探索全球前沿学术脉络

01.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18584

Speech-Driven End-to-End Language Discrimination towards Chinese Dialects

作者:

Fan Xu↗Jian Luo↗MingWen Wang↗GuoDong Zhou↗

Language discrimination among similar languages, varieties, and dialects is a challenging natural language processing task. The traditional text-driven focus leads to poor results. In this paper, we explore the effectiveness of speech-driven features towards language discrimination among Chinese dialects. First, we systematically explore the appropriateness of speech-driven MFCC features towards CNN-based language discrimination. Then, we design an end-to-end speech recognition model based on HMM-DNN to predict Chinese dialect words. We adopt attention to extract the discriminative words related to different Chinese dialects. Finally, through a CNN, we combine the word-level embedding and the MFCC-based features. Evaluation of two benchmark Chinese dialect corpora shows the appropriateness and effectiveness of the proposed speech-driven approach to fine-grained Chinese dialect discrimination compared to the state-of-the-art methods.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2602.08913

GEMSS: A Variational Bayesian Method for Discovering Multiple Sparse Solutions in Classification and Regression Problems

作者:

Kate\v{r}ina Henclov\'a↗V\'aclav \v{S}m\'idl↗

arXiv:2602.08913v2 Announce Type: replace Abstract: High-dimensional, underdetermined and highly correlated systems are common in data science practice, especially when analyzing physical measurements. In such settings, feature selection poses a fundamental challenge because multiple distinct sparse subsets may explain the response equally well. Their identification is crucial not only for predictive modeling but also for generating domain-specific insights into the underlying mechanisms. Yet, conventional methods typically isolate a single solution, obscuring the full spectrum of plausible explanations. This work introduces GEMSS (Gaussian Ensemble for Multiple Sparse Solutions), a variational algorithm designed to simultaneously discover multiple, diverse sparse feature combinations. The method employs a structured spike-and-slab prior for sparsity, a mixture of Gaussians to approximate the intractable multimodal posterior, and a Jaccard-based penalty to further control solution diversity. A single objective function is optimized via stochastic gradient descent. The method is tested on 128 comprehensive experiments by a novel benchmarking framework designed to generate artificial problems with multiple sparse solutions of equal predictive properties. This allows us to measure the retrieval of ground truth features rather than only evaluating predictive performance – characteristics more fitting to our practical needs. A comparative analysis shows that GEMSS consistently outperforms five prominent feature selection methods adapted through the ALFESE framework. Finally, we demonstrate practical usability through 3 challenging real-world datasets from metabolomics and physical chemistry: GEMSS successfully isolates multiple distinct yet quality solutions. GEMSS is available as a PyPI package 'gemss'. The corresponding repository github.com/kat-er-ina/gemss/ includes the full codebase and a free, no-code application GEMSS Explorer.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2603.08558

Impact of Connectivity on Laplacian Representations in Reinforcement Learning

作者:

Tommaso Giorgi↗Pierriccardo Olivieri↗Keyue Jiang↗Laura Toni↗Matteo Papini↗

arXiv:2603.08558v3 Announce Type: replace Abstract: Learning compact state representations in Markov Decision Processes (MDPs) has proven crucial for addressing the curse of dimensionality in large-scale reinforcement learning (RL) problems. Existing principled approaches leverage structural priors on the MDP by constructing state representations as linear combinations of the state-graph Laplacian eigenvectors. When the transition graph is unknown or the state space is prohibitively large, the graph spectral features can be estimated directly via sample trajectories. In this work, we prove an upper bound on the approximation error of linear value function approximation under the learned spectral features. We show how this error scales with the algebraic connectivity of the state-graph, grounding the approximation quality in the topological structure of the MDP. We further bound the error introduced by the eigenvector estimation itself, leading to an end-to-end error decomposition across the representation learning pipeline. Additionally, our expression of the Laplacian operator for the RL setting, although equivalent to existing ones, prevents some common misunderstandings, of which we show some examples from the literature. Our results hold for general (non-uniform) policies without any assumptions on the symmetry of the induced transition kernel. We validate our theoretical findings with numerical simulations on gridworld environments.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12609

Viral Proteins Reveal Geometry of Protein Language Models

作者:

Arthur Bigot↗Harmon Bhasin↗Core Francisco Park↗Eugene Shakhnovich↗Dianzhuo Wang↗

arXiv:2606.12609v1 Announce Type: new Abstract: Protein language models are trained on highly imbalanced datasets, raising the question of how they represent underrepresented biological sequences. Using viral proteins as a case study across ESM model families, we identify a dominant nativeness axis in embedding space, aligned with masked reconstruction perplexity, that orders sequences from well-modeled cellular proteins through viral proteins to shuffled and random sequences. Scaling contracts this axis unevenly across viral families. Despite this, protein language model embeddings retain viral-specific signal: viral proteins remain linearly separable beyond zero-shot perplexity and shallow sequence features. Together, these results suggest that pLM representations are structured by a general notion of nativeness while preserving information specific to distinct biological groups.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2603.02234

Structured vs. Unstructured Pruning: An Exponential Gap

作者:

Davide Ferre'↗Fr\'ed\'eric Giroire↗Frederik Mallmann-Trenn↗Emanuele Natale↗

arXiv:2603.02234v3 Announce Type: replace-cross Abstract: The Strong Lottery Ticket Hypothesis (SLTH) states that large, randomly initialized neural networks contain sparse subnetworks capable of approximating a target function at initialization without training, suggesting that pruning alone is sufficient. Pruning methods are typically classified as unstructured, where individual weights can be removed from the network, and structured, where parameters are removed according to specific patterns, as in neuron pruning. Existing theoretical results supporting the SLTH rely almost exclusively on unstructured pruning, showing that logarithmic overparameterization suffices to approximate simple target networks. In contrast, neuron pruning has received limited theoretical attention, despite its practical appeal for direct hardware speedups. In this work, we consider the problem of approximating a single bias-free ReLU neuron by pruning hidden units of a randomly initialized two-layer ReLU network, effectively isolating the intrinsic limitations of neuron pruning. We show that achieving an $\varepsilon$-approximation requires a starting network size of $\Omega(1/\varepsilon)$ for neuron pruning, whereas weight pruning succeeds with only $O(\log(1/\varepsilon))$ hidden units, revealing an exponential separation between the two approaches.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18599

MIDS: Detecting Stealthy Masquerade and Tampering Attacks on CAN Bus via Bidirectional Mamba

作者:

Qiqi Liu↗Runhan Song↗Lei Cui↗Heng Zhang↗Yuyan Sun↗Limin Sun↗

arXiv:2606.18599v1 Announce Type: cross Abstract: The Controller Area Network (CAN) protocol is the primary communication standard for Electronic Control Units (ECUs) in modern vehicles, but its lack of encryption and authentication exposes it to a range of security threats. Existing intrusion detection systems are largely tuned to fabrication-style attacks (DoS, fuzzing, ID spoofing realised by frame injection), in which detection signals such as per-ID inter-arrival statistics are readily available. We instead address the harder masquerade setting[b37], in which an internal adversary substitutes a legitimate frame in-situ at its original transmission slot, preserving traffic periodicity and rendering traffic-statistic defences ineffective. We propose the Mamba Intrusion Detection System (MIDS), an innovative dual-stream framework that processes CAN identifiers and payloads in parallel and reconstructs their joint temporal semantics through bidirectional selective state-space modelling. To evaluate MIDS, we collected over 100 million CAN frames from a physical Tesla Model 3 across three driving regimes and synthesised 54 masquerade attack variants spanning ID-only, data-only, and combined modifications. MIDS attains an F1 of 96.94\% on this dataset, exceeding the strongest reproducible baseline by more than 8 percentage points, while sustaining a 1.147~ms single-window inference latency – ample headroom for real-time onboard deployment. To verify generalisation, we further evaluate MIDS on four public benchmarks (ROAD, CrySyS, OTIDS, CT\&T) covering both masquerade and injection scenarios; MIDS attains F1 from 93.70\% to 99.61\%, outperforming the strongest of eight reproduced baselines by up to 13.94 percentage points under a unified 5-fold protocol.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14766

XMedFusion: A Knowledge-Guided Multimodal Perception and Reasoning Framework for Autonomous Medical Systems

作者:

Hamza Riaz↗Arham Haroon↗Maha Baig↗Muhammad Dawood Rizwan↗Muhammad Naseer Bajwa↗Muhammad Moazam Fraz↗

Autonomous medical and robotic systems increasingly rely on intelligent perception and reasoning capabilities to interpret visual data and support clinical decision making. Radiology report generation represents a critical component of such automated diagnostic workflows, yet existing end-to-end multimodal models often suffer from weak visual grounding, resulting in unreliable interpretations and omission of subtle clinical findings. This paper presents XMedFusion, a modular AI framework designed as an intelligent perception and reasoning module for autonomous medical systems. The proposed framework decomposes visual information into coordinated functional components that emulate expert-driven analysis, including a visual perception agent that extracts image-grounded evidence, a knowledge graph construction agent that structures clinically relevant findings, and a retrieval-guided drafting process that ensures a consistent reporting structure. A synthesis agent iteratively integrates visual and structured evidence through reasoning-driven verification to produce reliable and interpretable diagnostic outputs. Experimental evaluation on a public chest radiograph dataset demonstrates significant improvements over baseline vision-language models, achieving gains from 0.0493 to 0.3359 in BLEU-1, 0.0863 to 0.2440 in ROUGE-L, and 0.0829 to 0.1708 in METEOR, along with substantial improvements in semantic evaluation metrics such as Consistency (2.38 to 7.80) and Accuracy (2.34 to 6.93). The results highlight the effectiveness of structured multi-agent perception and reasoning for enhancing robustness, transparency, and automation in intelligent medical imaging systems, enabling integration into autonomous healthcare and robotic diagnostic workflows.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2605.17779

Learning Variable-Length Tokenization for Generative Recommendation

作者:

Minhao Wang↗Bowen Wu↗Wei Zhang↗

arXiv:2605.17779v2 Announce Type: replace Abstract: Generative recommendation reformulates recommendation as next-token prediction over discrete semantic identifiers (IDs). A fundamental yet unexplored design choice is that existing methods employ fixed-length tokenization for all items, implicitly assuming uniform encoding capacity regardless of item characteristics. Through systematic experiments across four datasets, we discover the Popularity-Length Paradox: popular items achieve optimal performance with short IDs, while tail items require substantially longer codes to capture discriminative semantics. This reveals a critical mismatch where popular items benefit from abundant collaborative signals and require minimal semantic detail, whereas tail items must rely on fine-grained content features due to sparse interaction data. To address this, we propose VarLenRec, a framework for learning variable-length tokenization. We develop Popularity-Weighted Information Budget Allocation (PIBA), an information-theoretic framework proving that optimal ID length should scale as a negative power of popularity. Directly implementing variable-length allocation faces two technical challenges: standard Euclidean residual quantization lacks geometric capacity to support diverse code lengths without distortion, and discrete length decisions are non-differentiable. We address these through Hyperbolic Residual Quantization, which leverages the exponential volume growth of the Poincaré ball to naturally stratify encoding capacity, and a Soft Length Controller, which enables differentiable length prediction via continuous layer retention probabilities regularized by PIBA-derived priors. Extensive experiments demonstrate that VarLenRec achieves significant improvements over state-of-the-art methods in recommendation accuracy and training/inference efficiency, revealing the importance of adaptive encoding capacity in generative recommendation.

阅读与讨论 → 访问原文 →

09.

medRxiv (Medicine) 2026-06-15 DOI: HASH:7dfa5bfb4f75632db783f85e7e0083d7

Investigation of Intra-Fraction Stability and Inter-Fraction Reproducibility of Deep Inspiration Breath-Hold Across Two Hypofractionated Radiotherapy Regimens in the HYPORT Adjuvant Study.

作者:

MAHATA↗Roy↗Khatua↗Maity↗Barik↗Chakraborty↗Chatterjee↗

Background: Deep Inspiration Breath Hold (DIBH) is a widely used respiratory motion management technique for minimizing cardiac dose in left-sided breast radiotherapy. In the Breast HYPORT Adjuvant study, DIBH was employed for cardiac sparing in patients without nodal irradiation using a standardized institutional protocol with the Varian Real-time Position Management (RPM) system. Both moderate-hypofractionation (control arm - 40Gy in 15 fractions) and one-week hypofractionation (experimental arm - 26 Gy in 5 fractions) regimens were delivered using this protocol. This study aimed to evaluate the robustness of DIBH by analyzing intra-fraction stability and inter-fraction reproducibility of breath-hold amplitude across the two treatment regimens. Methods: Respiratory waveforms acquired during each treatment session were analyzed to determine the median breath-hold amplitude and its standard deviation during beam delivery. Intra-fraction stability was assessed from vari- ations within individual treatment sessions, while inter-fraction reproducibility was evaluated relative to the simula- tion waveform amplitude across all treatment sessions. These parameters were compared between the two HYPORT regimens to examine breath-hold consistency during treatment delivery. Moreover, an additional comparison was made between the one-week hypofractionation regimen and the first five fractions of the moderate-hypofractionation regimen to evaluate the effect of treatment duration . Lung volumes from free-breathing and DIBH CT scans were analyzed to assess the effectiveness of patient breath-hold training. Results: Both arms demonstrated an average 1.7-fold increase of air volume in lung during the breath-hold position, confirming the effective implementation of DIBH during treatment planning and delivery. Structured training resulted in increased breath-hold amplitudes, with gains of 22.87% and 24.16% with respect to the first trial session in the experimental and control arms, respectively. Both regimens receive equivalent doses for approximately the same air volume in lung . Despite the different prescription doses in the two arms (26 Gy vs. 40 Gy), the experimental arm achieved an equivalent mean heart dose of 2.91% (75.6 cGy) compared with 2.95% (118.51 cGy) in the control arm, suggesting a similar cardiac preservation protocol adopted during treatment planning. Intra-fraction stability was similar between the control arm and the experimental arm, with median amplitude variations of 1.006 mm (95% CI: [0.998-1.015]) and 1.079 mm (95% CI: [1.067-1.097]), respectively. In contrast, inter-fraction reproducibility improved in the experimental arm, with lower deviation from simulation amplitude (0.44 {+/-} 0.24 mm vs. 0.66 {+/-} 0.25 mm) for the entire treatment schedule. The stability and reproducibility of experimental arm were further compared with the first five fractions of the control arm. The results were similar to those of the experimental arm. Conclusion: In this study, we compared two treatment regimens in terms of intra-fraction stability and inter-fraction reproducibility during DIBH radiotherapy. Both regimens demonstrated comparable intra-fraction stability, indicating effective motion management irrespective of treatment duration. However, the experimental arm showed better inter- fraction reproducibility, suggesting more consistent breath-hold performance throughout the treatment course. Based on stability and reproducibility, a reasonable narrowing of the DIBH gating window may be implemented with minor changes to the institutional protocol. The observed trend highlights the potential for improved consistency with the experimental approach and supports further investigation to better understand the underlying factors and strengthen these findings in future studies.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17930

How Inference Compute Shapes Frontier LLM Evaluation

作者:

Jessica McFadyen↗Ole Jorgensen↗Harry Coppock↗Kevin Wei↗Cozmin Ududec↗

arXiv:2606.17930v1 Announce Type: new Abstract: AI evaluations are shifting toward harder tasks that benefit from longer trajectories involving tool use and iterative problem solving. As a result, performance is increasingly sensitive to the amount and allocation of compute available at test time ("inference compute"). Yet many evaluations still report performance at a single restrictive budget, meaning that low scores may reflect the evaluation setup rather than the model's underlying capability. To test this, we evaluate up to 12 frontier language models on seven challenging benchmarks spanning software engineering, mathematics, medicine, and cybersecurity. We use a controlled setup combining three simple inference-scaling interventions: larger token budgets, context compaction, and repeated submission attempts, guided either by the model itself or by minimal correctness feedback. We find three main results. First, larger token budgets substantially improve performance on benchmarks across multiple domains, including cybersecurity, FrontierMath, Humanity's Last Exam, and TerminalBench. Second, fixed-budget evaluations can increasingly understate frontier capability as models advance. Newer models reach higher performance at large budgets, where they unlock harder tasks and solve them more reliably. Third, benchmarks differ in which inference-scaling methods help most: repeated submission broadly improves performance, but the value of larger token budgets, external feedback, and parallel attempts varies by benchmark. Overall, our results show that benchmark scores are protocol-dependent. We therefore argue that evaluations should report capability as a function of inference-time compute, specify protocol choices explicitly, and compare model generations over a large shared compute range at matched budgets, especially in safety- or policy-relevant settings.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2507.23534

Continual Learning with Support Boundary Experience Blending

作者:

Chih-Fan Hsu↗Ming-Ching Chang↗Wei-Chao Chen↗

Continual learning (CL) seeks to mitigate catastrophic forgetting when models are trained with sequential tasks. A common approach, experience replay (ER), stores past exemplars but only sparsely approximates the data distribution, yielding fragile and oversimplified decision boundaries. We address this limitation by introducing Support Boundary Data (SBD), generated via differential-privacy-inspired noise into latent features to create boundary-adjacent representations that implicitly regularize decision boundaries. Building on this idea, we propose Experience Blending (EB), a framework that jointly trains on exemplars and SBD through a dual-model aggregation strategy. EB has two components: (1) latent-space noise injection to generate support boundary data, and (2) end-to-end training that jointly leverages exemplars and SBD. Unlike standard experience replay, SBD enriches the feature space near decision boundaries, leading to more stable and robust continual learning. Extensive experiments on CIFAR-10, CIFAR-100, Tiny ImageNet, and ImageNet1K demonstrate consistent accuracy improvements of 10%, 6%, 13%, 2%, respectively.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18767

Output Vector Editing for Memorization Mitigation in Large Language Models

作者:

Ahmad Dawar Hakimi↗Kaiwei Lei↗Isabelle Augenstein↗Hinrich Sch\"utze↗

Large language models memorize and reproduce sequences from their training data, creating privacy, copyright, and security risks. Existing neuron-level mitigation methods equate editing with zeroing out neuron activations, but the activation only controls whether a neuron engages; the output vector is what writes to the residual stream and, through superposition, encodes multiple features. We propose output vector editing, a constrained-optimization weight edit that locates a small set of MLP neurons responsible for a memorized continuation and minimally modifies their output vectors to introduce a distractor in vocabulary space, redirecting their residual-stream contributions while leaving activations unchanged. Evaluating on four models from 360M to 7B parameters (SmolLM-360M, OLMo-1B, OLMo-7B, Llama2-7B), we center on OLMo-7B (whose open weights and pretraining corpus enable systematic mining) and mine 6831 memorized sequences, achieving up to 87.9% suppression. The 2.7$\times$ gap over zero ablation on the same located neurons shows the suppression comes from the output-vector edit, not localization alone. Four edit modes span a spectrum from aggressive suppression to minimal redirection; in ensemble they cover 96.5% of memorized sequences, while our recommended single-mode configuration reaches 81.5% with no catastrophic locality failures. We further identify a mechanistic boundary at ${\sim}14%$ of sequences unreachable by MLP-only editing; while these failures are not attention-driven overall, ablating the top contributing attention heads recovers 60–64% of them, with stronger recovery on continuations that copy tokens from the prefix, positioning attention as a complementary fallback rather than a primary mechanism. Edit mode ordering and the success-locality trade-off transfer across all four models, with success rates scaling with model size rather than family.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.19184

When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift

作者:

Dat Nguyen↗Cosmin Radoi↗Romain Hermary↗Marcella Astrid↗Nesryne Mejri↗Enjie Ghorbel↗Djamila Aouada↗

Recent advances in generative AI, such as diffusion models and face-swapping tools, have enabled the creation of highly realistic deepfakes, leading to real-world harms including financial fraud and non-consensual explicit content. In response, deepfake detection has become an active research area, with recent methods increasingly focusing on improving generalization to unseen manipulations. This is typically evaluated using the Area Under the ROC Curve (AUC) measured separately across multiple datasets. However, such an evaluation fails to reflect real-world scenarios where detectors face a mixture of data sources and varying artifact types. To address this limitation, we introduce a novel metric, Cross-dataset AUC (Cross-AUC) that averages per-domain AUCs with a measure of prediction polarization for taking into account the robustness to domain shift. The polarization extent is quantified by the Wasserstein Distance between class score distributions. Cross-AUC not only assesses the generalization capabilities of deepfake detectors under domain shifts more realistically, but it is also interpretable as it better explains the reason behind a drop in performance. Experiments performed on seven benchmark datasets demonstrate its practical relevance.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.18198

Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners

作者:

Xiaojun Jia↗Jie Liao↗Simeng Qin↗Ke Ma↗Wenbo Guo↗Yebo Feng↗Aishan Liu↗Yang Liu↗

Agent skills are emerging as an important attack surface in LLM-based systems. Through an empirical study of existing skill scanners, we find that current defenses primarily rely on textual descriptions, manifests, and source code as the main signals for security analysis, which can leave visually conveyed malicious intent insufficiently examined. This creates a practical blind spot: harmful operational instructions hidden in images may bypass scanning while still being recoverable by multimodal agents during deployment. To systematically investigate this threat, we propose SkillCamo, a document-mediated multimodal instruction attack that conceals malicious instructions within images bundled with a skill while rewriting the surrounding documentation to naturally reference those images as part of the normal workflow. Thus, the attack does not rely on the image alone, but on the joint interpretation of textual guidance and visual payload at execution time. To defend against such attacks, we further propose ExecScan, an execution-grounded multimodal scanning module that performs intent extraction, behavior reconstruction, abuse assessment, and deliberative execution simulation over skill artifacts. ExecScan jointly analyzes documentation, code, referenced resources, and visual content to recover hidden instructions, reconstruct executable behavior chains, and identify downstream risks such as exfiltration, destruction, persistence, deception, and privilege escalation. Extensive experiments show that image-hidden malicious instructions challenge existing skill scanners, while ExecScan can improve the skill scanning performance.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2605.01733

GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models

作者:

Zeshang Li↗Shuoyang Zhang↗

Vision-Language Models (VLMs) hallucinate objects that are not present, and a growing line of work tries to curb this by feeding the model its own generated caption as auxiliary evidence – assuming that a caption, once available, is something to consume. We show this fails: naively appending a caption can lower accuracy rather than raise it, dropping Qwen2.5-VL-3B$^\dagger$ on HallusionBench by nearly ten points. To understand why, we build GD-Probe, a diagnostic set that pairs a global and a detail question on the same image, so that any difference in caption effect is attributable to the question alone. Caption utility proves to be a per-query property: the same caption helps global questions and harms detail ones, through a single mechanism – an embedded caption competes with the image for attention and pulls the model's evidence onto its own text – whose sign is set by whether the caption covers the queried content. Crucially, this regime is readable from quantities the decoder already emits, with no attention access or grounding. We turn this into GEASS (Gated Evidence-Adaptive Selective Caption Trust), a training-free, logit-level module that decides per query how much of the caption to trust, gating it by the clean path's confidence, weighting it by the entropy reduction it induces, and raising the evidence bar when the two pathways disagree. Across four VLMs and two benchmarks (POPE and HallusionBench), GEASS improves over both vanilla inference and contrastive decoding under a single fixed setting, adding only two forward passes and no parameters.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12881

Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study

作者:

Yvonne Qiu↗Dezhi Yu↗ShuoJia Fu↗

We present an approach to fine-tuning large language models using Direct Preference Optimization (DPO), a reinforcement learning technique. Our experimental results demonstrate that DPO simplifies the training pipeline, improves computational efficiency, and achieves competitive performance. The evaluation using BLEU, ROUGE, and cosine similarity metrics indicates effective learning and convergence, though further investigation is needed to address observed training instability.

阅读与讨论 → 访问原文 →

17.

medRxiv (Medicine) 2026-06-11 DOI: HASH:d8d224e46c4ce4852adc3a4e7792eaef

A global cross-sectional survey of health professionals' interest-confidence gaps in value-based health care implementation: a learning needs assessment

作者:

Lewis↗Andrews↗Laing↗

Abstract Objectives Value-Based Health Care (VBHC) increasingly guides health system redesign internationally. Despite the increasing availability of VBHC education, gaps remain between health professionals' conceptual understanding of VBHC and their confidence to implement it in practice. This study assessed perceived learning needs and preferences of healthcare professionals across foundational topics essential to VBHC implementation. Design Cross-sectional online survey study Setting and participants The survey was distributed to the global VBHC community and yielded 518 responses. Most respondents were based in the UK and Ireland (51%) and 65% had more than 10 years of experience in the health sector. Participants represented a variety of professional backgrounds, including clinicians (34%), operational or executive managers and leaders (22%), and life sciences or procurement professionals (13%). Primary and secondary outcome measures Primary outcome measures included self-reported interest and confidence across 15 VBHC domains and the magnitude of the gap between them. Secondary outcomes included perceived implementation challenges and preferred VBHC learning approaches, including prior engagement with VBHC-related learning. Results Respondents identified substantial VBHC implementation challenges, including implementing outcome measurement (62.4%), conflicting priorities (57.7%), and resistance to change (56.8%). Interest in all VBHC domains was high (median >= 80/10), while confidence to implement remained substantially lower across most domains (median

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17246

GeoDisaster: Benchmarking Orchestrated Agents for Operational Disaster Geo-Intelligence

作者:

Maram Hasan↗Aman Verma↗Savitra Roy↗Hariseetharam Gunduboina↗Daksh Jain↗Muhammad Haris Khan↗Subhasis Chaudhuri↗Biplab Banerjee↗

Remote-sensing vision-language models (RS-VLMs) have advanced Earth-observation analysis toward visual interpretation and instruction-following, yet fall short of operational geo-intelligence, which demands tool-grounded spatial reasoning and structured, evidence-backed decisions. We introduce GeoDisaster, an operational geospatial disaster reasoning benchmark with 2,921 verified instances across 43 question types and five task families: deforestation monitoring, multi-hazard analysis, building-damage assessment, flood-safe routing, and Sentinel-1 SAR flood monitoring. Instances integrate heterogeneous EO/GIS evidence-optical and SAR imagery, raster masks, vector geometries, road networks, and exposure layers-spanning hazard detection, damage assessment, exposure estimation, and diagnostic report generation. Ground-truth answers are grounded in executable geospatial workflows and deterministic consistency checks, removing the need for language-model annotation. We further propose an orchestrated multi-agent framework with 18 disaster-oriented tools, where role-specialized agents coordinate through explicit execution contracts, aligned via Role-Contract Expectation Alignment (RCEA): failure-aware supervised fine-tuning combined with contract-grounded reinforcement learning over dense step-level signals. Experiments show that GeoDisaster challenges existing RS-VLMs and agentic systems, while RCEA improves tool use, evidence grounding, state consistency, and decision generation.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16774

OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models

作者:

Tianyi Lin↗Chuanyu Sun↗Jingyi Zhang↗Changxu Wei↗Huanjin Yao↗Shunyu Liu↗Xikun Zhang↗Liu Liu↗Jiaxing Huang↗

Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks in real-world systems like OpenClaw. In this work, we aim to develop a framework that automatically constructs such reusable skills to enhance LLMs in tool use, multi-step reasoning, and dynamic environment interaction. To this end, we propose Collective Skill Tree Search (CSTS), a novel tree-search-based skill construction framework that constructs structured, diverse and generalizable tree of skills. The core idea of CSTS is to leverage collective intelligence to jointly search, identify and compose effective skills via two iterative phases: Collective Skill Node Generation (CSN-Gen) and Collective Skill Node Assessment (CSN-Assess). CSN-Gen exploits collective knowledge from multiple models to explore diverse candidate skills for each subtask, enabling comprehensive skill exploration. CSN-Assess employs multiple models as judges to evaluate and select skill nodes with two scoring mechanisms: (1) collective quality scoring that aggregates independent evaluations to produce a robust estimate of skill effectiveness, and (2) collective transferability scoring that explicitly verifies whether a skill generalizes well across different models. With CSTS, we construct a set of comprehensive tree of skills along with skill-augmented training data, enabling models to effectively learn and utilize skills. Besides, we introduce Collective Skill Reinforcement Learning, which actively selects multiple relevant skills from the tree to broaden solution-space exploration, avoid being trapped by a single skill and its resulting homogeneous or suboptimal solutions. As a result, our trained model, OpenClaw-Skill, exhibits outstanding agentic capabilities in long-horizon planning, tool use and generalization over challenging benchmarks.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12918

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

作者:

Chejian Xu↗Zhaorun Chen↗Jingyang Zhang↗Freddy Lecue↗Avni Kothari↗Sarah Tan↗Wenbo Guo↗Bo Li↗

arXiv:2606.12918v1 Announce Type: cross Abstract: Hierarchical multi-agent systems (MAS) are rapidly being deployed in high-stakes workflows across domains such as finance and software engineering. In these systems, safety and security are inherently distributed across role-specialized agents, significantly expanding the attack surface, particularly under coordinated adversarial behaviors such as privilege escalation and cross-agent collusion. Existing red-teaming approaches for MAS remain limited: they rely on heuristic selection of target agents and perturb isolated message streams, leaving critical questions unanswered as which agents are most responsible for system safety, and how compromised agents can coordinate to bypass defenses. We propose MAStrike, a closed-loop framework for collusive red-teaming in hierarchical MAS. We propose the first agent-level Shapley value analysis for MAS, quantifying each agent's marginal contribution to system robustness under task-specific distributions. GGuided by this attribution, MAStrike identifies vulnerable agent coalitions and generates coordinated, role-aware adversarial manipulations. These attacks are iteratively refined through structured causal diagnosis, attributing failure cases to uncompromised agents that block adversarial attempts. We further build a comprehensive MAS red-teaming benchmark and controllable environments spanning diverse hierarchical topologies and domains, including finance, software engineering, and CRM. Extensive experiments across MAS built on multiple frontier models show that MAStrike substantially outperforms heuristic baselines. Our analysis further uncovers non-trivial Shapley value distributions and higher-order interaction structures among agents, revealing critical vulnerabilities and coordination patterns that are overlooked by prior single-agent or template-based methods.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13571

Existence Precedes Value: Joint Modeling of Observational Existence and Evolving States in Time Series Forecasting

作者:

Yifan Hu↗Hongzhou Chen↗Peiyuan Liu↗Yiding Liu↗Zewei Dong↗Jiang-Ming Yang↗

arXiv:2606.13571v1 Announce Type: cross Abstract: Real-world time series are often highly incomplete and irregular due to sensor dormancy, transmission delays, and event-driven sampling, making reliable forecasting fundamentally challenging. Existing methods have evolved from impute-then-forecast pipelines to continuous-time models such as Neural ODEs and continuous-time graph networks. While these approaches improve the modeling of historical irregularity, they still rely on an implicit oracle assumption at inference time: the timestamps of future valid observations are presumed to be known in advance. This assumption limits practical relevance, since in many real systems the more fundamental question is not only what the future value will be, but also whether a valid observation will occur at all. In this paper, we propose Timeflies, a unified framework that reformulates forecasting as a joint problem of future observability inference and value estimation. To explicitly model the interaction between observation dynamics and state evolution, Timeflies adopts an observation stream and a value stream, coupled through three dedicated modules for reliability-aware embedding, observation-guided dependency modeling, and joint prediction. We further construct Shadow, a benchmark that combines natural missingness from public datasets with real-world industrial data, and introduce the Observation-Value Joint Entropy (OVJE) metric to comprehensively evaluate this coupled predictability. Extensive experiments show that Timeflies consistently outperforms existing methods, highlighting the importance of explicitly modeling future observability in time series forecasting with missing values. Code and dataset are available in https://github.com/ant-intl/Timeflies.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2605.04893

Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics

作者:

Dominik Dahlem↗Diego Maniloff↗Mac Misiura↗

When a language model processes a hallucinated response, its attention routing tends to fail in one of two shapes: over-concentrating on a narrow set of positions, or spreading so diffusely that relevance is diluted, and the shape of the failure carries diagnostic signal. We study these shapes as a diagnostic characterization, computed from attention matrices under forced scoring of benchmark-labeled responses rather than during live generation. A widely used family of spectral methods analyzes the symmetric component of the degree-normalized attention operator, which governs transport capacity; we prove that every transpose-invariant spectral diagnostic of this operator is structurally orientation-blind (it cannot distinguish an operator from its transpose, and therefore cannot detect information-flow direction), with a converse to the blindness theorem bounding any Lipschitz diagnostic's transpose sensitivity by the asymmetry coefficient $G$. Pairing this with a closed-form bipartite-Cheeger landscape for canonical causal architectures, we show that uniform causal attention satisfies an $n$-independent floor $\phi \ge 1/5$, while window attention pierces the floor as $O(w/n)$; failure modes are shape-different, not just value-different. This floor is an idealized-architecture benchmark, not an empirical attractor: the fraction of real attention heads that pierce it is itself an architectural signature. The resulting two-axis diagnostic ($\phi$ for capacity, $G$ for direction) yields a falsifiable polarity prediction: bottleneck- and diffuse-dominated benchmarks should exhibit opposite polarity. Under length-controlled evaluation, transport features retain interpretable signal (0.62-0.84 LC-AUROC) across the tested decoder-only, encoder-only, and encoder-decoder models, with polarity reversing as predicted between HaluEval and MedHallu.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2604.00730

A CEFR-Inspired Classification Framework with Fuzzy C-Means To Automate Assessment of Programming Skills in Scratch

作者:

Ricardo Hidalgo-Arag\'on↗Jes\'us M. Gonz\'alez-Barahona↗Gregorio Robles↗

arXiv:2604.00730v2 Announce Type: replace-cross Abstract: Context: Schools, training platforms, and technology firms increasingly need to assess programming proficiency at scale with transparent, reproducible methods that support personalized learning pathways. Objective: This study introduces a pedagogical framework for Scratch project assessment, aligned with the Common European Framework of Reference (CEFR), providing universal competency levels for students and teachers alongside actionable insights for curriculum design. Method: We apply Fuzzy C-Means clustering to 2008246 Scratch projects evaluated via Dr.Scratch, implementing an ordinal criterion to map clusters to CEFR levels (A1-C2), and introducing enhanced classification metrics that identify transitional learners, enable continuous progress tracking, and quantify classification certainty to balance automated feedback with instructor review. Impact: The framework enables diagnosis of systemic curriculum gaps-notably a "B2 bottleneck" where only 13.3% of learners reside due to the cognitive load of integrating Logic Synchronization, and Data Representation–while providing certainty–based triggers for human intervention.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2505.03201

Enhancing Visual Feature Attribution via Weighted Integrated Gradients

作者:

Kien Tran Duc Tuan↗Tam Nguyen Trong↗Son Nguyen Hoang↗Khoat Than↗Anh Nguyen Duc↗

arXiv:2505.03201v4 Announce Type: replace-cross Abstract: Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential. A key limitation of IG is its sensitivity to the choice of baseline (reference) images. Multi-baseline extensions such as Expected Gradients (EG) assume uniform weighting over baselines, implicitly treating all baseline images as equally informative. In high-dimensional vision models, this assumption often leads to noisy or unstable explanations. This paper proposes Weighted Integrated Gradients (WG), a principled approach that evaluates and weights baselines to enhance attribution reliability. WG introduces an unsupervised criterion for baseline suitability, enabling adaptive selection and weighting of baselines on a per-input basis. The method preserves the core axiomatic properties of IG in a generalized weighted-baseline form. Under an expected, proxy-based fitness–relevance monotonicity assumption, WG provides a probabilistic justification for assigning larger weights to more informative baselines. Experiments on commonly used image datasets and models show that WG improves over EG under our protocol, with up to 36% gains across evaluated convolutional and Transformer architectures. These gains come with additional fitness-evaluation cost, so WG should be viewed as an attribution-fidelity trade-off rather than a faster alternative to EG. By moving beyond the assumption that all baselines contribute equally, Weighted Integrated Gradients offers a clearer and more reliable approach to explaining computer-vision models, improving both understanding and practical usability in explainable AI.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15034

OSGuard: A Benchmark for Safety in Computer-Use Agents

作者:

Mina Mohammadmirzaei↗Jeffrey Flanigan↗

arXiv:2606.15034v1 Announce Type: new Abstract: Computer-use agents are increasingly evaluated by whether they complete realistic desktop and web tasks. However, task success alone can miss failures in which an agent reaches the nominal goal through an unsafe shortcut. We introduce OSGuard, a dual-granularity benchmark suite for evaluating safety in computer-use agents under benign, unchanged user instructions. OSGuard contains an action-level benchmark for local guardrail decisions and a risk-augmented execution suite for end-to-end evaluation. The action-level benchmark consists of contextualized proposed actions labeled as allowed, unrelated, or unsafe, each judged relative to the original instruction and current interface state. The execution suite contains manually constructed OSWorld-derived task variants in which the original task remains achievable, but the environment is modified to introduce latent hazards such as destructive overwrites, etc. Each variant is paired with augmented evaluators that retain the original task-success criterion while adding explicit state-based safety invariants, allowing us to distinguish safe completions from unsafe completions that satisfy the nominal task objective. Our experimental results on OSGuard show that current multimodal guardrails can perform well on isolated action judgments, while risk-augmented execution exposes remaining gaps between local oversight and reliable end-to-end safety. This dual-granularity design enables more precise diagnosis of whether models can both recognize unsafe proposed actions and improve full-task safety when deployed as guardrails.

阅读与讨论 → 访问原文 →