论文广场 - AcademicHub

01.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13473

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

作者:

Jiacheng Chen ↗Xinyu Zhang ↗Shunkai Zhang ↗Yanmohan Wang ↗Lin Li ↗Tiancheng Qin ↗Qin Wang ↗Zhengmao Zhu ↗Tianle Li ↗Jingyang Li ↗Zehan Li ↗Binyang Jiang ↗…

We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities – proof generation, proof verification, and critique-conditioned proof repair – using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.14718

Gender Differences in AI Literacy Workshop Outcomes and Deepfake Engagement

作者:

Jake Renzella ↗Christian Bergh ↗Natasha Banks ↗Alexandra Vassar ↗

arXiv:2606.14718v1 Announce Type: cross Abstract: As Artificial Intelligence (AI) literacy initiatives expand in K-12 settings, understanding how gender shapes student baseline perceptions, tool-use, and responsiveness to interventions is essential for equitable curriculum design. This study examines gender differences in AI literacy, safety awareness, and STEM career aspirations among Australian secondary students (Years 7, 8, and 10; N(pre) = 199, n(post) = 136) from two co-educational government schools who participated in a one-day AI literacy workshop. Using statistical regression methods controlling for year level and school, we found that pre-workshop, male students reported significantly higher STEM career interest across all three domains (AI, computer science, and engineering), while female students were significantly more likely to use AI for schoolwork and to seek advice from AI tools. Gender-differentiated patterns also emerged in deepfake behaviours: males were significantly more likely to have created or shared deepfake content. Both genders improved in AI knowledge post-intervention, yet females showed a richer profile of gains: wider conceptual understanding, greater confidence, and meaningful increases in AI and CS career interest that partially narrowed the gender STEM gap. These findings highlight the need for gender-responsive AI curricula, particularly deepfake safety education for male students, and demonstrate that even single-day workshops can narrow gender gaps in STEM aspirations and AI confidence.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14094

FEMOT: Multi-Object Tracking using Frame and Event Cameras

作者:

Shiao Wang ↗Xiao Wang ↗Chao Wang ↗Yitao Li ↗Menghao Liu ↗Bo Jiang ↗Yaowei Wang ↗Yonghong Tian ↗Jin Tang ↗

Conventional RGB cameras have been widely used in multi-object tracking due to their ability to capture rich appearance and semantic information. However, their performance is often degraded under complex real-world challenges, such as motion blur, low illumination, and overexposure. Bio-inspired event cameras offer high temporal resolution and high dynamic range, providing complementary cues under extreme scenarios. Nevertheless, RGB-event multi-object tracking remains underexplored due to the lack of large-scale and well-annotated datasets. To address this issue, we propose FEMOT, a large-scale RGB-event multi-object tracking dataset that covers diverse real-world scenarios and 14 challenging attributes. With both RGB and event data as well as high-quality annotations, FEMOT provides a reliable platform for systematically evaluating RGB-event multi-object tracking methods. Based on FEMOT, we retrain and evaluate over ten strong trackers, thereby establishing a comprehensive benchmark for future research. Furthermore, we propose FEMOTR, a multimodal tracking framework that decouples RGB and event features and fuses them in the frequency domain, thereby effectively exploiting their complementary characteristics for robust object localization and identity association. Extensive experiments on FEMOT and DSEC-MOT datasets demonstrate the effectiveness of the proposed method. The source code and benchmark dataset have been released on https://github.com/Event-AHU/FEMOT.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2602.00176

Posterior Continuation with Noise-Conditioned Frequency Exposure for Diffusion Inverse Problems

作者:

Feng Tian ↗Yixuan Li ↗Weili Zeng ↗Weitian Zhang ↗Yichao Yan ↗Xiaokang Yang ↗

Diffusion posterior sampling solves inverse problems by combining a pretrained diffusion prior with measurement-consistency guidance. However, full-band guidance can be unreliable at high noise levels, where clean estimates contain score-induced errors and high-frequency measurement directions are weakly identifiable. We argue that posterior guidance should expose measurement frequencies according to the instantaneous diffusion noise level. Based on this principle, we propose a posterior continuation framework that constructs a family of intermediate posteriors whose likelihood emphasizes currently reliable frequency bands and gradually returns to full-band consistency. We instantiate this framework with a stabilized sampler that combines a diffusion predictor, frequency-limited likelihood refinement, and a Haar-domain commitment rule that commits reliable coarse corrections while deferring weakly identifiable details. Across super-resolution, inpainting, and deblurring, our method achieves competitive-to-state-of-the-art restoration performance, including up to 5 dB PSNR improvement on motion deblurring over strong baselines in evaluations on FFHQ and ImageNet.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2603.09715

Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFT

作者:

Peng Sun ↗Yi Yang ↗Huawen Shen ↗Yi Ban ↗Tianfan Fu ↗Yanbo Wang ↗Yuqiang Li ↗

arXiv:2603.09715v2 Announce Type: replace Abstract: Visual instruction tuning is crucial for improving vision-language large models (VLLMs). However, many samples can be solved via linguistic patterns or common-sense shortcuts, without genuine cross-modal reasoning, limiting the effectiveness of multimodal learning. Prior data selection methods often rely on costly proxy model training and focus on difficulty or diversity, failing to capture a sample's true contribution to vision-language joint reasoning. In this paper, we propose CVS, a training-free data selection method based on the insight that, for high-quality multimodal samples, introducing the question should substantially alter the model's assessment of answer validity given an image. CVS leverages a frozen VLLM as an evaluator and measures the discrepancy in answer validity with and without conditioning on the question, enabling the identification of samples that require vision-language joint reasoning while filtering semantic-conflict noise. Experiments on Vision-Flan and The Cauldron show that CVS achieves solid performance across datasets. On Vision-Flan, CVS outperforms full-data training by 3.5% and 4.8% using only 10% and 15% of the data, respectively, and remains robust on the highly heterogeneous Cauldron dataset. Moreover, CVS reduces computational cost by 17.3% and 44.4% compared to COINCIDE and XMAS.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15320

Conditional Multi-Event Temporal Grounding in Long-Form Video

作者:

Yuanhao Zou ↗Arthad Kulkarni ↗Lucas Tonanez ↗Lincoln Spencer ↗Guangyu Sun ↗Tianxingjian Ding ↗Andong Deng ↗Yi Li ↗Shuangjun Liu ↗Yuan Li ↗Dashan Gao ↗Ning Bi ↗…

Multimodal large language models have made rapid progress in video temporal grounding, yet real-world applications routinely require localizing every event that satisfies compositional temporal and spatial conditions. Existing benchmarks fall short: they localize only a single moment per query, count without temporal conditions, or treat grounding and counting as disjoint tasks. We introduce CoMET-Bench for Conditional Multi-Event Temporal Grounding in long-form video, comprising 2789 queries over 600 videos averaging 33.8 minutes across five real-world domains, with each query composed from 4 temporal conditions, 3 spatial conditions, and a dedicated negative-query subset. We further propose a unified evaluation protocol jointly measuring counting, grounding, and negative-query recognition, including a new Rejection-F1 metric that prevents trivial gaming by lazy "always-empty" models. Benchmarking a broad suite of MLLMs, agent-based, and grounding-specialized methods reveals that existing approaches remain far from solving this task. Building on these findings, we propose CoMET-Agent, a training-free agentic framework that reformulates the task as structured search-and-aggregate, improving F1@0.5 by 6.1% over GPT-5 purely through structural reasoning. Failure analysis further surfaces three open directions: fine-grained entity tracking, position-uniform retrieval, and causal event pairing.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2512.11682

MedAI: Evaluating TxAgent's Therapeutic Agentic Reasoning in the NeurIPS CURE-Bench Competition

作者:

Tim Cofala ↗Christian Kalfar ↗Jingge Xiao ↗Johanna Schrader ↗Michelle Tang ↗Wolfgang Nejdl ↗

arXiv:2512.11682v2 Announce Type: replace Abstract: Therapeutic decision-making in clinical medicine constitutes a high-stakes domain in which AI guidance interacts with complex interactions among patient characteristics, disease processes, and pharmacological agents. Tasks such as drug recommendation, treatment planning, and adverse-effect prediction demand robust, multi-step reasoning grounded in reliable biomedical knowledge. Agentic AI methods, exemplified by TxAgent, address these challenges through iterative retrieval-augmented generation (RAG). TxAgent employs a fine-tuned Llama-3.1-8B model that dynamically generates and executes function calls to a unified biomedical tool suite (ToolUniverse), integrating FDA Drug API, OpenTargets, and Monarch resources to ensure access to current therapeutic information. In contrast to general-purpose RAG systems, medical applications impose stringent safety constraints, rendering the accuracy of both the reasoning trace and the sequence of tool invocations critical. These considerations motivate evaluation protocols treating token-level reasoning and tool-usage behaviors as explicit supervision signals. This work presents insights derived from our participation in the CURE-Bench NeurIPS 2025 Challenge, which benchmarks therapeutic-reasoning systems using metrics that assess correctness, tool utilization, and reasoning quality. We analyze how retrieval quality for function (tool) calls influences overall model performance and demonstrate performance gains achieved through improved tool-retrieval strategies. Our work was awarded the Excellence Award in Open Science. Complete information can be found at https://curebench.ai/.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18441

Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMs

作者:

Chengwen Liu ↗Zhe Huang ↗Jisheng Dang ↗Hong Peng ↗Qi Tian ↗Tat-Seng Chua ↗

Reinforcement learning has improved the reasoning ability of large language models, but applying outcome-only rewards to video multimodal large language models (Video-MLLMs) provides limited guidance on which visual evidence should support the answer. Inspired by multisensory integration, where consistent cues can enhance the salience and reliability of perceptual estimates, we introduce Consensus Frame GRPO (CF-GRPO), a temporal-annotation-free process-level reward framework for evidence-aware video reasoning. CF-GRPO constructs a consensus frame prior from intrinsic video cues, including temporal coverage, scene-transition cues, and query-conditioned visual relevance. It then computes a model-side frame-use score from visual and response representations and optimizes their agreement through the Consensus Frame Reward (CFR). With salience-aware sparse aggregation and distribution sharpening, CFR provides a high-contrast reward signal without requiring human temporal annotations. Experiments show that VideoCFR achieves competitive performance across complex video reasoning benchmarks and improves several metrics over representative Video-MLLM and RL baselines, while the consensus prior provides an interpretable view of the evidence frames emphasized during training. The implementation is available at https://github.com/1Pansy/VideoCFR.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2505.14418

Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents

作者:

Pengzhou Cheng ↗Haowen Hu ↗Zheng Wu ↗Zongru Wu ↗Tianjie Ju ↗Zhuosheng Zhang ↗Gongshen Liu ↗

Graphical user interface (GUI) agents powered by multimodal large language models (MLLMs) have shown greater promise for human-interaction. However, due to the high fine-tuning cost, users often rely on open-source GUI agents or APIs offered by AI providers, which introduces a critical but underexplored supply chain threat: backdoor attacks. In this work, we first unveil that MLLM-powered GUI agents naturally expose multiple interaction-level triggers, such as historical steps, environment states, and task progress. Based on this observation, we introduce AgentGhost, an effective and stealthy framework for red-teaming backdoor attacks. Specifically, we first construct composite triggers by combining goal and interaction levels, allowing GUI agents to unintentionally activate backdoors while ensuring task utility. Then, we formulate backdoor injection as a Min-Max optimization problem that uses supervised contrastive learning to maximize the feature difference across sample classes at the representation space, improving flexibility of the backdoor. Meanwhile, it adopts supervised fine-tuning to minimize the discrepancy between backdoor and clean behavior generation, enhancing effectiveness and utility. Extensive evaluations of various agent models in two established mobile benchmarks show that AgentGhost is effective and generic, with attack accuracy that reaches 99.7\% on three attack objectives, and shows stealthiness with only 1\% utility degradation. Furthermore, we tailor a defense method against AgentGhost that reduces the attack accuracy to 22.1\%. Our code is available at \texttt{anonymous}.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12352

CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy

作者:

Ria Doshi ↗Tian Gao ↗Annie Chen ↗Chelsea Finn ↗Jeannette Bohg ↗

arXiv:2606.12352v1 Announce Type: cross Abstract: Multi-robot collaboration allows robots to efficiently take on a wide range of tasks, from moving a couch through a doorway to assembling structures on a construction site. However, achieving such coordination in mobile multi-robot settings remains challenging: centralized methods conditioned on the combined observations of a team scale poorly with team size, and decentralized methods that train one policy per robot often require explicit alignment procedures or information sharing at inference time to overcome partial observability. Our key insight is that the visuomotor priors of pretrained vision-language-action (VLA) models should enable reactive, decentralized collaboration from each robot's local observations alone, without these inference-time assumptions. We propose CHORUS, a framework that adapts a single VLA backbone to control diverse, multi-robot teams. At inference time, each robot runs an independent copy of CHORUS, conditioned only on its own observations and a robot-identifying prompt. In real-world experiments including mobile tape measurement, library book handovers, and laundry basket lifting, CHORUS achieves a 64% point improvement over decentralized, from-scratch models, improves reactivity to teammate behavior by 40% points, and outperforms centralized baselines. Together, these results show that a shared VLA backbone is capable of achieving decentralized multi-robot collaboration, without per-robot policies or inter-robot communication at inference.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2410.12327

Neuron-based Personality Trait Induction in Large Language Models

作者:

Jia Deng ↗Tianyi Tang ↗Yanbin Yin ↗Wenhao Yang ↗Wayne Xin Zhao ↗Ji-Rong Wen ↗

Large language models (LLMs) have become increasingly proficient at simulating various personality traits, an important capability for supporting related applications (e.g., role-playing). To further improve this capacity, in this paper, we present a neuron-based approach for personality trait induction in LLMs, with three major technical contributions. First, we construct PersonalityBench, a large-scale dataset for identifying and evaluating personality traits in LLMs. This dataset is grounded in the Big Five personality traits from psychology and is designed to assess the generative capabilities of LLMs towards specific personality traits. Second, by leveraging PersonalityBench, we propose an efficient method for identifying personality-related neurons within LLMs by examining the opposite aspects of a given trait. Third, we develop a simple yet effective induction method that manipulates the values of these identified personality-related neurons. This method enables fine-grained control over the traits exhibited by LLMs without training and modifying model parameters. Extensive experiments validate the efficacy of our neuron identification and trait induction methods. Notably, our approach achieves comparable performance as fine-tuned models, offering a more efficient and flexible solution for personality trait induction in LLMs. We provide access to all the mentioned resources at https://github.com/RUCAIBox/NPTI.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14397

Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments

作者:

arXiv:2606.14397v1 Announce Type: new Abstract: As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capabilities. However, current benchmarks are typically built on popular applications with relatively simple tasks and focus on a narrow set of capabilities while overlooking broader dimensions, resulting in saturated performance on modern agents and failing to probe their limitations. To this end, we introduce GauntletBench, a web-based benchmark for evaluating agent generalisation in challenging scenarios, focusing on three underexplored capabilities (temporal perception, graphical understanding, and 3D reasoning), across five less-covered professional applications (Video Editor, Workflow Builder, 3D Modeller, Flight Analyser, and Circuit Designer), each with 20 vision-intensive tasks (100 in total). Our benchmark provides a modular pipeline that comprises an environment compatible with both open- and closed-source agent frameworks, a controlled web-based application, a well-structured task suite, and an automated evaluation engine with diverse metrics. Contrary to widespread expectations, our empirical results reveal that frontier agentic systems remain far from achieving human-level performance. Even the state-of-the-art agent achieves only a 19.1% success rate on our GauntletBench, highlighting the limitations in these overlooked capabilities and generalisation. By comparison, non-expert human annotators achieve over 80% success on our challenging yet feasible tasks, revealing the substantial gap between current agent capabilities and those required for complex real-world scenarios.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.07678

DOG-DPO:Dynamic Optimization in Geometry for Safety Alignment

作者:

Yi Nian ↗Tiankai Yang ↗Yudi Zhang ↗Qi Pan ↗Zelong Xu ↗Shenzhe Zhu ↗Qingqing Luan ↗Yue Huang ↗Xiangliang Zhang ↗Yue Zhao ↗

arXiv:2606.07678v2 Announce Type: replace-cross Abstract: Safety alignment for large language models relies on preference data, but current pipelines often train on large, redundant datasets. Existing data selection methods typically score each preference pair independently, collapsing directional preference information into scalar quality or diversity scores. This sample-centric view is especially limiting in multi-dataset settings, where shared safety directions coexist with dataset-specific residual risks. We propose DOG-DPO, a training-free data selection framework that treats preference pairs as structured geometric signals. DOG-DPO first represents each preference pair as a direction in model representation space. It then decomposes multi-dataset preference geometry into a global anchor subspace and dataset-specific residual subspaces. Finally, it selects subsets by maximizing diversity-based coverage, encouraging broad, non-redundant coverage of alignment directions before DPO training. Across six safety benchmarks and two model backbones, DOG-DPO achieves a strong utility-robustness trade-off using only 11% of the preference pairs. It recovers most of the safety gains of full-data training while remaining entirely teacher-free, training-free, and substantially faster than representative selection baselines.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.19302

Optimal scenario design for climate emulation

作者:

Christopher B. Womack ↗Shahine Bouabid ↗Andrei Sokolov ↗Popat Salunke ↗Glenn Flierl ↗Sebastian D. Eastham ↗Noelle E. Selin ↗

arXiv:2606.19302v1 Announce Type: cross Abstract: As deep learning for physical systems continues to grow in popularity, efforts to improve generalizability have primarily focused on designing architectures that embed physical constraints. However, for machine-learning surrogate climate models (emulators), we show that the low structural diversity in existing scenarios commonly used to generate training data places a ceiling on predictive skill. Here, we examine whether training datasets themselves can be optimized to improve generalization. We introduce a method to create datasets that produce emulators capable of generalizing to new, structurally different scenarios absent from the training data. We use a differentiable Simple Climate Model (SCM) to calculate the sensitivity of emulator loss to perturbations in the training data, iteratively updating the training data to maximize emulator skill. For an SCM, training on one scenario optimized in this fashion outperforms an emulator trained on six standard ScenarioMIP pathways. We achieve this higher predictive skill despite training on a smaller dataset, finding that our emulator successfully isolates distinct physical behaviors of different climate forcing agents (e.g., greenhouse gases vs. aerosols) without single-forcing runs. We then demonstrate that scenarios optimized using an SCM, when used to drive an intermediate-complexity climate model, produce a training dataset that yields a more skillful emulator than training on ScenarioMIP outputs. Our results suggest that, in the compute-constrained environment of running full-scale climate models, generating a small number of dynamically rich scenarios provides greater marginal value for emulation and characterizing system responses than expanding the suite of traditional emissions pathways.

阅读与讨论 → 访问原文 →

15.

arXiv (math.PR) 2026-06-17 DOI: arXiv:2606.17452

Optional Stopping for Superhedging Supermartingales

作者:

Christian Bender ↗Sebastian E. Ferrando ↗

arXiv:2606.17452v1 Announce Type: new Abstract: Superhedging supermartingales, introduced by the authors in previous work, are non-probabilistic processes defined via subadditive outer integrals that carry a purely financial interpretation in terms of superhedging cost. Building on the Leinert-König theory of non-lattice integration, the present paper establishes several results that are classical in probability theory but whose non-probabilistic proofs require fundamentally new arguments: (i) a tower inequality for the conditional outer integral \overline{\sigma}_j applied at stopping times, reducing to equality when the integrand is conditionally integrable; (ii) three versions of Doob's optional stopping theorem, organised by the class of supermartingale and the range of the stopping times; and (iii) Dubins' upcrossing inequality in both finite- and infinite-time horizons. A key structural result, property (K)-a.e., identifies conditions under which the two superhedging operators \overline{\sigma}_j and \overline{I}_j coincide on non-negative functions, extending the scope of all preceding results to the positive operator \overline{I}_j. None of the proofs invoke classical measure-theoretic tools; in particular, (classical) integrability and measurability are not assumed. The analogues of classical stochastic results acquire a purely financial interpretation and, in this way, gain depth and generality by providing a context that is independent of any a priori probabilistic structure.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12072

World Model Self-Distillation: Training World Models to Solve General Tasks

作者:

Sebastian Stapf ↗Pablo Acuaviva Huertos ↗Aram Davtyan ↗Paolo Favaro ↗

Pretrained video generators are promising visual world models that exhibit emergent task-solving abilities; however, their reliance on detailed textual descriptions limits their direct use for planning and decision-making. Existing approaches either outsource this reasoning to language or vision-language models, or rely on supervised fine-tuning with paired task-execution videos, which are costly to collect and difficult to scale. We propose a scalable framework that elicits task-solving ability in such models by combining self-distillation with reinforcement learning. Given an unlabeled scene image, a vision-language model generates a candidate task and a detailed step-by-step solution. The solution conditions a pretrained video diffusion model, the Demonstrator; we distill its behavior into an Executor conditioned only on the image and a short task prompt. This transfers execution knowledge from caption-guided generation to instruction-conditioned task solving without curated task-video supervision. We further improve the Executor with reinforcement learning from VLM feedback, exploiting the asymmetry between judging whether a sampled video satisfies a task and generating the solution. Experiments on our proposed WorldTasks-Benchmark and the DreamGen robotics benchmark show that the Executor surpasses the Demonstrator under our VLM-based evaluation protocol and transfers competitively to robotic tasks.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12935

MARS: Margin-Adversarial Risk-controlled Stopping for Parallel LLM Test-time Scaling

作者:

Wenbo Chen ↗Puheng Li ↗Mengyang Liu ↗Weijie Su ↗Tianpei Xie ↗

arXiv:2606.12935v1 Announce Type: new Abstract: Parallel test-time scaling samples many reasoning traces and majority-votes their answers, improving LLM accuracy but requiring traces to run to completion, incurring substantial computational overhead. We observe that probing partial traces at intermediate checkpoints can extract current answers without disrupting generation, revealing an evolving aggregate vote. Based on this observation, we introduce MARS, a margin-adversarial stopping rule that estimates which active traces are likely to change their answers and stops once the leader remains safe under a conservative bound on future vote movement. The rule separates two sources of uncertainty. It learns the trace-level switch probabilities that determine how much of the current margin is likely to be retained, while handling the harder question of where switching traces land through an adversarial bound calibrated from warmup traces. With true switch probabilities, MARS guarantees with high probability that the early-stopped answer matches the full-budget vote. In practice, a five-feature logistic model closely matches oracle switching behavior. Across three reasoning models and three competition-math benchmarks, MARS saves 25-47% of self-consistency tokens and 14-29% on top of DeepConf Online, a strong confidence-weighted baseline that already filters and truncates weak traces, while matching the accuracy of the corresponding full-budget baselines.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.12633

ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation

作者:

Jiangtao Kong ↗Peijun Zhao ↗Chun-Fu Chen ↗Youngwook Do ↗Shaohan Hu ↗Tianyi Zhou ↗Huajie Shao ↗

Incremental Learning (IL) for Open-ended Image-to-Text Generation (OpenITG) enables models to continuously generate accurate, contextually relevant text for new images while preserving previously acquired knowledge. Unlike prior studies, this paper addresses a more practical scenario in which the predominant category of visual data shifts over time as environments evolve. In this context, we introduce a new notion of continual alignment, which incrementally adapts the alignment module within pre-trained VLMs to preserve high-quality cross-modal representations. Based on this idea, we propose Efficient Continual Alignment (ECA), a novel exemplar-free IL approach for OpenITG. The key challenge is enabling the model to acquire new, task-specific features while minimizing interference with the established alignment without accessing raw data from previous tasks. To address this, ECA employs three core mechanisms: a Mixture of Query (MoQ) module that adapts task-specific query tokens, a Fisher Dynamic Expansion (FeDEx) that dynamically expands model structure based on a Fisher Information Matrix (FIM)-based metric, and an embedding dictionary with Dictionary Replay (DR) to retain past knowledge. To evaluate ECA's performance, we construct four new IL OpenITG benchmarks that better reflect real-world scenarios. Experimental results demonstrate that ECA significantly mitigates catastrophic forgetting and improves IL performance compared to baseline methods. Code and benchmarks are available at https://github.com/Snowball0823/ECA.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17710

Vision-language models for chest radiography do not always need the image

作者:

Mahshad Lotfinia ↗Sebastian Ziegelmayer ↗Lisa Adams ↗Daniel Truhn ↗Andreas Maier ↗Soroosh Tayebi Arasteh ↗

Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image. That inference is unsafe: a model exploiting finding-name priors scores like one that reads the scan, and no standard benchmark separates them. We introduce a causal audit that intervenes on the image, occluding the relevant region, occluding an irrelevant one, and swapping in another patient's same-label scan, and combines three behavioral metrics to test whether a correct answer depends on the image. Across nine systems, a text-only model with no image access reaches within 5.7 accuracy points of the best multimodal one, and a 119-billion-parameter multimodal model is statistically indistinguishable from a 7-billion text-only baseline. The audit splits the cohort into three models that ignore the image, one that is unstable, and five that use it selectively, for a subset of findings; the categories hold across a second dataset, resolution, and prompt phrasing. Against board-certified radiologists, a text-only model is statistically indistinguishable from a radiologist's accuracy while grounding at zero, whereas the image-using models ground at radiologist-comparable rates. Reported confidence flags ungrounded answers only when a model uses the image. Grounding audits, not accuracy, should gate clinical deployment.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.11884

Image Quality Assessment of Identity Cards Using Measures from Open Face Image Quality

作者:

Gregor Grote ↗Juan E. Tapia ↗Christian Rathgeb ↗

This paper addresses the challenge of assessing image quality in ID cards in remote verification systems by applying capture-related quality measures from the Open Face Image Quality (OFIQ) standard to ID card images. Our preprocessing pipeline includes corner detection, perspective normalization, and comprehensive foreground masking to ensure accurate and unbiased quality measure computation. We evaluate the effectiveness of these measures by analyzing their correlation with the performance of three presentation attack detection (PAD) algorithms across four diverse ID card datasets, where two datasets contain bona fide, i.e. pristine, images and two contain printed mock ID cards. Our results suggest that quality assessment based on some OFIQ measures can significantly improve PAD performance.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17609

The Benchmark Illusion: Pruned LLMs Can Pass Multiple Choice but Fail to Answer

作者:

Rui Wen ↗Lu Sun ↗Jiayang Liu ↗Zesheng Xu ↗Tianshuo Cong ↗Zheng Li ↗

Compressing large language models reduces memory use and inference cost, but it can also create failures that standard benchmarks miss. A pruned model may still perform well on multiple-choice evaluations, yet fail to answer the same question in open generation. We ask what pruning changes: does it erase the correct answer, or does it make the answer harder to produce as the top output? We study this question with multilingual question answering, tracking the same questions before and after pruning. We find a benchmark illusion. Under high-sparsity pruning, especially Wanda, models often fail in greedy open generation while still selecting the correct answer under multiple-choice scoring. In these recognition-only errors, the answer is usually not gone, but demoted: it often reappears with beam search, sampling, or one in-context example. Overall, multiple-choice benchmarks can overstate the usability of compressed LLMs, creating an evaluation blind spot. Compressed models should be tested on what they can produce, not only on what they can recognize.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2602.07544

MUFASA: A Multi-Layer Framework for Slot Attention

作者:

Sebastian Bock ↗Leonie Sch\"u{\ss}ler ↗Krishnakant Singh ↗Simone Schaub-Meyer ↗Stefan Roth ↗

Unsupervised object-centric learning (OCL) decomposes visual scenes into distinct entities. Slot attention is a popular approach that represents individual objects as latent vectors, called slots. Current methods obtain these slot representations solely from the last layer of a pre-trained vision transformer (ViT), ignoring valuable, semantically rich information encoded across the other layers. To better utilize this latent semantic information, we introduce MUFASA, a lightweight plug-and-play framework for slot-attention-based approaches to unsupervised object segmentation. Our model computes slot attention across multiple feature layers of the ViT encoder, fully leveraging their semantic richness. We propose a fusion strategy to aggregate slots obtained on multiple layers into a unified object-centric representation. Integrating MUFASA into existing OCL methods improves their segmentation results across multiple datasets, setting a new state of the art while simultaneously improving training convergence with only minor inference overhead.

阅读与讨论 → 访问原文 →

23.

arXiv (quant-ph) 2026-06-19 DOI: arXiv:2606.20387

Interaction geometry and ground-state properties of sparse quantum lattice models

作者:

Alex Gunning ↗Sebastian Schmid ↗Zhengxiao Liu ↗Sridevi Kuriyattil ↗Aydin Deger ↗Andrew J. Daley ↗

arXiv:2606.20387v1 Announce Type: new Abstract: We investigate how interaction geometry shapes the low-energy phases of sparse tunable long-range quantum models. We focus on a class of graphs whose degree grows logarithmically with system size, and show how symmetry and frustration in graph connectivity can drive, suppress, and reshape ground-state phase transitions. The central examples are power-of-$p$ graphs, where even and odd values of $p$ exhibit qualitatively distinct behaviour: even-$p$ graphs inherit the rich phase structure of the power-of-two model, while odd-$p$ graphs are governed by geometric frustration. Fibonacci graphs provide a contrasting case, lacking the discrete self-similarity of the power-of-$p$ family but exhibiting a direct geometric mapping between the short- and long-range limits. Across our models, we find that phase structure and criticality are governed by the same effective-geometry principle, unifying our framework for experimentally motivated long-range quantum systems.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2602.12670

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

作者:

Xiangyi Li ↗Yimin Liu ↗Wenbo Chen ↗Bingran You ↗Zonglin Di ↗Yifeng He ↗Shenghan Zheng ↗Kyoung Whan Choe ↗Jiankai Sun ↗Shuyi Wang ↗Chujun Tao ↗Binxu Li ↗…

arXiv:2602.12670v4 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13239

ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm

作者:

Jiaxin Ai ↗Tao Hu ↗Xuemeng Yang ↗Shu Zou ↗Hairong Zhang ↗Daocheng Fu ↗Yu Yang ↗Hongbin Zhou ↗Nianchen Deng ↗Pinlong Cai ↗Zhongyuan Wang ↗Botian Shi ↗…

Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accumulation, while API-basedapproaches struggle with heterogeneous protocols and inaccessible commercial interfaces. In this work,we identify the Component Object Model (COM) as a unified executable abstraction, proposing COM-as-Action: a new paradigm that reframes professional software interaction as deterministic program synthesisrather than sequential visual control. To validate this paradigm in the most demanding environments, weintroduce ComCADBench, the first benchmark for agents operating real industrial CAD software. Ourexperiments reveal a substantial paradigm gap: frontier proprietary models achieve near-zero successunder GUI-based interaction, whereas COM-based execution yields substantial immediate gains. Tobridge the remaining gap between syntactic correctness and geometric accuracy, we develop ComActor, aself-correcting agent trained through a progressive three-stage framework, alongside ComForge, a scalableplatform for large-scale training in Windows containers. Extensive experiments show that ComActorachieves state-of-the-art performance on ComCADBench, with strong resilience in long-horizon taskswhere baselines collapse, and generalizes to external CAD benchmark.

阅读与讨论 → 访问原文 →

探索全球前沿学术脉络