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

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 22:53 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 23:14 — 2026-11-08 23:14（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：2026-11-08 22:53最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 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 14,661 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 22:48（北京时间）
版本更新 · v3arXiv:2606.29494

VCS-SLAM: Visibility-Consistent Semantic Fusion for 3D Gaussian SLAM

Raman Jha, Shuaihang Yuan, Yi Fang

原文摘要

Semantic 3D Gaussian SLAM commonly fuses 2D semantic priors into a persistent 3D map using uniform optimization weights. However, such priors are not equally reliable in online mapping: occlusions, unsupported semantic boundaries, and ambiguous ray geometry introduce persistent semantic artifacts into the global Gaussian map. We propose VCS-SLAM, a visibility-consistent semantic fusion framework for RGB-D 3D Gaussian SLAM. Instead of treating all semantic priors as uniformly valid signals, VCS-SLAM evaluates their geometric reliability through visibility consistency, surface-supported boundary evidence, and ray-level conflict uncertainty. The resulting reliability-aware objective suppresses occluded semantic updates, reduces unsupported semantic bleeding, and delays premature label assignment in ambiguous regions. Experiments on Replica show improved semantic consistency, boundary preservation, and reconstruction quality, while ScanNet results confirm competitive tracking under real RGB-D input. Under structured corruption of the 2D priors, VCS-SLAM degrades at little more than half the rate of a comparable semantic Gaussian SLAM baseline and outperforms naive gating, smoothness, and entropy-weighting variants of its own modules, indicating that the gains follow from the specific formulation rather than from reweighting alone. Code is available at \textit{https://github.com/jhakrraman/VCS-SLAM}

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06682

SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents

Guoqin Xiong, Shengtao Wen, Xiang Chen, Xinyi Zeng, Zhaoxin Fan, Wei Ye, Xiaofeng Cao, Sheng-Jun Huang

原文摘要

Tool-using large language model (LLM) agents translate model outputs into consequential actions, turning indirect prompt injection into an execution-security problem. Existing defenses constrain tool calls, trajectories, or information flows, but often leave action semantics, state dependencies, and evidence relations implicit, limiting generalization across heterogeneous tools and complicating safe updates. We present \ours{}, a dynamic ontology-guided governance framework. \ours{} grounds heterogeneous calls in a shared semantic representation and combines an executable ontology with episode-level task state to derive deterministic ready, waiting, and forbidden decisions. A waiting decision identifies an unmet but recoverable obligation, enabling bounded replanning without expanding the agent's authorization boundary. \ours{} evolves its ontology offline from verified training executions. An offline LLM proposes instance-independent action--state axioms, which are accepted only if they address ontology errors exposed by training failures, preserve logical consistency and protected entailments, and pass held-out validation before the ontology is frozen. We evaluate \ours{} on AgentDojo, ASB, and AgentDyn under benign and indirect prompt-injection settings. \ours{} achieves a 0\% attack success rate (ASR) across all three benchmarks while improving task utility under attack compared with existing baselines. These results show that explicit semantic governance can strengthen execution security without indiscriminate blocking.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06681

Do unlearning algorithms learn the right features?

Polina Dolgova, Amartya Sanyal, Sebastian U. Stich

原文摘要

Machine unlearning is commonly evaluated with standard post-deletion metrics that compare an unlearned model to one retrained on the remaining data. Such snapshot evaluations can conceal consequential differences in the features the two models encode. We prove that if an unlearned and a retrained model agree on their outputs but encode different features, a single gradient step on their prediction heads can break this agreement. We further show that deleting an arbitrarily small fraction of the data can cause retraining to select qualitatively different features, so matching retraining can require learning features that the full model never had. We then introduce a measure of feature recovery that separates missing from extraneous features. Across eight unlearning methods, models that perform well on standard metrics often fail to recover the retrained features. This mismatch predicts deviations from retraining under subsequent relearning and downstream adaptation, and directly correcting it systematically reduces these deviations.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06677

Self-Directed Apple Tasting

Tanmay Devale, Reed Phillips, Arvind Ramaswami

原文摘要

We study the classical apple-tasting setting, a partial feedback model in which the learner observes the true label only when it predicts $1$. A combinatorial characterization for the rates of this problem in the online adversarial setting has been studied by Raman et al. (2024). We study the self-directed setting, in which the learner can adaptively choose the order of the points it predicts on. In the realizable setting, we establish a tetrachotomy on the expected minimax number of mistakes made by any learner. Depending on the VC dimension, the $\emptyset$-centered star number, and the self-directed dimension, we show that the rates could possibly be $Θ(1)$, $O(\log n) \cap ω(1)$, $\tilde Θ(\sqrt{n})$, or $Θ(n)$. In the agnostic setting, the minimax regret is $\tilde Θ(\sqrt{n})$ or $Θ(n)$, depending on the VC dimension.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06674

AgentTrustCI: Build-Time Policy, Grounding, and Trajectory Tests for Java LLM Agents

Sachin Gupta

原文摘要

Infrastructure security does not establish whether an LLM agent selected an allowed tool, grounded its answer in tool output, or followed a required workflow. AgentTrustCI is a Java/JUnit 5 framework that expresses these application-layer expectations as policy, grounding, and trajectory checks over recorded traces. A deterministic replay implementation supports repeatable build-time tests; a judge interface provides an extension point for optional semantic evaluation. On 55 synthetic cases spanning seven enterprise domains, the full pipeline correctly classifies all 30 injected faults and 25 passing controls, including ten non-trivial controls, and misses none of 12 designated critical cases. Each single-layer configuration correctly classifies 35 cases because the corpus deliberately isolates ten faults per layer. A grounded answer obtained through a disallowed sequence illustrates the additional coverage of trajectory checks. Repeated measurements quantify validator execution separately from process startup and reporting. These results establish coverage of the authored regression suite, not production accuracy. We describe a production-trace validation protocol, optional LLM-judge integration, and maintenance of expectations as workflows evolve. The contribution is a practical pattern for expressing behavioral contracts within an existing Java release pipeline.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06673

Which Physical Tactile Cues Matter for Contact-Rich Imitation Learning? A Controlled Real-Robot Study

Xuhao Qin, Xiyan Huang, Haoyu Dong, Xi Zhang, Chenxi Xiao

原文摘要

Vision-based tactile sensors capture multiple aspects of physical interaction within a single image stream, including contact appearance, geometry, indentation depth, and tangential deformation. However, existing visuo-tactile policies often directly process tactile observations as images, making it difficult to determine which physical cues contribute to policy learning. This paper presents a controlled real-robot study that compares physically interpretable tactile signals using the LeRobot platform, enhanced with our visuo-tactile perception system. From the same tactile stream, we derive tactile RGB images, normal/depth maps, and marker-flow fields, representing contact appearance, geometry, and tangential deformation, respectively. Using identical task demonstrations and the same policy backbone, we evaluate the individual and combined contributions of these tactile cues. We further compare tactile encoders and visuo-tactile fusion strategies. Evaluation across 720 real-robot trials yields four key findings: (1) tactile perception substantially improves the overall success rate from 57.8% to 78.9%, although its contribution varies across task stages; (2) marker flow is the most effective individual cue, achieving a success rate of 74.4% and playing a particularly important role in regulating established contact; (3) cue-factorized encoding consistently improves performance, highlighting that different physical cues require tailored processing techniques; and (4) although the effectiveness of tactile fusion is task-dependent, cross-attention offers a lightweight solution with performance comparable to that of pretrained tactile encoders.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.06988

Space efficient implementation of hypergraph dualization in the D-basis algorithm

Skylar Homan, Mikhail Khlystun, Anoop Krishnadas, Kira Adaricheva

原文摘要

We present a new implementation of the $D$-basis algorithm called the Small Space which considerably reduces the algorithm's memory usage for data analysis applications. The previous implementation delivers the complete set of implications that hold on the set of attributes of an input binary table. In the new version, the only output is the frequencies of attributes that appear in the antecedents of implications from the $D$-basis, with a fixed consequent attribute. Such frequencies, rather than the implications themselves, became the primary focus in analysis of datasets where the $D$-basis has been applied over the last decade. The $D$-basis employs a hypergraph dualization algorithm, and a dualization implementation known as Reverse Search allows for the gradual computation of frequencies without the need for storing all discovered implications. We demonstrate the effectiveness of the Small Space implementation by comparing the runtimes and maximum memory usage of this new version with the current implementation.

cs.DB · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.20270

Optimality-Informed Neural Networks for Solving Parametric Optimization Problems

Matthias K. Hoffmann, Amine Othmane, Kathrin Flaßkamp

原文摘要

Many engineering tasks require solving families of nonlinear constrained optimization problems, parametrized in setting-specific variables. This is computationally demanding, particularly if solutions have to be computed across strongly varying parameter values, e.g., in real-time control or for model-based design. Thus, we propose to learn the mapping from parameters to the primal optimal solutions and to their corresponding duals using neural networks, giving a dense estimation in contrast to gridded approaches. Our approach, Optimality-Informed Neural Networks (OptINNs), combines (i) a KKT-residual loss that penalizes violations of the first-order optimality conditions under standard constraint qualification assumptions, and (ii) problem-specific output activations that enforce simple inequality constraints (e.g., box-type/positivity) by construction. This design reduces data requirements, allows the prediction of dual variables, and improves feasibility and closeness to optimality compared to penalty-only training. Taking quadratic penalties as a baseline, as previously proposed for this problem class in the literature, our method simplifies hyperparameter tuning and attains tighter adherence to optimality conditions. We evaluate OptINNs on different nonlinear optimization problems ranging from low to high dimensions and compare them with equally sized neural networks trained using the quadratic-penalty method. On small problems, OptINNs match a quadratic-penalty baseline in primal accuracy while additionally predicting dual variables with low error. On larger problems, OptINNs achieve lower constraint violations, lower primal error, and lower errors in the predicted costs. These results suggest that embedding feasibility and optimality into the network architecture and loss can make learning-based surrogates more accurate, feasible, and data-efficient for parametric optimization.

math.OC · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.06395

Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves

Kartik Tandon, Julian Gould, Tanishq Bhatia, Francesca Dominici, Alejandro Ribeiro, Claudio Battiloro

原文摘要

Modern deep learning architectures increasingly contend with sophisticated signals that are natively infinite-dimensional, such as time series, probability distributions, or operators, and are defined over irregular domains. Yet, a unified learning theory for these settings has been lacking. To start addressing this gap, we introduce a novel convolutional learning framework for possibly infinite-dimensional signals supported on a manifold. Namely, we use the connection Laplacian associated with a Hilbert bundle as a convolutional operator, and we derive filters and neural networks, dubbed as \textit{HilbNets}. We make HilbNets and, more generally, the convolution operation, implementable via a two-stage sampling procedure. First, we show that sampling the manifold induces a Hilbert Cellular Sheaf, a generalized graph structure with Hilbert feature spaces and edge-wise coupling rules, and we prove that its sheaf Laplacian converges in probability to the underlying connection Laplacian as the sampling density increases. Notably, this result is a generalization to the infinite-dimensional bundle setting of the Belkin \& Niyogi \cite{BELKIN20081289} convergence result for the graph Laplacian to the manifold Laplacian, a theoretical cornerstone of geometric learning methods. Second, we discretize the signals and prove that the discretized (implementable) HilbNets converge to the underlying continuous architectures and are transferable across different samplings of the same bundle, providing consistency for learning. Finally, we validate our framework on synthetic and real-world tasks. Overall, our results broaden the scope of geometric learning as a whole by lifting classical Laplacian-based frameworks to settings where the signal at each point lives in its own Hilbert space.

cs.LG · cs.AI · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06664

CardioDrift: Automatic Cardiac Motion Tracking on a 3D Atlas Mesh via Shape-aware Coherent Point Drift with Slice Shift Correction

Reza Akbari Movahed, Abuzar Rezaee, Shatha Alamri, Edmond S. L. Ho, Fani Deligianni, Ali Gooya

原文摘要

Automatic cardiac motion tracking from cine cardiac magnetic resonance (CMR) imaging is essential for quantifying myocardial motion abnormalities associated with cardiovascular disease. Existing methods fall into two groups: those that represent motion without anatomical correspondence across subjects and therefore limit inter-subject motion assessment; and those that represent motion with globally corresponding points, which typically require a time-consuming and error-prone semi-automatic step to fit a cardiac atlas to the subject space. To address these limitations, this study proposes CardioDrift, a fully automatic, atlas-based probabilistic framework that represents subject-specific cardiac motion on a 3D atlas mesh with globally corresponding points. The Coherent Point Drift (CPD) formulation is generalised to jointly register the atlas surfaces of multiple cardiac regions to the anatomically corresponding contours extracted from cine CMR segmentation maps throughout the cardiac cycle. Slice-shift correction is embedded in the same probabilistic model, estimating slice-wise translations that suppress the misalignment artefact limiting atlas-fitting accuracy. Evaluation on 1301 randomly selected UK Biobank subjects and the M&M dataset, CardioDrift attains Dice similarity coefficients (DSCs) of $92.23\pm8.70\%$, $82.11\pm7.56\%$, and $88.69\pm4.13\%$ for the left ventricle (LV), myocardium (Myo), and right ventricle (RV), exceeding the strongest baseline on every distance and overlap metric of both datasets.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.14189

SUPER - Sensitivity-based Uncertainty-aware Performance and Risk Assessment in Visual Inertial Odometry

Johannes A. Gaus, Daniel Häufle, Woo-Jeong Baek

原文摘要

This paper presents SUPER (Sensitivity-based Uncertainty-aware PErformance and Risk assessment), a bounded controller that adapts visual measurement information in visual-inertial odometry at runtime. Building on multi-view landmark dispersion from stereo observations, SUPER projects track consistency into pixel space and combines it with the reprojection residual to gate a temporally smoothed, bounded information update. Because the controller operates inside nondeterministic optimizers, we additionally propose an action-verification protocol based on factor-level logs, inactive-instrumented controls, and same-linearization replay. We evaluate SUPER in Ceres and g2o backends on EuRoC, TUM-VI, UMA-VI, and TartanAir under controlled visual corruptions, with a frozen policy and prospective confirmation. SUPER is computationally efficient and selectively active, but does not establish a general accuracy improvement: all 13 split-level confidence intervals cross zero, and effects are heterogeneous across corruption families. The action-verification protocol reliably distinguishes controller-induced state changes from solver variability.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.00489

A hybrid quantum-classical neural network for learning to route

Marcus Rolf Peter Ritt, Alexsandro Santos da Rosa Júnior, Marcos Vinicius Reballo, Cesar Augusto do Amaral, Fernando Augusto Caletti de Barros

原文摘要

This work studies hybrid quantum-classical neural networks for learning routing heuristics. Specifically, this paper asks whether small quantum neural networks can replace parameter-heavy modules inside a competitive attention-based routing model while maintaining solution quality. For the capacitated vehicle routing problem, encoder feed-forward replacement emerges as the most promising design: it reduces the number of model parameters by 56.6% while keeping the hybrid model close to the classical neural baseline at small and medium instance sizes, although the gap grows for larger instances. This work also compares to classical routing algorithms, which remain highly competitive and often superior on the fixed Euclidean test sets. Our results therefore do not indicate quantum advantage or solver dominance, but identify encoder feed-forward replacement as a viable hybrid-module compression strategy for neural combinatorial optimization.

cs.LG · quant-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06662

Where Search Agents Go Off the Rails: Graph-Grounded Step-Level Verification

Hyeseo Jeon, Seonho Yoo, Jay-Yoon Lee

原文摘要

Search-augmented reasoning systems can reach correct answers while making errors in intermediate steps. Reliable auditing must check whether evidence $D$ covers the question $Q$, reasoning $T$ addresses $Q$, and $T$ is grounded in $D$. We introduce GraphRail, which represents requirements, evidence, and reasoning as structured claims and compares them without a generative judge or gold answer. Across three multi-hop QA benchmarks and three reasoning frameworks, GraphRail improves error recall over generative verifiers while remaining stable under stochastic extraction. Its diagnoses can also guide online reasoning, providing a traceable way to detect and correct intermediate errors.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06661

Fingerprinting the Dispatchers behind Distributed Model Extraction

Snigdha Chandan Khilar

原文摘要

API distillation campaigns try to hide model-stealing traffic by splitting requests across thousands of load-balanced accounts, which standard content classifiers often miss. However, request timestamps, specifically arrival time and stream completion time, reveal the underlying dispatching strategy, such as round-robin counters or key-shuffling pools. Using a 20 percent seed set, this timing analysis can forensically rank the remaining accounts of a campaign with 0.92 to 1.00 AUC within 20 minutes, even across thousands of real production accounts. While adaptive attackers struggle to hide rotating dispatchers using jitter, pinning keys successfully evades detection, though it can severely throttle throughput when quotas bind. Ultimately, timing exposes shared infrastructure patterns even when content filters fail.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06984

Resource-Efficient Reinforcement Learning Post-Training through Elastic Expert Parallelism

Jia Wei, Ziyi Qiu, Yi Xu, Xuehai Qian

原文摘要

Reinforcement learning post-training improves the capabilities of large language models, but generating training responses is a major computational bottleneck. In mixture-of-experts models, workers that finish their assigned responses may remain occupied because their experts are still needed by workers processing longer responses. Consequently, approximately one-third of occupied worker time in the baseline occurs after local response generation finishes. Here we present FlexFloor, a system that enables earlier resource release during synchronous response generation while preserving the expert computation required by ongoing responses. FlexFloor jointly adapts response scheduling and the active group of workers. It uses historical response lengths and memory constraints to guide batching and prompt placement, then progressively releases workers while maintaining expert availability and correct communication. Compared with the verl baseline, FlexFloor generates approximately 65.40% more response tokens per unit of occupied computing time and increases response generation throughput by 52.74%, with little observed variation in rollout reward. By making reinforcement learning post-training more efficient, FlexFloor supports faster development and iterative improvement of large language models and AI agents.

cs.AI · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.04093

Federated Concept-Based Models: Interpretable models with distributed supervision

Dario Fenoglio, Arianna Casanova, Francesco De Santis, Gabriele Dominici, Johannes Schneider, Pietro Barbiero, Giovanni De Felice, Marc Langheinrich 等 9 位作者

原文摘要

Concept-based Models (CMs) enhance interpretability in deep learning by grounding predictions in human-understandable concepts. However, concept annotations are costly and rarely available at scale within a single data source. Federated Learning (FL) could alleviate this limitation by enabling cross-institutional training over concept annotations distributed across multiple data owners. Yet, FL lacks interpretable modeling paradigms. Integrating CMs with FL is non-trivial: although FL supports heterogeneous and non-stationary client participation, it typically assumes a fixed shared architecture, whereas CMs may require architectural adaptation as the available concept set evolves. We propose Federated Concept-based Models (F-CMs), a new methodology for deploying CMs in evolving FL settings. F-CMs aggregate concept-level information across institutions and efficiently adapt the model architecture to changes in concept supervision while preserving privacy. Empirically, F-CMs maintain accuracy and intervention effectiveness comparable to training settings with full concept supervision, while outperforming on average non-adaptive federated baselines. Notably, F-CMs enable interpretable inference on concepts unavailable to a given institution, a key novelty over existing approaches.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.40902

FlapSim: A Composable MuJoCo Simulation Platform and Reduced-Order Aerodynamic Model Hierarchy for Flapping-Wing Robotics

Mingshan He

原文摘要

Flapping-wing simulation need to reconcile high-frequency wingbeat aerodynamics with the slower dynamics relevant to flight control and reinforcement learning. We present FlapSim, a modular open-source MuJoCo simulation platform that combines robot descriptions, wing geometry, and composable aerodynamic models in a deterministic simulation pipeline. Across $48$ held-out scenarios spanning frequency, gimbal, wind, frequency-step, gust, and cross-robot flat-plate regimes, we compare five reduced-order configurations operating at $1\,\text{ms}$ with a $50\,μ\text{s}$ quasi-steady blade-element reference. The built-in hover cycle-averaged baseline achieves a $67.51\times$ CPU speedup but only $0.6593$ mean wrench fidelity. Combining multirate $21$-substep clock synchronization, three-dimensional linear/quadratic inflow and gust coupling, analytical blade-element geometry scaling, and phase-locked $1f\text{--}6f$ harmonics raises mean fidelity to $0.9646$ at a $65.19\times$ speedup in a five-block model. A streamlined four-block model without explicit step-transient lag states achieves $0.9662$ fidelity at a $67.98\times$ speedup. Controlled ablations show that stroke harmonics are particularly important during frequency transitions, improving held-out frequency-step fidelity by $+0.3176$. Transfer-function analysis explains this effect: fixed-window cycle averaging retains harmonic contributions when the wingbeat frequency changes, so within-cycle reconstruction also improves the filtered wrench. These results characterize the accuracy--computation tradeoff of the aerodynamic hierarchy and identify timing, inflow, geometry, and harmonic representation as central considerations for reduced-order flapping-wing simulation. The source code are available at: https://mingshanhe.github.io/FlapSim/\href{https://mingshanhe.github.io/FlapSim/}.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.26617

MMAP: Multimodal Missing-Aware Pretraining for Longitudinal Alzheimer's Prediction

Fiona Kekwick, Matthew Baugh, Bernhard Kainz, Paul M. Matthews, Wenjia Bai

原文摘要

Clinical decision making heavily relies on predicting the disease progression trajectory by seeking to understand patient's health status which is characterised by multimodal medical data. AI holds great potential for learning useful representations from multimodal medical data to predict disease progression and aid clinical decision making. However, development of predictive AI models is constrained by missing modalities and incomplete tabular data frequently occurring in medical datasets. In addition, disease labels alone may only provide limited supervisory signals for learning representations from high-dimensional multimodal data. Here, we present MMAP, a novel Multimodal Missing-aware Alignment Pretraining method for learning image-tabular representations from incomplete data. An image encoder is pretrained with efficient sigmoid contrastive learning combined with generative reconstruction. A tabular encoder is built upon a tabular foundation model. A missing token generator enables the two encoders to take incomplete data as input, enabling the model to be robust against missing modalities, either with missing images or missing tabular data. We evaluate the clinical usefulness of the learnt multimodal representations on two challenging longitudinal clinical tasks for Alzheimer's disease: predicting disease stage conversion and predicting amyloid status. The proposed method outperforms strong multimodal and unimodal baselines.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06655

Beyond accuracy: what AI assurance needs to establish in public services

Louise Yorke

原文摘要

Public bodies increasingly rely on AI-produced evidence, including classifications, summaries and assessments. These outputs can inform policy decisions and service delivery, making their reliability a matter of public accountability. Establishing whether this evidence can be relied upon requires testing its outputs and examining how organisations decide whether those tests are sufficient. We combine technical evaluation with analysis of AI governance requirements, informed by measurement theory and management-based regulation. We compare eight GPT-4o configurations classifying 1,200 UK Prime Minister's Questions into 21 policy topics, against human-coded labels and across unchanged repeats. Accuracy ranges from 68.2% to 70.3%, yet 24.3% of questions receive different labels, with changes in topic shares and rankings. Configurations agree more with one another than with human coding: agreement does not guarantee correctness. Under the implemented score-extraction procedure, the proportion flagged for human review ranges from 0.9% to 41.0%. We analyse 37 UK and EU policy documents. Both sets expect testing and oversight, but reporting expectations do not consistently cover changing answers, shared errors, selective evaluation, substantive conclusions or review routing. Some UK guidance explicitly addresses stability. The UK sample emphasises public bodies checking their own use; the EU places substantial testing duties on providers while leaving them important choices about measures and acceptance thresholds. Without appropriate checks, evidence could misrepresent policy issues, redirect attention or resources, and leave errors undetected. Public policy should require organisations to justify reliance through checks beyond aggregate accuracy, clear responsibility, access to expertise and scrutiny of results.

cs.CY · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06654

Compounding Physical RSI: Turning Execution Failure into Inherited Capability

Yixuan Yang, Qiang Chen, Run Shao, Shuwei Dong, Wenhao Li, Yunpeng Wang, Wenhan Fang, Haomiao Wu 等 34 位作者

原文摘要

Generalist robot policies are trained on static offline datasets, yet physical manipulation unfolds sequentially across stages. Because a weakness in a downstream stage remains unobservable until the policy passes earlier ones, each resolved bottleneck exposes the next hidden failure mode. This staged structure calls for Recursive Self-Improvement (RSI), in which a policy iteratively executes, diagnoses failures, and updates itself. Moreover, because task completion behaves like a product of stage-level pass rates, recursive gains can multiply across generations. In physical environments, three bottlenecks obstruct compounding: terminal execution feedback rarely localizes the stage that caused a failure, failed trajectories do not supply the corrective action, and updating shared parameters can degrade previously mastered skills. We propose Compounding Physical RSI, a self-evolving policy framework that turns execution failures into heritable capability. First, automated capability-gap assessment traces failed rollouts to the task stage where progression breaks down and formulates a structured improvement objective. Second, conditioned on this objective, our remedy stage curates validated, stage-relevant experience and refines the policy via behavior-regularized offline reinforcement learning, without requiring costly online rollouts at each optimization step. Third, to safeguard existing skills, our retention stage constructs weight-space candidates between the inherited reference policy and the refined policy, evaluates them across the task suite, and promotes the best candidate as the reference state for the next generation. Evaluated across all 42 tasks of the RoboDojo-Sim benchmark, CSU-AI-07 ranks first on the leaderboard with a three-seed mean Overall Score of 26.15 and Success Rate of 20.70%, outperforming the next-best entry by 5.92 points and 5.82 percentage points.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06653

Detecting Silent Action-Interface Mismatch with Calibrated Relational World Models

Rui Zhu, Xurui Li, Haixu Tang

原文摘要

A robot action can satisfy shape and range constraints yet carry the wrong semantics: axes may be permuted, signs inverted, rotations rescaled, or gripper polarity reversed. We study learned state-action-effect relations as offline contracts for detecting these mismatches and ranking their likely fields. Clean held-out transitions calibrate alarms; a fixed inverse vocabulary supports closed-set localization. On ten LIBERO Spatial tasks comprising 432 source episodes, a capacity-controlled comparison at 2.5% empirical clean false-positive rate gives 46.1% recall for a ridge forward residual, 61.0% for a four-component joint Gaussian mixture, and 65.7% for the exact conditional of that same mixture. The joint score retains a 14.9 percentage-point advantage over ridge, while conditioning improves recall by a further 4.7 points. Joint scoring instead has higher localization: 95.8% versus 94.6%. These matched-rate comparisons are retrospective diagnostics, not deployment calibration guarantees. Earlier Object/Goal results broaden tasks within the LIBERO convention; DROID, all three HYDRA tasks, short temporal faults, small offsets, exact repair, and simulated mitigation fail their respective gates, while xArm contributes one task only. The evidence supports a bounded offline diagnostic and a detection-localization tradeoff, rather than joint-density superiority or cross-robot safety.

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06652

Dynamical State-Space Diffusion for Spatiotemporal Prediction

Woojun Lee, Hankyeol Kim, Pilsung Kang

原文摘要

Diffusion models for temporal prediction typically corrupt each future frame with independent noise, leaving temporal dependence entirely to the denoiser. We propose Dynamical State-Space Diffusion (DSSD), which learns the temporal structure of the corruption process itself. DSSD builds a temporal kernel from the damped oscillatory modes of a stable diagonal state-space model, whose learned decay rates and frequencies let the corruption capture multiple timescales and oscillatory correlations, while the denoiser architecture remains unchanged. Running this model on a finite clip, however, requires the state before the first frame, which is unobserved; starting from a zero state leaves the early frames with less noise than the diffusion schedule prescribes. We avoid this by using the Cholesky factor of the model's stationary covariance as the temporal operator. We prove that this operator is causal, exactly invertible, keeps each frame's noise variance equal to that of standard diffusion, and reduces to the identity at the clean end of the process, and that it is exactly the Kalman innovations form of the state-space model. The denoiser is trained to predict the temporally correlated noise, and sampling removes and reapplies the temporal mixing at each step. On scientific-field and robot-video datasets, DSSD outperforms diffusion baselines that share its denoiser, and the evolution of its learned modes during training shows that the temporal operator adapts to each dataset.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06649

SCRUB: Contact-Based Surface-Frame Estimation for Force-Motion Control with an Armless Quadruped

Sourav Selvaraj, Juan Pablo Espinosa Chessal, Mahdi Agheli

原文摘要

Wiping, sanding, and inspection robots press a sliding tool on a surface with controlled force. Controlling that force needs the surface normal, which is unknown on real-world, unmapped surfaces. Surface-normal estimators can help estimate the surface normal, but they either need a friction model or assume that the instantaneous tool velocity lies along the surface; however, walking violates this assumption. We propose SCRUB, a contact-based surface-frame estimator, which lets an armless quadruped slide a body-mounted tool along near-vertical surfaces in the absence of known, axis-aligned, or vision-predicted normals. SCRUB's predictive controller presses and slides the tool using a Kalman-filter estimate of the normal from two cues: 1) A force cue measures the estimate's tilt across the motion. If friction directly opposes the motion, the cue is zero exactly when that tilt is zero, for any friction coefficient. However, if the cue's sliding direction is wrong, friction appears as a false tilt. 2) A velocity cue measures tilt along the motion. Walking and pressing move the tool in and out. SCRUB therefore subtracts the commanded press rate from the tool velocity, averages the result over each gait cycle, and treats this mean as lying along the surface. On Unitree Go1 hardware at nominal speed and load, SCRUB completed every wall traverse and column orbit. No orbit completed with either cue removed, without gait averaging, or with a fixed normal.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.20590

Feed-Forward Multi-View Feature Coding for 3D Gaussian Splatting

Seungmi Choi, Ji-Hyoun Choi, Suhyun Jo, Tae-Gwon Park, Hui Yong Kim

原文摘要

Feed-forward 3D Gaussian Splatting (3DGS) methods enable efficient reconstruction of 3D scenes from sparse multi-view images in a single forward pass, without scene-specific optimization. However, existing feed-forward scene-coding pipelines follow a "generate-then-compress" framework, first generating a Gaussian representation and then encoding its geometry and appearance through separate coding paths, complicating codec design and limiting the exploitation of cross-attribute redundancy. We propose multi-view feature coding for Gaussian splatting (MFGS), an end-to-end feed-forward framework for scene coding. Instead of compressing an explicit Gaussian representation, MFGS extracts multi-view features from the input images and encodes them into a compact bitstream. Through end-to-end rate-distortion training, MFGS learns a compact latent representation of multi-view features that jointly represents geometry and appearance, enabling the receiver to predict Gaussian attributes from the decoded features. We further introduce importance-guided Gaussian selection to accommodate different rendering budgets, allowing the receiver to adjust the number of Gaussians used for rendering from the same bitstream. Across RE10K, ACID, and DL3DV, MFGS achieves 99.76-99.86% bitrate savings over the generate-then-compress pipeline, as measured by BD-rate, while reducing total GMACs by 52-55% and providing an approximately 12 times end-to-end speedup.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.27428

Learning Soft Robotic Dynamics with Active Exploration

Hehui Zheng, Bhavya Sukhija, Chenhao Li, Klemens Iten, Andreas Krause, Robert K. Katzschmann

原文摘要

Soft robots offer adaptability and safety in unstructured environments, yet their compliant, high-dimensional, and nonlinear dynamics make modeling for control difficult. Existing data-driven approaches often fail to generalize, constrained by narrowly focused task demonstrations or inefficient random exploration. We introduce an uncertainty-aware active exploration framework that autonomously learns task-agnostic and generalizable dynamics models of soft robotic systems. We evaluate this framework on three simulated platforms---a continuum arm, an articulated fish in fluid, and a musculoskeletal leg---and on a real-world pneumatically actuated continuum arm. Compared with random exploration and task-specific baseline, our method achieves higher modeling accuracy by actively collecting informative data. This improved model quality yields higher returns in zero-shot control on unseen tasks and robust performance under sensing noise, actuation delays, and material nonlinearities. These results demonstrate that uncertainty-driven active exploration enables data-efficient dynamics learning across soft robotic morphologies, supporting autonomous and adaptable control for compliant robots.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2508.19008

Computational Phenomenology of Borderline Personality Disorder: A Comparative Evaluation of LLM-Simulated Expert Personas and Human Clinical Experts

Marcin Moskalewicz, Anna Sterna, Karolina Drożdż, Kacper Dudzic, Marek Pokropski, Paula Flores

原文摘要

Building on a human-led thematic analysis of clinical life-story interviews (> 150,000 words) with inpatients with Borderline Personality Disorder, this study examines the capacity of large language models (OpenAI's GPT, Google's Gemini, and Anthropic's Claude) to support qualitative clinical analysis. The models' interpretative potential was evaluated using a mixed-methods approach. Study A involved blinded and non-blinded judges in phenomenology and clinical psychology. The experts assessed the validity of AI-generated content using semantic congruence, Jaccard coefficients, and multidimensional validity ratings, including credibility, coherence, the substantiveness of results, and grounding in qualitative data. In Study B, neural methods were used to embed human- and model-generated theme descriptions in a multidimensional vector space. This approach provided an objectified computational measure of the difference between human and model semantics and linguistic style. In Study C, complementary non-expert evaluations were conducted (N=115) to examine the influence of thematic verbosity on the perception of human authorship and content validity. Overall, the results of AI analysis showed a highly variable overlap (0-58%) with the human interpretation, while all models identified themes originally omitted by human researchers, proving their capacity to mitigate human bias. At the thematic level, external evaluators were unable to reliably distinguish human-authored themes from those generated by AI. In terms of content validity assessed against raw data by high-level experts in the blinded mode, the performance of Gemini 2.5 Pro was indistinguishable from that of humans. The comparison of semantic vector embeddings showed that its style was also the closest to humans.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2602.20207

Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis

Shrestha Datta, Hongfu Liu, Anshuman Chhabra

原文摘要

Knowledge editing in Large Language Models (LLMs) aims to update the model's prediction for a specific query to a desired target while preserving its behavior on all other inputs. This process typically involves two stages: identifying the layer to edit and performing the parameter update. Intuitively, different queries may localize knowledge at different depths of the model, resulting in different sample-wise editing performance for a fixed editing layer. In this work, we hypothesize the existence of fixed golden layers that can achieve near-optimal editing performance similar to sample-wise optimal layers. To validate this hypothesis, we provide empirical evidence by comparing golden layers against ground-truth sample-wise optimal layers. Furthermore, we show that golden layers can be reliably identified using a proxy dataset and generalize effectively to unseen test set queries across datasets. Finally, we propose a novel method, namely Layer Gradient Analysis (LGA) that estimates golden layers efficiently via gradient-attribution, avoiding extensive trial-and-error across multiple editing runs. Extensive experiments on several benchmark datasets demonstrate the effectiveness and robustness of our LGA approach across different LLM types and various knowledge editing methods.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06639

Replicability, Reproducibility, and Robustness in Political and Social Science Research with Large Language Models

Joan C. Timoneda, Sebastián Vallejo Vera

原文摘要

This chapter addresses the central reproducibility problem of research with large language models. LLM output is probabilistic and varies across models and versions, which can have significant effects on downstream statistical results. The chapter distinguishes between replicability, reproducibility, and robustness, and proposes a probabilistic standard based on the distribution of results, not identical outputs. It introduces a standardized prompt script, tests within-model variation for encoders and decoders, and develops error-structure analysis to diagnose where models err and whether their errors align. Using three datasets, the chapter shows that measurement choice can reverse the sign of downstream regression coefficients. Existing design-based corrections with gold-labeled subsamples restore validity, but come at the cost of estimate precision. The main contribution of the chapter is a stacked ensemble of open-weight models that improves precision in the correction step while retaining estimate validity.

cs.CL · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06637

Human Motion Prediction via Continual Prior Compensation

Jianwei Tang, Jian-Fang Hu, Tianming Liang, Xiaotong Lin, Jiangxin Sun, Wei-Shi Zheng, Jianhuang Lai

原文摘要

Human Motion Prediction (HMP) aims to predict future human poses at different moments according to observed past motion sequences. Previous approaches mainly treated the prediction of different temporal moments as a single prediction task and learned the predictions of varied moments simultaneously, which would encounter a main limitation: the learning of short-term predictions (referring to ``near-future'' prediction) could be hindered by the predictions of long-term (referring to ``far-future'' prediction) motions. In this paper, we develop a novel temporal continual learning framework called Continual Prior Compensation (CPC) to progressively train HMP models, in which we divide the prediction task of motions corresponding to varied temporal moments into several subtasks and train the model in a multi-stage manner. To mitigate the prior information forgetting in the progressive training, we further introduce a learnable random variable Prior Compensation Factor (PCF) to explicitly measure the prior knowledge loss. We theoretically show that the PCF can be efficiently learned together with the model parameters by minimizing a reasonable upper bound of the objective function. The proposed CPC is further enhanced to estimate the prior information loss for each subtask and a new framework called Continual Prior Compensation++ (CPC++) with Fine-Grained Prior Compensation Factor (FGPCF) is finally developed. Our CPC and CPC++ frameworks are quite flexible and can be easily integrated with different HMP backbone models and adapted to various datasets and applications. Extensive experiments on three HMP benchmark datasets using multiple SOTA HMP backbones (PGBIG, siMLPe, MotionMixer, and LTD) demonstrate the effectiveness and flexibility of our frameworks.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06635

Uncertainty-Driven Efficient Communication for UAV-Based Collaborative Perception

Jiuwu Hao, Yuting Wan, Liguo Sun, Zao Zhang, Yueyang Wu, Pin Lv

原文摘要

Unmanned aerial vehicle (UAV)-based collaborative perception enables multiple agents to share complementary perceptual information, overcoming limitations such as occlusion and limited sensing range. Communication efficiency is a critical bottleneck, as UAVs operate under stringent bandwidth and computational constraints. However, existing spatial selection methods focus predominantly on foreground regions to reduce missed detections, neglecting perceptually ambiguous regions and leaving false detections unresolved. We propose UCP, an uncertainty-driven framework that characterizes collaborative value through observational uncertainty, identifying sensor-limited regions, and discriminative uncertainty, capturing model-level ambiguity near the decision boundary. These estimates drive spatial request and supply maps for efficient inter-agent communication, and the received messages are aggregated via U-Fusion, an uncertainty-guided cross-attention module. Experiments on three benchmarks across 3D object detection and trajectory prediction demonstrate a superior performance-bandwidth trade-off with high interpretability and strong generalizability.

cs.CV

查看论文
arXiv ↗PDF ↗