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

+479新增论文
+361其中 AI 相关
+63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:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 14:21 — 2026-11-16 14:21(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:2026-11-16 13:44库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,921 有修订112 HF 社区发现

浏览论文库

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

找到 23,827 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)
版本更新 · v2arXiv:2610.37105

Text Generation in Low-Resource Languages Using Human-Curated Vocabularies

Michael Christlambert Sinanta, Muhammad Dehan Al Kautsar, Amanda Nurul Izzah, Thanh-Nhi Nguyen, Phan Phuong Mai Chau, Zheng Wei Lim, Fajri Koto

原文摘要

Synthetic text generation offers a promising approach to alleviating data scarcity in low-resource languages. However, its effectiveness is inherently limited for languages that are scarcely represented, or entirely absent, in an LLM's pretraining data. At the same time, many such languages have human-curated vocabularies that provide rich lexical and semantic information, often accompanied by grammatical information such as part-of-speech labels. In this work, we ask whether LLMs can leverage these resources to generate coherent text in extremely low-resource and unseen languages. We introduce a framework that combines human-curated vocabularies with a small number of human-written exemplars that provide syntactic signals, while sampling candidate words according to a Zipfian distribution. Across languages with varying levels of resource availability, we evaluate the generated text using lexical diversity, off-target ratio, and human judgments of fluency. Our results show that reasoning-enabled LLMs can generate fluent text even in extremely low-resource languages, with particularly strong results at the sentence level and promising performance at the paragraph level. Our findings highlight a practical pathway for bootstrapping synthetic data in low-resource languages, expanding the amount of usable text even when existing digital resources are extremely limited. Our source code is available at https://github.com/michaelsinanta/vocab2text.

cs.CL

版本更新 · v2arXiv:2608.23034

ST$^2$U: Stateful Test-Time Unlearning via Restricted Knowledge Boundary Control

Xunlei Chen, Qinghui Gong, Ruini Xue, Yaodong Hu, Tian Lan, Wenhong Tian

原文摘要

Controlling restricted knowledge in large language models is essential for model alignment and safe deployment. Test-time unlearning avoids costly retraining and parameter updates by intervening only during inference. However, existing activation-editing methods apply isolated pointwise corrections, overlooking how autoregressive generation continually reconstructs hidden states from the prompt, cache, and generated prefix. Consequently, later states may return to restricted knowledge regions after a locally successful correction, causing restricted knowledge re-entry. In this work, we propose Stateful Test-Time Unlearning via restricted knowledge boundary control (ST$^2$U), which formulates test-time unlearning as trajectory-wide boundary control. ST$^2$U first models restricted knowledge boundaries in low-dimensional invertible coordinates while leaving orthogonal non-target components unchanged. During inference, ST$^2$U monitors risk along the trajectory, applies minimal boundary corrections with contextual anchoring, and propagates historical correction states across tokens to mitigate knowledge re-entry. This trajectory-wide control enables more persistent forgetting while preserving non-target capabilities and limiting inference overhead. Across three benchmarks and three model families, ST$^2$U delivers the strongest overall balance, combining best or second-best retention with competitive forgetting and substantially less restricted knowledge re-entry than test-time baselines (13.76--19.84% versus 30.44--59.10%).

cs.LG · cs.CL

新论文 · v1arXiv:2611.14143

GARD: Gradient-Guided Adversarial Representation Defense against Backdoors in Multimodal Contrastive Learning Models

Yuhong Wang, Yujun Cai, Lei Feng, Songze Li

原文摘要

Multimodal contrastive learning models such as CLIP are vulnerable to backdoor attacks with diverse trigger structures, ranging from localized patches to globally distributed perturbations, with recent attacks increasingly optimizing these triggers in the representation space. Existing post-hoc defenses based on clean fine-tuning may leave backdoors active, while trigger-inversion methods depend on accurately estimating the attack target and trigger. We observe that backdoored encoders exhibit structure-dependent representation sensitivity: global perturbations preferentially expose distributed backdoors, whereas local patch perturbations are more effective for localized backdoors. Based on this observation, we propose Gradient-Guided Adversarial Representation Defense (GARD), a target- and trigger-agnostic post-hoc defense. GARD optimizes complementary global and local adversarial probes to maximally displace clean-image representations, and then realigns the perturbed representations with detached clean anchors while preserving image-text alignment. The resulting model requires no additional computation at inference time. Across six visual backdoor attacks and two CLIP visual backbones, GARD reduces the attack success rate below 1% in all 12 evaluated attack-backbone combinations while maintaining competitive clean accuracy. These results demonstrate the effectiveness of adversarial representation probing for repairing backdoored multimodal contrastive encoders.

cs.CR · cs.CV

新论文 · v1arXiv:2611.14141

Deviation-Aware Pretraining for Cardiovascular Disease Detection from Electrocardiograms

Siyuan Yan, Haibo Zheng, Feng Lu, Wei Li

原文摘要

Electrocardiogram (ECG) signals are critical for cardiovascular disease (CVD) detection. Most current deep learning models rely on supervised, task-specific training, which limits their ability to generalize across diseases, patient populations, and acquisition settings. This paper presents a self-supervised ECG feature extraction framework that learns from nearly one million unlabeled 12-lead ECG recordings. The framework includes two modules: Deviation Localization Embedding (DLE), which detects waveform-level deviations from normal patterns, and Association Reconstruction Embedding (ARE), which models cross-lead associations through deviation-guided reconstruction to capture abnormal patterns expressed across multiple leads. These modules enable the framework to capture subtle deviation-related patterns and their cross-lead context. The framework achieves up to 6.5% AUROC and 12.8% F1 improvements over prior methods on multiple public datasets, even without additional fine-tuning the pretrained feature extractor. Embedding visualizations show that the learned features support meaningful disease grouping and anomaly identification. The approach reduces the need for labeled data and can support clinicians in diverse healthcare settings. The framework has potential to improve early detection and monitoring of cardiovascular diseases, contributing to more accessible and equitable heart care.

cs.LG

版本更新 · v2arXiv:2605.19557

Density-Ratio Losses for Post-Hoc Learning to Defer

Alexander Soen, Ragnar Thobaben, Joakim Jaldén, Richard Nock

原文摘要

We study post-hoc Learning to Defer (L2D) through the lens of ideal distributions: divergence-regularized reweightings of the data distribution under which a model attains low task loss. We define deferral via the density-ratio between a model's and an expert's ideals. Using the reduction from density-ratio estimation to class-probability estimation, we derive the DR CPE losses for post-hoc L2D scorers. Deferral decisions are then made by thresholding the scorer. For KL-based ideal distributions, our deferral rule recovers Chow's rule under the original distribution and a connection to an expert-tilted Bayes posterior---which incorporates the expert's performance---depending on if the ideal distributions are marginal or joint distributions. This leads to two variants of the DR CPE losses, with the joint variant being computationally convenient in practice. We establish consistency properties of the joint DR CPE losses when considering the zero-one task loss and strongly proper composite CPE losses. Experimentally, our approach is competitive compared to common baselines and is more robust across dataset settings. More broadly, our results cast post-hoc L2D as density-ratio estimation between ideal distributions, bridging Chow-style rules, expert comparison, and elucidating connections to related learning settings including anomaly detection.

stat.ML · cs.LG

版本更新 · v2arXiv:2608.04971

Exploring Cross-Reality Transitions between Projections and Head-Mounted Displays for Immersive Digital Art

Xiangpeng Fu, Mads Haahr

原文摘要

Immersive exhibitions increasingly combine large-scale projections with mixed reality (MR) head-mounted displays (HMDs), but how users perceive transitions across these heterogeneous visualization environments remains underexplored. We investigate cross-reality (CR) object- and scene-level transitions in a hybrid immersive art installation spanning projection, augmented reality (AR), and virtual reality (VR). In a within-subjects study (N=24), we compared a calibrated condition with a bundled inconsistency condition introducing noticeable differences in spatial alignment, visual appearance, and cross-device latency. This contrast was used not to establish perceptual thresholds or hardware targets, but as a diagnostic probe to make transition disruptions more perceptible and discussable. The inconsistency condition reduced presence and increased workload. Interviews showed that spatial misalignment disrupted action-outcome predictability, appearance mismatch reduced aesthetic coherence, and latency weakened perceived responsiveness. Effects also varied by asset type: rigid static assets exposed inconsistencies more clearly, animated skeletal assets shifted attention toward motion, and particle effects often masked small discrepancies. These findings clarify how users perceive projection-MR transitions and support asset-aware design strategies for coherent hybrid immersive art. We also release HUICRSync, an open-source Unreal Engine plugin for prototyping projection-MR CR experiences.

cs.HC · cs.GR

新论文 · v1arXiv:2611.14136

HaiRuo: Forecasting Ocean Eddies as Fields and Objects with a Satellite-Altimetry Foundation Model

Xukun Qin, Haochen Sun, Yuyang Tian, Ge Chen

原文摘要

Mesoscale eddies carry most of the ocean's kinetic energy and move heat, salt and nutrients across basins, yet where an eddy will be two weeks ahead is still read off ocean models with post-hoc tracking heuristics. We introduce HaiRuo, which forecasts eddies as fields and as objects at once: from 30 days of satellite sea-level maps, one forward pass returns 15 days of sea level and geostrophic velocity, daily eddy masks and the trajectory of every eddy alive today. HaiRuo pairs two components with a clear division of labour: (1) HaiRuo-1B, an open-weight 1.05-billion-parameter foundation model pretrained without labels on 24 years of global satellite-altimetry observations, which supplies the 15-day physical fields and masks (+0.14 field skill and +1.1 mIoU points under the same decoder) and further lowers 15-day centre error by 1.2 km frozen (1.35 km over training from scratch); and (2) XuanJi, a Lagrangian object decoder that samples the evolving forecast in each eddy's co-moving polar frame and refines the 15-day path across three look-ahead rounds, removing 2.5 km on HaiRuo-1B (2.9 km with joint fine-tuning) and 2.5-3.3 km via its object attention across six published backbones. Under one pre-registered global evaluation over the whole ocean, HaiRuo improves on fourteen methods on every endpoint (25.2 vs. 30.6 km 15-day centre error, -18%), holding its margin outside the labelled regions and through both phases of the El Nino-Southern Oscillation (ENSO), while reproducing westward drift, 50-60 deg S eastward reversal and poleward cyclone-anticyclone deflection. Over ten days through one fixed tracker, HaiRuo's forecast field cuts the eddy-centre error of WenHai and XiHe by 37-43% (-2.8 km vs. day 0 while they degrade +4.3-8.7 km), and its object trajectories cut pipeline error by 77-78% globally. Open-weight checkpoints, code and project page: https://github.com/xkqin/HaiRuo

cs.LG · cs.CV

新论文 · v1arXiv:2611.14135

Sim(3)-TurboReg: Robust and Efficient Scale-Aware Registration via Tri-Scale Consistency

Zijun Zhou, Shaocheng Yan, Zhenjun Zhao, Yutong Hu, Ke Yang, Yingdong Gu, Pengcheng Shi, Jiayuan Li

原文摘要

Feed-forward 3D foundation models recover geometry at high fidelity, yet inference memory constraints keep them from processing long sequences natively. Current streaming systems work around this limit with sliding-window chunking, which introduces severe monocular scale ambiguity. Resolving this ambiguity requires Sim(3) registration that stays accurate and efficient under outlier contamination. We introduce Sim(3)-TurboReg, which reformulates the compatibility graph construction of TurboReg by replacing absolute distance constraints with a strict Tri-Scale Consistency (TSC) criterion. Our analysis shows that TSC suppresses both mismatching and coordinate-distortion outliers. We integrate the resulting solver into existing streaming systems and obtain high-fidelity, kilometer-scale reconstruction for feed-forward models. On controlled unknown-scale registration at 90% outliers, ours matches RANSAC accuracy with 92.5% lower median latency. In DA3-Streaming on KITTI, ours improves mean ATE RMSE by 22.2% and reduces mean end-to-end time by 16.6%. Code: https://github.com/ivan-zzj/Sim3-TurboReg

cs.CV

新论文 · v1arXiv:2611.14134

Right for the Wrong Reasons? Evaluating Plausibility and Behavioral Change in Explanation-Guided Learning

David Dembinsky, Adriano Lucieri, Andreas Dengel

原文摘要

Explanation-Guided Learning (EGL) promises models that are not only accurate but also rely on task-relevant evidence. However, whether improved agreement between model explanations and human-provided rationales also implies a changed decision strategy remains unclear. We study this tension under controlled synthetic shortcut introduction using a constructed shortcut dataset. Inspired by real-world applications, our benchmark covers shortcuts of different kinds, including localized, background-based, and global cues. This allows us to evaluate whether different EGL objectives produce behavioral changesand explanatory changes. Across these axes, we find that the effects of EGL are strongly objective-specific. Rationale-based data augmentation provides the clearest robustness gains when shortcut evidence can be separated from task-relevant foreground information, reaching average accuracy improvements of up to +4.8 percentage points (pp) together with increased foreground reliance. Attribution-constraining objectives primarily improve explanation plausibility, increasing Importance Mass by up to +14 pp on average, but provide weaker and less consistent behavioral correction, with average accuracy gains of at most +1.6 pp. Moreover, neither improved robustness nor improved plausibility reliably implies higher perturbation-based fidelity. Overall, our results show that EGL can be useful, but its success cannot be inferred from rationale agreement alone and should instead be evaluated along complementary behavioral and explanation-level axes. We publicly release all experimental results to enable further analysis (https://right-for-wrong-reasons.dfki.de/).

cs.LG

新论文 · v1arXiv:2611.14129

Continuous 3D Spatial Transcriptomics Reconstruction via Histology-Informed Implicit Neural Representations

Kaito Shiku, Ryoma Bise, Ahtisham Fazeel Abbasi, Yuichiro Iwashita, Shumpei Takezaki, Andreas Dengel, Muhammad Nabeel Asim

原文摘要

Three-dimensional spatial transcriptomics (3D ST) enables the analysis of gene-expression patterns across tissue depths. However, 3D ST measurements are acquired from discrete 2D tissue sections, which are often sparsely sampled due to high acquisition costs. To address this limitation, we propose a histology-informed multi-task implicit neural representation (HIM-INR) for continuous 3D gene-expression reconstruction from sparse ST observations. HIM-INR jointly reconstructs gene-expression profiles and histological representations using an INR with a shared backbone, leveraging densely sampled histological images as auxiliary spatial supervision. Once trained, HIM-INR predicts gene expression at arbitrary 3D coordinates without requiring histological images. Experiments on two 3D ST datasets demonstrate improved reconstruction over existing methods, particularly as the number of missing ST sections increases.

cs.CV · cs.LG

版本更新 · v4arXiv:2607.02137

Adaptive Reparametrized Time for Score-Based Diffusion Sampling

Yilie Huang, Wenpin Tang, Xun Yu Zhou

原文摘要

We study timestep allocation for score-based diffusion sampling, where a learned reverse-time dynamics is discretized on a finite grid. Uniform and hand-crafted schedules are standard choices, but they rely on fixed prescriptions and can therefore be suboptimal. To address this limitation, we propose Adaptive Reparameterized Time (ART), a continuous-time control formulation that learns a time change by treating the speed of the sampling clock as the control, so that a uniform grid on the learned clock induces adaptive timesteps in the original diffusion time. Based on a leading-order Euler error surrogate, ART provides a principled objective for allocating timesteps along the sampling trajectory. To solve this deterministic control problem, we introduce ART-RL, an auxiliary randomized formulation with Gaussian policies that turns schedule learning into a continuous-time reinforcement learning problem. We prove that the randomized ART-RL formulation is equivalent to ART at the optimizer level, in the sense that its optimal Gaussian policy recovers the optimal ART time-warping rate through its mean. We further establish policy evaluation and policy improvement characterizations and derive trajectory-based moment identities that yield implementable actor--critic updates for learning the schedule. Across experiments ranging from controlled low-dimensional settings to image generation, ART-RL can be plugged into existing diffusion samplers by changing only the timestep grid, consistently improving sample quality over strong baseline schedules at matched budgets while leaving the rest of the sampling pipeline unchanged. The learned schedules also exhibit broad generalization, transferring without retraining across sampling budgets, datasets, solvers, pipelines, and representation spaces.

cs.LG · cs.AI · eess.SY · math.OC

新论文 · v1arXiv:2611.14126

Hierarchical Graph Representation Learning with Pooling-Induced Substructures

Luca Sbicego, Xiaowen Dong, Dorina Thanou

原文摘要

Hierarchical graph-level tasks that require reasoning over substructures that extend beyond local neighborhoods are posing challenges for standard Graph Neural Networks (GNNs). While graph pooling aims to address this by coarsening graphs into hierarchical representations, existing methods often fail to explicitly preserve the substructures they induce, leading to inconsistent empirical performance. Moreover, evaluating such approaches remains challenging due to the lack of benchmarks with explicit hierarchical structure. We propose Pooled-Substructure-Aware GNNs, an approach to graph pooling that explicitly preserves and processes substructures uncovered by structure-based pooling schemes. We show that this design enhances the expressive power of pooling-based GNNs in the sense of the Weisfeiler-Lehman (WL) test. To enable principled evaluation, we introduce two new synthetic datasets with controllable hierarchical structure and propose a metric to characterize the prevalence of hierarchical patterns in real-world graph-level benchmarks. On tasks with relevant hierarchical structure, our approach outperforms matched pooling baselines, while remaining competitive on structurally simpler benchmarks. Code and datasets are publicly available at https://github.com/lsbicego/PSA-GNN/.

cs.LG

版本更新 · v2arXiv:2611.02536

FORGE: Fault-Oriented Rework Code Generation for Executable Interlocking Assembly

Fuqiang Wang, Jiahao Fu, Ren Hefeng, Yining Qian, Chuanting Zhang, Cheng Tan, Yuwen Liu, Jingxuan Wei

原文摘要

Large language models have demonstrated strong capabilities in structured reasoning and code generation, yet identifying an assembly fault does not guarantee the ability to generate executable rework programs. In interlocking assemblies, a locally plausible repair program may violate blocking dependencies, omit required recovery operations, or terminate in an incorrect configuration. We identify this challenge as fault-conditioned executable rework generation, where models must jointly reason about structural failures and generate programs that restore constrained assembly states. To benchmark this capability, we introduce FORGE-Bench, containing 4,000 tasks across 26 interlocking assemblies with five assemblies held out for evaluating generalization to unseen structures. We further propose FORGE (Fault-Oriented Rework Code Generation for Executable Interlocking Assembly), a structured state-to-program framework that decomposes rework generation into Rework Structuring and Action Grounding. Rework Structuring captures fault-induced recovery dependencies, while Action Grounding maps these dependencies into state-conditioned executable actions. Experiments show that locally reasonable repair code is insufficient for reliable assembly recovery, and that connecting structural recovery reasoning with executable action realization is essential for verified target restoration.

cs.AI

新论文 · v1arXiv:2611.14124

CroCoMAE: Cross-modal self-supervised collaborative representation learning for SAR-optical remote sensing data

Vito Recchia, Giuseppe Guarino, Cássio Fraga Dantas, Giuseppina Andresini, Annalisa Appice, Dino Ienco

原文摘要

Remote sensing increasingly captures the Earth's surface through complementary sensors such as SAR and optical, yet ground-truth annotations remain scarce, limiting supervised approaches. Self-supervised learning (SSL) addresses the label scarcity, and cross-modal SSL further exploits the complementarity between co-located sensors, but existing cross-modal frameworks align modalities mostly through global image-level representations or treat them as largely redundant, leaving their fine-grained complementary structure underexploited. We propose CroCoMAE, a cross-modal SSL framework for SAR-optical remote sensing that unifies contrastive learning and masked image modeling within a ViT-based architecture, operating at two complementary levels. At the image level, an intra-modality contrastive loss on the class token yields globally discriminative, augmentation-invariant representations. At the patch level, masked image modeling drives fine-grained per-modality representations, while a cross-modal contrastive objective aligns a shared subspace across SAR and optical patch tokens, leaving the complementary subspace unconstrained to retain modality-specific information. On two SAR-optical benchmarks covering scene classification and semantic segmentation, CroCoMAE improves over uni-modal SSL baselines and outperforms state-of-the-art cross-modal frameworks in most configurations, with gains in both single-modality and multi-modal evaluation across varying label regimes and the largest improvements on semantic segmentation.

cs.CV · cs.LG

新论文 · v1arXiv:2611.14122

Hx2Dx: From Anamnesis to Diagnosis - A Multimodal Arena for Conversational Clinical Reasoning in LLMs

Federico Ravenda, Mirko Cesarini, Daniele Montagnani, Volodymyr Karpenko, Antonietta Mira, Andrea Raballo

原文摘要

Large language models (LLMs) achieve expert-level diagnostic accuracy in static evaluations, where the model receives a curated vignette or case report that already condenses the diagnostically relevant findings. Such evaluations measure inference over already selected evidence; the evaluations do not account for the inquiry used to obtain it. In clinical practice, however, diagnosis is an iterative process of inquiry. Clinicians take the patient's history, or anamnesis (Hx), through targeted questioning, examine the patient, and request and interpret tests, progressively narrowing the differential until they reach a final diagnosis (Dx). We introduce Hx2Dx ARENA, an interactive benchmark of 1'000 clinical cases from the New England Journal of Medicine (NEJM). Each case is a simulated encounter that proceeds from initial presentation through history taking and physical examination to diagnostic workup. We evaluate open- and closed-source LLMs under multiple configurations. Performance varies considerably across models in the interactive setting, and every model loses diagnostic accuracy relative to the static setting, where the full case is presented upfront. The ability to ask the right questions accounts for much of both the gap between models and the loss of accuracy: diagnosis improves as questions become more targeted and build a more complete clinical picture. LLMs thus reason well once the relevant data are available but remain limited in hypothesis-driven information gathering, in knowing what to ask in order to know. Closing this gap is a prerequisite for their safe integration into real-world diagnostic workflows.

cs.AI

新论文 · v1arXiv:2611.14121

Criticality-Aware RAN Function Placement for Robust 6G Networks

Gabriel M. Almeida, Joao F. Santos, Walid Saad, Nicola Marchetti, Kleber V. Cardoso

原文摘要

The disaggregation of base stations into radio access network (RAN) functions introduces new vulnerabilities to mobile networks, as disruptions in cloud locations can interrupt multiple RAN functions and trigger cascading failures, leading to widespread outages. In this paper, we propose a criticality-aware RAN function placement solution to improve the robustness of disaggregated mobile networks against random failures and targeted attacks. Our solution optimizes the placement of centralized units (CUs) and distributed units (DUs) across cloud locations to reduce functional dependencies and limit the criticality of cloud locations, while preserving the cost benefits of RAN function centralization. We formulate the placement as an optimization model that jointly minimizes functional dependency and placement cost, subject to criticality constraints, as well as computing and transport requirements. We numerically evaluated our approach on a real-world mobile network topology across multiple disruption scenarios and demonstrated that our solution improves robustness, yielding up to 75% more operational radio units (RUs) after disruptions than existing approaches.

cs.NI

版本更新 · v4arXiv:2604.18216

EFX Need Not Exist

Hannaneh Akrami, Simon Mackenzie, Alexander Mayorov, Kurt Mehlhorn, Shreyas Srinivas, Mashbat Suzuki, Christoph Weidenbach

原文摘要

The existence of envy-free up to any good (EFX) allocations has long been a central open problem in discrete fair division. We resolve it in the negative by constructing a counterexample with three agents and eight goods. The instance is invariant under every simultaneous permutation of the agents and their associated good types, and this symmetry yields a short, self-contained proof of nonexistence. The counterexample can be realized with weighted-coverage, and hence submodular, valuations, and it extends to $n$ agents and $m$ goods for all $n\ge3$ and $m\ge n+5$. For three agents, eight goods is the minimum: every instance with three agents and at most seven goods admits an EFX allocation under arbitrary monotone valuations. The proof relies on a new analysis, valid for any number of goods, of when the invariant-based technique of [AACGMM25] produces an EFX allocation. This analysis strictly extends the class of MMS-feasible valuations. We also give explicit bounds for approximate EFX. For subadditive valuations, $α$-EFX allocations need not exist for any $α>2^{-1/6}\approx0.891$, and for submodular valuations for any $α>0.958$. On the positive side, if two of three agents have arbitrary monotone valuations and the third has a subadditive valuation, there is always an allocation that is EFX for the first two and $2^{-1/3}$-EFX ($\approx0.794$) for the third. A first version of the counterexample and of the seven-goods result was obtained using SAT/SMT solving, and the insights it provided guided our classical, pen-and-paper proofs. We also describe the encoding, which we believe is a valuable tool in its own right: to our knowledge, this is the first use of SAT/SMT solving for EFX.

cs.GT · cs.DS

新论文 · v1arXiv:2611.14118

TAMEing the Open-World Personalization: Towards Open-Set Personalized MLLM Assistant

Rongpei Hong, Jian Lang, Ting Zhong, Fan Zhou

原文摘要

Personalizing Multimodal Large Language Models (MLLMs) as intelligent assistants has recently emerged as an active research topic, where an MLLM is expected to go beyond generic, one-size-fits-all replies, and instead generate responses grounded in user-specific objects, entities, and concepts encountered during interactions. Nevertheless, existing studies mainly focus on personalizing MLLMs on a static, predefined set of personalized concepts and require users to manually and frequently extend this set to accommodate newly emerging concepts, which is infeasible in dynamic-world scenarios. To address this limitation, we recast conventional MLLM personalization as an Open-Set problem, and propose TAME-O, the first long-context open-set personalized MLLM assistant. Specifically, TAME-O introduces a training-free, plug-and-play Concept Reconciliation Skill (CR Skill). It enables the assistant to automatically unlock novel concepts during prolonged human-MLLM interactions while preventing confusion with previously unlocked ones, allowing the MLLM to continually grasp more and more concepts and progressively refine the modeling of known ones. Extensive experiments under the open-set personalization setting underscore the efficacy of our method.

cs.CV

新论文 · v1arXiv:2611.14116

Visual Similarity in Adult Word Extension and Artificial Word Learning

Patricio M. Vera

原文摘要

When two objects share a name, how much does their visual similarity explain, and what do the teaching examples add? First, we reanalyzed trial-level data from a large adult word-extension study (Lewis & Frank, 2018), computing each test image's distance to the examples shown in the space of a frozen self-supervised visual encoder (DINOv2). Distance was associated with extension (log odds -3.23 per standard deviation; 520 people), and an exploratory post hoc analysis suggested that this association persisted within the taught domain after controlling for taxonomic level and teaching condition. Example composition also mattered: after three examples, adults extended a word to 1.1% of superordinate items when the examples were subordinate and to 77.5% when they were superordinate. Second, in an artificial learner using the same encoder, words joining two categories were learned less accurately the farther apart the categories were (84.7%, 65.4%, and 53.0% naming accuracy for near, mid, and far pairs). The encoder's distances correlated with human similarity and confusability measures from three datasets (rho = .501-.795), but this representational alignment did not translate into conclusive evidence that human-derived distances predict learner difficulty, and a second encoder trained on one child's experience reproduced the tier ordering but not the pair-level effect. The secondary human data were analyzed under an internal plan fixed before the confirmatory analyses (not externally preregistered). Visual similarity accounts for part of how generalization is organized in both systems, while the composition of examples contributes what the distance we used does not capture.

cs.CL · cs.AI · cs.CV

新论文 · v1arXiv:2611.14115

LEASH: Stay Safe in Agentic Robotics

Qinfeng Zhu, Weiguang Zhao, Ke Sun, Xihao Guo, Yunxi Jiang, Rui Zhang, Lei Fan, Kaizhu Huang

原文摘要

Foundation models such as GPT and Claude have shown strong capabilities in spatial understanding and embodied intelligence. These advances make agentic robotics a promising path toward artificial general intelligence in robotics. However, we find that using foundation models to control robots poses serious safety risks, and comprehensive safety evaluation is still lacking. We introduce RoboRisk, a comprehensive benchmark for evaluating safety in agentic robotics. Its 92 simulated tasks and 13 physical-robot tasks fall into five categories: Task-level Refusal (T), Plan Repair (P), Execution-time Hazard (E), Injection (I), and Sequential Memory (S). Prior benchmarks cover at most two of these categories, and several evaluate only text outputs. In contrast, RoboRisk covers all five and executes every task in closed loop. We evaluate six state-of-the-art foundation models on RoboRisk: GPT-6 Astra, GPT-6.1 Sol, GPT-6 Luna, Claude Opus 5.5, Gemini 4 Argon, and Grok 4.7. These models generally show high harm rates. We also evaluate two robot-specific APIs: the Dream API and PokeBot's RoboAPI. We further propose the Lease-Enforced Agentic Safety Harness (LEASH), which offers essential safety infrastructure for agentic robotics and can be integrated into nearly any agentic architecture. LEASH leverages a decision model (Jev or OpenAI's Decisions API) to implement task, action, and commit gates, which review the task, each action, and each irreversible operation in their visual context. The planner and all three gates share a common safety policy. Experiments on RoboRisk in simulation and on physical robots show that LEASH effectively reduces harm across all six foundation models. It largely preserves their task completion performance and adds little time and token overhead.

cs.RO

新论文 · v1arXiv:2611.14113

Looking One Step Ahead: An Anticipation-guided Agent for Object State Readout in Videos

Yuanhe Tian, Yan Song

原文摘要

Understanding the progress of an activity requires tracking how the objects involved change over time. Object state readout provides this information by describing a target object's states and transitions across video frames. Although multimodal large language models (MLLMs) generate detailed visual descriptions, these descriptions may leave the attributes needed to distinguish successive states insufficiently specified. In this paper, we propose look-ahead state readout (LASER), an anticipation-guided agent for object state readout that uses possible next-step changes to determine which attributes to inspect in the present. Given temporally ordered frames and a target object, LASER converts anticipated changes into targeted visual questions and inspects the current frame to establish attribute values. It then checks state readouts and forecasts against independent observations of subsequent frames, refining a state record used to generate the final description. Reusable textual observation skills guide this process and are refined by tracing discrepancies with reference captions to the responsible instructions. Candidate revisions are selected on separate videos based on improved caption quality without increased contradictions with reference facts. Model parameters remain frozen throughout adaptation and inference, and the revised skills remain fixed during evaluation. Experiment results and further analysis on OSCaR and PLM RCap show consistent improvements of LASER over strong baselines and existing approaches, which demonstrates the effectiveness of our approach.

cs.CV · cs.AI

版本更新 · v2arXiv:2507.22953

CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography

Murong Xu, Fernando Navarro, Maksym Fritsak, Ibrahim Ethem Hamamci, Suprosanna Shit, Bastian Wittmann, Sezgin Er, Sebastian M. Christ 等 33 位作者

原文摘要

Volumetric computed tomography (CT) segmentation supports quantitative image analysis, but most AI-based methods remain organ-specific, with fragmented models, inconsistent label definitions, and heterogeneous training and evaluation protocols. Here we present CADS, a unified data-model framework for scalable and generalizable whole-body CT segmentation. We construct a SNOMED-CT-referenced anatomical label space harmonizing heterogeneous cohorts from over 100 imaging centers, yielding complete annotations of 167 structures across 22,022 CT volumes and markedly expanding anatomical coverage and scale beyond existing resources. To complete labels on sparsely annotated CTs, we combine self-training with shape-informed quality control based on neural implicit functions, curating high-quality pseudo-labels. Trained on this resource, CADS shows robust whole-body segmentation across distribution shifts and improved performance relative to state-of-the-art approaches across 18 public datasets. We further validate it in an independent, expert-reviewed real-world oncology cohort of 2,864 CTs. The curated dataset, pretrained models, and user-friendly software together provide an accessible, reproducible foundation for large-scale anatomical segmentation and computational anatomy research.

eess.IV · cs.CV

新论文 · v1arXiv:2611.14111

Model-Free Runtime Measurement of Task-Relevant Information

Dimitris Panagopoulos, Adolfo Perrusquía, Yang Xing, Weisi Guo

原文摘要

Autonomous systems increasingly monitor physical kinematics, environmental states and task completion outcomes. While existing work provides methods to plan information seeking actions and interpret acquired observations, current approaches do not monitor whether the live process of information gathering is functioning properly. Consequently, such systems can remain operationally active without resolving outstanding mission requirements. To address this limitation, we introduce Acquisition-State Telemetry (AST), a model free architecture that evaluates ongoing information acquisition from observable evidence relative to declared task requirements. Specifically, a domain interface maps raw observations into task resolution coordinates and normalized comparative representations, which are processed by a fixed causal monitor. This monitor emits two continuous real time signals that quantify (i) prospective progress across unresolved requirements and (ii) informational friction generated when recurrent evidence yields negligible informational gain. We evaluated a single, unadjusted monitor configuration across eight diverse domains including search and rescue dialogue, spatial grid exploration, hierarchical capability acquisition, continuous robotic manipulation, and probabilistic intent estimation. We show that across these domains the friction channel distinguished unproductive stagnation from purposeful exploration prior to task completion, while remaining muted during post completion activity. Furthermore, in closed loop reinforcement learning experiments under early termination constraints, we demonstrate that penalizing informational friction allowed agents to sustain high mission success, whereas unpenalized policies and baselines with matched operational costs failed to complete required tasks.

cs.RO · cs.AI

版本更新 · v3arXiv:2604.12497

Allocating Human Oversight in AI-Enabled Analytics

Zikun Ye, Jiameng Lyu, Rui Tao

原文摘要

Artificial intelligence provides low-cost predictions for many analytics tasks, but their reliability and the value of another human label vary across tasks. We study how to allocate a shared human-validation budget when task-level uncertainty is unknown and each acquired label informs both estimation and subsequent allocation. For known difficulty levels, the benchmark follows a cost-adjusted Neyman rule that accounts for task importance and label cost. Within our Tuned Rectification-Difficulty framework, we develop an upper-confidence-bound policy that jointly learns the correction coefficients of tuned prediction-powered inference and the resulting difficulties from paired human labels and predictions, and establish an allocation-regret guarantee for the confidence-radius policy. In synthetic experiments and a real digital-twin survey with 68 tasks and over 2,000 respondents, our method closes most of the gap to the oracle on the allocation objective. It matches the estimation error of uniform allocation with up to 22.7% and 4.5% fewer human labels, respectively. The same allocation structure extends beyond scalar means to vector-valued decision models, including regression and choice/conjoint estimation, by replacing the scalar residual variance with a scalarized sandwich covariance. The value of AI depends not only on model accuracy but also on the operational policy that targets human oversight where it matters most.

cs.LG · stat.ML

新论文 · v1arXiv:2611.14106

ProofCoder: Continuous Reasoning for Automated Software Verification

Martim Afonso, Inês Lynce, Maurizio Morisio, João F. Ferreira

原文摘要

Formal verification using proof assistants provides strong correctness guarantees for software, but constructing proofs remains labor-intensive and requires significant expertise. Recent approaches based on large language models (LLMs) have shown promise in automating proof synthesis. However, these approaches typically constrain the model to a rigid tactic-generation loop, in which the surrounding system controls premise retrieval, proof-state management, and backtracking. We introduce ProofCoder, an agentic proof-synthesis system for Rocq that approaches theorem proving from a coding-agent perspective. Rather than generating tactics within a fixed loop, ProofCoder reasons continuously throughout proof search and uses proof-assistant feedback to decide when to gather additional information, inspect proof states, revise previously generated proof fragments, or backtrack to an earlier point in the proof. This allows it to iteratively construct, repair, and refine proofs, at either tactic-level or whole-proof granularity. We evaluate ProofCoder on 280 challenging verification tasks from the AutoRocq Benchmark. On the best-performing configurations, ProofCoder increases proof success from 47% to 60% over the state-of-theart AutoRocq system, corresponding to a 27.7% relative improvement at approximately half the cost. Our ablations identify continuous reasoning as a key design choice: without it, the agent solves fewer lemmas at substantially higher cost, backtracks four to six times more often, and more frequently discards its own revisions. Whole-proof and tactic-level generation achieve similar success rates but follow distinct search and repair strategies. These results suggest that effective automated software verification requires more than improved tactic selection: continuous reasoning and feedback-guided proof revision are critical ingredients for robust proof synthesis.

cs.SE · cs.AI

新论文 · v1arXiv:2611.14102

Mobility-Aware Task Offloading in Mobile Edge Computing-Empowered Space-Air-Ground Integrated Internet-of-Things Networks

Minghao Sun, Jinghuai Xiong, Xiaoli Chu, Zitian Zhang

原文摘要

Mobile edge computing (MEC)-empowered spaceair-ground integrated Internet-of-Things (IoT) networks (SAGIINs) provide a promising solution for computation-intensive tasks generated by mobile IoT devices (IDs). However, task offloading in SAGIINs is challenging due to time-varying IDto-unmanned aerial vehicle (UAV) channels, intermittent LEO satellite service availability, and the coupling among UAV trajectory, communication, computation, and energy decisions. This paper investigates an energy-efficient task offloading and UAV trajectory planning problem in an MEC-empowered SAGIIN, where one UAV acts as both an aerial relay and an MEC server, and multiple LEO satellites provide supplementary computing resources. The UAV trajectory planning, task splitting, and computing resource allocation are jointly optimized to minimize the total system energy consumption under task completion, communication, computation, flight region, and satellite service window constraints. The resulting non-convex problem is decomposed into a UAV trajectory planning subproblem and a task splitting and computing resource allocation subproblem. To solve the former, a retrieval-augmented generation (RAG)-assisted large language model (LLM)-enhanced deep deterministic policy gradient (DDPG) algorithm, termed RLD, is proposed. The latter is shown to be convex and can be solved by using CVXPY for a given UAV trajectory. A weighted retrieval score is further designed to balance ID mobility-pattern similarity and historical UAV trajectory energy performance. Simulation results show that RLD completes all computational tasks in previously unseen test scenarios while consuming less total energy than the benchmark algorithms.

cs.NI

新论文 · v1arXiv:2611.14100

Sckwoky at SHROOM-Visions: Character-Level Hallucination-Span Detection in Image-Conditioned VLMs via Dual-Prompted LoRA Decoders

Mikhail Kulakov, Ruslan Solikhov, Ivan Bondarenko

原文摘要

We present our system for the SHROOM-visions 2026 shared task on character-level hallucination span detection in image-conditioned vision-language model (VLM) responses, evaluated across English, French, Italian, and Chinese. The detector is built on a frozen Gemma-4-12B-it backbone with trainable LoRA adapters (approximately 10.7M parameters). Because the backbone is a causal decoder, hidden states read from a single copy of an answer cannot attend to subsequent tokens; we therefore repeat the candidate answer within one prompt and extract features from its second occurrence, giving every position approximate bidirectional context in a single non-autoregressive pass. A character-level locator combines intermediate hidden states to predict hallucination probabilities, BIO boundaries, and a response-level abstention score, while separate language-specific classifiers assign one of five hallucination types to each predicted span. On the closed test set, our system reaches a macro-averaged character IoU of 0.4404, more than doubling the official baseline (0.1854), and ranks 5th-6th on IoU across the four languages. On the English tuning split, controlled ablations attribute a gain to the repeated answer that is comparable to that of LoRA adaptation (its held-out gain is smaller and concentrated on hallucinated answers), and they show that the detector relies on the image-answer pairing: shuffling images across examples drives IoU down to the level of the predict-nothing floor or below it in every language. In deployments where the same Gemma-4-12B-it model also generates answers, its base weights can be reused, making the approach practical for local question-answering systems that cannot run a separate verifier.

cs.CL

新论文 · v1arXiv:2611.14099

Opportunity-Cost Option-Critic: Adaptive Switching Costs for Robust Hierarchical Reinforcement Learning

Khaled Ammoura, Aya Kayal, Naseem Daher

原文摘要

Deliberation costs are commonly used in hierarchical reinforcement learning (HRL) to prevent options from collapsing to primitive actions. Existing approaches rely on fixed penalties or duration-based adaptations, both of which are indirect proxies for an option's utility. This paper argues that option persistence should instead depend on the opportunity cost of abandoning the current behavior. We propose the Opportunity-Cost Option-Critic ($OC^2$) framework, which defines a state-dependent deliberation cost using the positive value gap between the active option and its best alternative. This encourages persistence when the current option is clearly preferable and allows rapid switching when a better option emerges. We show that directly learning such costs leads to a degenerate zero-cost solution and introduces an auxiliary objective that aligns the learned cost with the value-gap target. The approach is evaluated in Four Rooms and Pinball domains under stationary, goal-shift, and geometry-shift conditions. In the Pinball goal-shift task, the $OC^2$ framework achieves a 52\% first-ten-episode success rate compared with 18\% for a fixed-cost baseline. The results suggest that opportunity-cost-based persistence improves adaptation in non-stationary environments.

cs.LG

新论文 · v1arXiv:2611.14098

CUVE: Making Supervised Classification more Accessible through Visualization

Sanchitha Kuppusami, Xiyao Wang, Miguel Nacenta

原文摘要

We present CUVE, an interface that enables people to build classifiers by generating visualizations that are interpretable by both humans and learning algorithms (the Visualization as Intermediate Representation approach). This UI enables users to create supervised classifiers and to visually investigate how to improve them and how they carry out their function. A preliminary study investigates the usability of our prototype and compares it with a traditional text-based programming interface.

cs.HC · cs.LG

新论文 · v1arXiv:2611.14094

Wave-Domain Semantic ISAC: Holographic Surfaces as Analog Semantic Encoders for Integrated TN-NTN

Shadi Danesh, Pooria Salami, Hesaam Zaravashan, Abdulkadir Köse, Ayhan Akbas, Chuan Heng Foh, Mohsen Khalily

原文摘要

Semantic communication, near-field operation, and integrated sensing and communication (ISAC) are often considered separately in terrestrial and non-terrestrial networks (TN--NTN). We show how a large electromagnetic aperture can connect them. \textcolor{black}{Nonlocal metasurfaces and holographic apertures act on the spatial spectrum of an incident field and can execute linear projections, which form an early stage of semantic feature extraction, directly in the wave domain before digitisation, thereby reducing the corresponding digital processing burden.} Near-field focusing also provides position-dependent sensing features, allowing the aperture to serve as an analog semantic-ISAC front end on resource-constrained aerial and satellite platforms. We describe the underlying physics, the co-design of constrained analog projections with lightweight digital decoders, and a case study in which a data-adaptive projection outperforms a fully digital baseline in the simulated energy-limited regime while transmitting four times fewer coefficients and using 11.4 times fewer decoder MACs. Finally, we identify relevant 3GPP, ITU-R, and ETSI activities and the remaining standardisation gaps.

cs.LO