the London Underground and the New York City Subway. We construct accessibility-restricted subnetworks in which nodes represent accessible stations and edges represent connections between them, and compare them with the corresponding full transit networks. We analyze the cyclomatic number, betweenness, and closeness centrality to identify key accessible hubs and differences in network organization. London has a larger share of accessible stations, and its accessible network retains more of the alternative routes of its full network, whereas New York City has a more compact accessible core concentrated around central Manhattan and major interchanges. Comparing the observed accessible stations with random sets of the same size, we find that in London they have higher betweenness centrality than random allocations, but more of their stations are beyond two stops of an accessible station, consistent with accessibility concentration at major interchanges and along fully step-free lines. In New York City, their higher betweenness centrality is fully explained by their concentration at interchanges, and their coverage is similar to that of random allocations. We also examine income and daytime activity around accessible stations. In both systems, several of the most central accessible stations are in high-activity locations, whereas accessible stations show no consistent relationship with median income. Our findings highlight substantial differences in accessibility between and within the two systems and demonstrate the utility of network-theoretic methods for understanding and improving transit infrastructure.

cs.SI · physics.soc-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15635

An Empirical Square-Root Law for the Degree Discrepancy of Binary m-Sequences

Joonas Pääkkönen

原文摘要

Let $k\ge 2$, $N=2^k$, $M=N-1$ and let $Δ(r)$ be the range, over all starting offsets, of the total-variation degree discrepancy of a length-$r$ window of a primitive binary linear feedback shift register (LFSR) of period $M$. Degree-discrepancy profiles for every $k\le 28$ support the scaling $\max_r Δ(r)=Θ(\sqrt{N})=Θ(2^{k/2})$. The tabulated peaks are maxima on a discrete grid, hence lower bounds on the exhaustive maximum. The normalized peaks $d_k=\max_{r\in R_k}Δ(r)/2^{k/2}$ oscillate between values near 1/2 and values that approach, but do not exceed, 1. The data suggest $\liminf d_k=1/2$ and $\limsup d_k\le 1$. We conjecture the same square-root law for the exhaustive maximum, with those normalized envelopes. A Brownian-bridge heuristic accounts for the square-root scale. The same profiles do not place the recorded maximizer at mid-path: after folding by the complement identity $Δ(M-r)=Δ(r)$, the median of $\min(ρ^*_k,1-ρ^*_k)$ is 0.35, and several $k$ (notably 16 and 28) peak on a short window. Mid-horizon $Δ$ remains a large fraction of the peak, so the square-root scale can still come from a Brownian-bridge envelope. The same range has two readings of the starting offset: a pairing fragment in serial-knockout scheduling, and a change to the plaintext on an LFSR orbit. The location of the maximizer is not part of the conjecture. Open questions that separate the conjecture from a theorem are listed.

cs.IT · math.CO · math.NT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.00828

Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models

Okan S. Coskun, Florian Rottach, Carsten Eickhoff, William Rudman

原文摘要

We investigate the geometry of decision-making in Multiple Choice Question Answering (MCQA) through the lens of isotropy. Analyzing five open-weight models across diverse datasets, we identify decision-critical transition layers characterized by a shift in isotropy, coinciding with a major representational change and the emergence of task-relevant clusters. We demonstrate that this synchronized geometric behavior is strongly correlated with downstream accuracy ($r\approx0.84$), displaying its relevance for successful decision-making. Furthermore, we show that this transition is robust to prompt variations, suggesting that it reflects a general mechanism of model behavior.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.12183

Data-Efficient Unknown Attack Detection in IoT Networks Using Pretrained Language Models

Shan Ali, Feifei Niu, Paria Shirani, Lionel C. Briand

原文摘要

The rapid evolution of cyberattacks continues to drive the emergence of unknown (zero-day) threats, posing significant challenges for network intrusion detection systems in Internet of Things (IoT) networks. Existing machine learning and deep learning approaches typically rely on large labeled datasets, payload inspection, or closed-set classification, limiting their effectiveness under data scarcity, encrypted traffic, and distribution shifts. To address these limitations, we propose SiamXBERT, a data-efficient, open-set Siamese meta-learning framework built on a pretrained language model for unknown-attack detection. The framework constructs a dual-modality feature representation by integrating flow-level and packet-level information, enabling richer behavioral modeling while remaining compatible with encrypted traffic. The model learns similarity patterns for known benign and attack classes using 100 labeled samples per class. It flags traffic that does not sufficiently match any known class as potentially unknown, using a threshold set without unknown-attack data. We evaluate SiamXBERT on two IoT intrusion detection datasets against five state-of-the-art detection methods. When training and testing are performed on the same dataset at this labeling budget, SiamXBERT attains the highest unknown F1-score, exceeding the strongest competing method on each dataset by 84.8% and 37.4%; the improvement is statistically significant against all five methods on one dataset and against four of the five on the other. When a model trained on one dataset is tested on another, SiamXBERT transfers effectively in one direction but degrades in the reverse, reflecting the rejection behavior learned from the source traffic rather than the choice of threshold. These results highlight the practicality of SiamXBERT for data-efficient unknown attack detection in real-world IoT environments.

cs.CR · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2609.10947

The Platonic brain bridge hypothesis: brain networks as architectural priors for multimodal large language models

Pengfei Zhang, Biao Tian, Xiangang Li, Li Liu

原文摘要

Multimodal large language models predict brain activity, but alignment has remained a measurement, not a design tool. We propose the Platonic brain bridge hypothesis: omni models, which jointly process video, audio and text, share brain-like representations usable in both directions. From model to brain, seven omni models show stable brain-likeness across participants, and our encoding experts lead the Algonauts 2025 out-of-distribution leaderboard by mean score. From brain to model, we make three contributions. Brain-MoE ties the experts of a frozen model to the seven cortical networks, raises held-out accuracy in all 15 model-benchmark pairs and exceeds capacity-matched random experts in 14. Brain-AVQA, to our knowledge the first audiovisual benchmark with cortical-network labels for every question, supplies the pretraining questions. Brain-Scope finds sparse features that predict brain responses, steer routing and, when removed, weaken brain prediction. Human brain organization is therefore a usable architectural prior for multimodal large language models.

q-bio.NC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15622

Quota-Based Traffic Classification for Bounded Jitter in Multi-CQF under Redundancy Mechanisms

Mohamed Elattar, Zhe Lou, Georg Carle

原文摘要

The demand for deterministic and reliable communication is rapidly increasing in industrial networks. Time-Sensitive Networking (TSN) addresses these requirements through deterministic scheduling and redundancy mechanisms such as Multiple Cyclic Queuing and Forwarding (Multi-CQF) and Frame Replication and Elimination for Reliability (FRER). Multi-CQF guarantees bounded end-to-end (E2E) latency and jitter, while FRER provides seamless fault tolerance through redundant forwarding. With static traffic classification, redundant paths with different hop counts can exhibit different E2E latency ranges. This can amplify jitter when a failure causes packets to be delivered over a longer redundant path. To address this, we propose a quota-based traffic classification mechanism that adapts class assignments hop-by-hop using a common E2E latency budget derived from the primary path, thereby mitigating jitter amplification. Simulation results show that the proposed mechanism reduces jitter amplification by up to 70% and latency degradation by up to 41% compared to static classification.

cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15621

Data-Free Metrics Don't Work: The Missing Invariance Under Functionally Preserving Reparameterisations

Gabryel Mason-Williams, Israel Mason-Williams, Fredrik Dahlqvist

原文摘要

Data-free methods for analysing and understanding the layers of neural networks offer many metrics for quantifying notions of 'strong' versus 'weak' layers, with the promise of increased interpretability. In particular, random matrix theory (RMT) offers data-free metrics that claim predictive power over the quality of pre-trained models at a layerwise precision and the ability to identify model pathologies, indicating a unique relationship with generalisation. As a result, metrics from RMT are championed for pre-training optimisation strategies and post-training compression. We establish that RMT-based metrics are unrelated to performance or training by showing that functionally preserving reparametrisations of a pre-trained model can have arbitrary metrics. We show this across a range of architectures and scales. To create functionally preserving reparametrisations, we exploit the well-established phenomenon of criticality: some layers can be re-initialised or re-randomised without affecting the functional behaviour of the model -- they are called robust -- while others cannot -- they are called critical. Re-initialising or re-randomising robust layers provides functionally preserving reparametrisations for which RMT-based metrics are arbitrary. Moreover, we show that relationships between metrics offered by RMT are spuriously related to generalisation. We conclude by showing that if many pre-trained models have data-free metrics in a 'good' range, it is, in part, dependent on model initialisation. Project page available at: https://gmw99.github.io/data-free-metrics-dont-work

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.04161

HEHA: Bounded Suboptimal Planning for Constrained Routing and Its Use in Heterogeneous Multi-Robot Exploration of Unknown Environments

Longrui Yang, Yiyu Wang, Jingfan Tang, Yunpeng Lyu, Shizhe Zhao, Chao Cao, Zhongqiang Ren

原文摘要

This paper considers the path planning problem for autonomous exploration of an unknown environment using multiple heterogeneous robots such as drones, wheeled, and legged robots, with different capabilities to traverse complex terrains. A key challenge there is to intelligently allocate the robots to the unknown areas to be explored and determine the visiting order of those areas subject to traversability constraints, which leads to a large-scale constrained multiple hamiltonian path problem (mHPP) that needs to be quickly and iteratively solved every time when new space is explored. To address the hallenge, we propose HEHA (Hierarchical Exploration with Heterogeneous Agents) using a recent hierarchical method that decomposes the exploration into global planning and local planning. The major contribution in HEHA is its global planning, where we propose a new routing algorithm RCH (Routing with Constraints and Heterogeneity) that can quickly find bounded sub-optimal solutions for mHPP to minimize the maximum path length (i.e., makespan) among the agents subject to traversability constraints. Additionally, the local planner in HEHA also considers heterogeneity to avoid repeated and duplicated exploration among the robots. The experimental results show, in the presence of heterogeneous traversability, our RCH can solve mHPP with up to 47% smaller makespan than several baselines, and HEHA can reduce the exploration time by up to 30% compared with existing approaches.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.11270

Quantifying Subliminal Behavioral Transfer Ratios in Language Model Distillation

Uwe König, Hamza Kazmi, Ruizhe Li, Maheep Chaudhary

原文摘要

Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are present in the teacher model, a phenomenon known as subliminal learning. While qualitative evidence supports the existence of this effect, its magnitude has not been systematically characterized. This study quantifies subliminal behavioral transfer ratios by steering two teacher models (Llama-2-7B-Chat and Qwen2.5-7B-Instruct) at varying steering strengths and distilling student models using only benign data. Evaluation on 100 JailbreakBench prompts with GPT-4.1, serving as the evaluator, indicates that transfer is robust but exhibits distinct scaling behaviors. Llama-2 demonstrates a sharp threshold ($τ= {0.25,0.32} \ \text{beyond} \ α= -0.15$), whereas Qwen2.5 displays continuous and higher levels of transfer ($τ$ up to $0.61$).

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15618

Data augmentation for the generalizability and transportability of fairness in a clinical heart failure algorithm

I. Elizabeth Kumar, Sherri Rose

原文摘要

Synthetic data augmentation has been proposed as a way to artificially supplement clinical datasets to address fairness concerns in downstream classification algorithms. This approach is closely related to upweighting or upsampling methods employed for the problem of class imbalance, which have shown mixed empirical results in practice. Synthetic data augmentation also runs the risk of overfitting to the noise present in subgroups with relatively small sample sizes, raising both generalizability and transportability concerns. We present an empirical evaluation of synthetic data augmentation for fairness in tabular data using simulation studies as well as a real-world application of in-hospital mortality classification for heart failure patients in two distinct data samples. We implement upsampling and upweighting methods as benchmarks for the implicit fairness objective of synthetic data augmentation. Our results suggest that the fairness impacts of data augmentation are sensitive to the design of the downstream algorithm as well as the deployment context and its similarity to the training data. It is crucial that studies making generalizability and transportability claims should provide empirical support for these assertions.

stat.AP · cs.CY · stat.ME

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15617

WaveletLoRA: Frequency-Aware Content-Style Decomposition for Personalized Image Generation

Peiyao Wang, Jiahui Sun, Weining Wang, Jing Liu

原文摘要

Content-style decomposition from a single image is a fundamental challenge in personalized image generation, aiming to separate subject identity from visual style for flexible recomposition. Existing approaches primarily operate in the spatial domain, without explicitly exploiting the distinct frequency characteristics naturally associated with content and style. In this paper, we propose WaveletLoRA, a novel frequency-aware framework for explicit content-style decomposition through wavelet-domain supervision. Specifically, we first apply a multi-level discrete wavelet transform (DWT) to decompose the reference image into low-frequency and high-frequency subbands. We then assign a dedicated LoRA branch to each subband, where the low-frequency branch models global appearance for style acquisition, while the high-frequency branches capture structural details for content preservation. To further improve disentanglement quality, we introduce a dense Mixture-of-Experts aggregation module together with a frequency-domain regularization objective, which reduces style leakage and enhance content fidelity. In addition, we establish WaveBench and develop a VLM-based evaluation protocol that explicitly measures both attribute similarity and attribute separation for disentanglement assessment. Extensive experiments demonstrate that WaveletLoRA consistently outperforms existing methods and produces results that better align with human preference.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15615

A Parallel Greedy Algorithm for Maximal b-Matching in Hypergraphs

Saeed Bakhshan, Daniel Grosu, Henrik Reinstädtler, Christian Schulz

原文摘要

We present \parallelBatchBMatch, a parallel batch-vote algorithm for maximal $b$-matching in hypergraphs. The algorithm is deterministic for a given ordering of edges and produces the same output as the sequential greedy algorithm, i.e., the lexicographically first maximal $b$-matching. Under a uniformly random priority order it performs $O(m')$ expected work in the binary fork--join model, where $m'$ is the number of pins, the total number of vertex--edge incidences. The algorithm performs at most $m$ rounds for every priority order, where $m$ is the number of edges. Every round of the algorithm has $O(\log^2 m')$ depth with high probability, and thus the total depth of the algorithm is $O(m \log^2 m')$ with high probability. We implement the parallel algorithm in CUDA and evaluate it on real-world hypergraphs with capacities $b \in \{1, 3, 5\}$. The parallel algorithm computes the same matchings as the greedy algorithms and for the case of $b = 5$ it is up to $19.07$ times faster than the existing state-of-the art greedy algorithm.

cs.DS · cs.DC

查看论文
arXiv ↗PDF ↗