探索全球前沿学术脉络

01.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18856

Approximate Structured Diffusion for Sequence Labelling

作者:

Nicolas Floquet↗Joseph Le Roux↗Nadi Tomeh↗

Sequence labelling, a core task of Natural Language Processing (NLP), consists in assigning each token of an input sentence a label. From a Machine Learning point of view, sequence labelling is often cast as a Linear-Chain Conditional Random Field (CRF) parametrised by a neural network. While this approach gives good empirical results, CRFs assume a finite decision span (eg label bigrams) which can limit their expressivity and hurt performance when long-range dependencies are required. We show we can leverage diffusion to train a CRF conditioned on an entire label sequence, with the caveat that the condition is on a noisy version of labels. We show experimentally that this method, in conjunction with approximate CRF inference, improves label accuracy with a 16.5% error reduction for POS-tagging.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.17858

Meta-classification of one-class classification models using ranking correlation and nearest neighbor

作者:

Toshitaka Hayashi↗Hamido Fujita↗Dalibor Cimr↗Richard Cimler↗Jitka K\"uhnov\'a↗

arXiv:2606.17858v1 Announce Type: new Abstract: Machine Learning (ML) techniques have been applied to various problems. However, applying ML to ML models is an unexplored direction. For this purpose, this paper considers a meta-classification of one-class classification (OCC) models, because all ML models could be approximated as OCC models. The proposal represents OCC models as normality rankings and classifies them using nearest-neighbor and ranking-correlation metrics. The experiment classifies OCC models, where classes correspond to training datasets, algorithms, and hyperparameters. The proposal achieves high accuracy when class labels are datasets. Moreover, it can classify algorithms when the training datasets contain the same class. In addition, the discussion highlights that the classification of OCC models is essentially the classification of datasets that treats multiple samples as a single input. The experiment demonstrates the classification of datasets using sleeping records. The proposed method can provide a unified solution for classifying OCC models, datasets, and rankings. Source code is uploaded to the public repository https://github.com/ToshiHayashi/ClassOCC.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17678

See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL

作者:

Yilian Liu↗Sicong Leng↗Guoshun Nan↗Junyi Zhu↗Jiayu Huang↗Minghao Sun↗Xuancheng Zhu↗Yisong Chen↗Zexian Wei↗Xiaofeng Tao↗

Multimodal large language models (MLLMs) integrate strong text reasoning with visual inputs, yet their responses can be inconsistent with the underlying images, indicating ineffective utilization of visual evidence during inference. The prevailing training paradigm relies on large-scale caption-based pretraining for general alignment, followed by supervised fine-tuning and reinforcement learning to enable instruction following and complex reasoning. However, such pretraining provides only weak visual grounding: short, coarse captions bias models toward salient objects while neglecting fine-grained visual evidence. In this paper, we introduce Visual Evidence Pre-Alignment (VEPA), an intermediate stage between pretraining and post-training that explores a novel sufficiency-driven objective with Group Relative Policy Optimization (GRPO) to optimize question-conditioned visual evidence descriptions. Extensive experiments across diverse benchmarks show that our VEPA consistently enhances performance on visually demanding evaluations and complements standard supervised post-training. Further analyses show that the income stems from strengthened, transferable visual grounding, rather than from additional task-specific training.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.12277

Finding Multiple Interpretations in Datasets

作者:

Matthew Chak↗Paul Anderson↗

arXiv:2606.12277v1 Announce Type: new Abstract: In this paper, we propose an approach to finding sets of similar-performing models (in terms of loss/accuracy measurements) with highly different context-aware characteristics. Through experiments on the METABRIC dataset, we show that the proposed method finds multiple models with highly different gene expressions than those found by the control methodology without performance penalties. We argue that the proposed methodology is important whenever one aims to analyze any global characteristic of a model to extract insight into the underlying phenomenon being studied.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.07040

Beyond Rubrics: Exploration-Guided Evaluation Skills for Reward Modeling

作者:

Xing Yue↗Linjuan Wu↗Daoxin Zhang↗Yongliang Shen↗Weiming Lu↗

Open-ended reward modeling requires judges that can follow subtle, domain-specific preferences when verifiable answers are unavailable. Existing rubric-based methods often address this by generating criteria online for each query, but the extra generation step can add inference overhead and produce rigid or misaligned guidance. We introduce Eval-Skill, an exploration-guided method that synthesizes reusable evaluation skills for reward modeling and reframes reward guidance as context evolution rather than parameter training or per-query rubric generation. Using only 100 cases per domain for skill evolution, Eval-Skill synthesizes reusable domain-level evaluation skills through two progressive stages, workflow generation followed by principle generation, with exploration and selection interleaved across both stages. Once generated, a skill is directly injected into the judge context. Across multiple RM benchmarks, Eval-Skill consistently improves diverse judge backbones; on RewardBench 2, it yields significant gains over vanilla judging for each main backbone (+13.44% for Qwen3-8B, and 18.51% for DeepSeek-V4-Flash). Further analyses of evolution-time scaling, generalizability, and transferability show that compact evaluation skills offer an efficient new paradigm for LLM-based evaluation. Code is available at https://github.com/xing-stellus-yue/Eval-Skill.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.04935

What Type of Inference is Active Inference?

作者:

Wouter W. L. Nuijten↗Mykola Lukashchuk↗Thijs van de Laar↗Bert de Vries↗

arXiv:2606.04935v2 Announce Type: replace Abstract: Active inference casts decision-making as inference, with the Expected Free Energy (EFE) unifying goal-directed and information-seeking behavior. Recent work showed that EFE minimization can be written as Variational Free Energy (VFE) minimization on a generative model augmented with epistemic priors. We prove that the VFE of the augmented model can be rewritten as the VFE of the predictive model plus explicit entropy-correction terms, making the EFE contribution transparent. We then show that proper EFE-based planning requires combining these epistemic corrections with a planning correction that turns marginal inference into policy optimization, yielding a full variational characterization of EFE-based planning. This clarifies which corrections are needed for cross-entropy planning and for full EFE-based planning. The same entropy-corrected formulation leads to a detailed message-passing scheme for EFE-based planning together with simpler ablations. Experiments on three grid-world environments show that full EFE-based planning outperforms ablations that omit either the planning correction or the epistemic corrections.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11447

AI Coding Agents Can Reproduce Social Science Findings

作者:

Meysam Alizadeh↗Mohsen Mosleh↗Fabrizio Gilardi↗Atoosa Kasirzadeh↗Joshua Tucker↗

Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic evaluation across social sciences remains limited. Existing evaluation benchmarks are insufficient, either small or conflate agent performance with problems in the reproduction materials themselves, such as code that fails to execute correctly. Here we introduce SocSci-Repro-Bench, a benchmark of 221 tasks spanning four disciplines and 13 substantive domains, constructed from studies whose results are either fully reproducible with available materials or demonstrably non-reproducible due to missing data, allowing us to isolate agents' reproduction capacity. Evaluating two frontier coding agents, Claude Code and Codex, we find that both can reproduce a large share of social science findings, with Claude Code substantially outperforming Codex. These reproduction rates considerably exceed those previously reported for general-purpose LLM-based agents on comparable reproducibility benchmarks. Both agents also perform strongly on a reasoning task requiring identification of underlying research questions, and additional analyses suggest that results are not primarily driven by memorization. Providing the original paper PDF alongside replication materials modestly improves performance but introduces bias on tasks where reproduction is impossible. We also show that agents can be nudged toward confirmatory specification search through subtle prompt framing. Together, these findings suggest that at least some frontier coding agents can serve as reliable executors of computational workflows while underscoring the need for careful benchmarking and prompt design as AI systems assume larger roles in scientific production.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2401.14381

Manifold GCN: Diffusion-based Convolutional Neural Network for Manifold-valued Graphs

作者:

Martin Hanik↗Gabriele Steidl↗Christoph von Tycowicz↗

arXiv:2401.14381v3 Announce Type: replace Abstract: We propose two graph neural network layers for graphs with features in a Riemannian manifold. First, based on a manifold-valued graph diffusion equation, we construct a diffusion layer that can be applied to an arbitrary number of nodes and graph connectivity patterns. Second, we model a tangent multilayer perceptron by transferring ideas from the vector neuron framework to our general setting. Both layers are equivariant under node permutations and the feature manifold's isometries. These properties have led to a beneficial inductive bias in many deep-learning tasks. Furthermore, they enable novel, more flexible feature designs. Numerical examples on synthetic data and an Alzheimer's classification application on triangle meshes of the right hippocampus demonstrate the usefulness of our new layers: While they apply to a much broader class of problems, they outperform task-specific state-of-the-art networks.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2604.17892

LEPO: Latent Reasoning Policy Optimization for Large Language Models

作者:

Yuyan Zhou↗Jiarui Yu↗Hande Dong↗Zhezheng Hao↗Hong Wang↗Jianqing Zhang↗Qiang Lin↗

arXiv:2604.17892v4 Announce Type: replace-cross Abstract: Recently, latent reasoning has been introduced into large language models (LLMs) to leverage rich information within a continuous space. However, without stochastic sampling, these methods inevitably collapse to deterministic inference, failing to discover diverse reasoning paths. To bridge the gap, we inject controllable stochasticity into latent reasoning via Gumbel-Softmax, restoring LLMs' exploratory capacity and enhancing their compatibility with Reinforcement Learning (RL). Building on this, we propose \underline{L}atent R\underline{e}asoning \underline{P}olicy \underline{O}ptimization~(LEPO), a novel framework that applies RL directly to continuous latent representations. Specifically, in rollout stage, LEPO maintains stochasticity to enable diverse trajectory sampling, while in optimization stage, LEPO constructs a unified gradient estimation for both latent representations and discrete tokens. Extensive experiments show that LEPO significantly outperforms existing RL methods for discrete and latent reasoning.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14230

A Multi-Domain Feature Fusion Framework for Generalizable Deepfake Detection Across Different Generators

作者:

Amna Amjid↗Sana Qadir↗Mehwish Fatima↗Raja Khurram Shahzad↗

Deepfakes are artificially generated images, audio, or videos that threaten privacy, security, and information integrity. Detecting such content is crucial for countering disinformation, as the latest models generate highly realistic content. While spatial- or frequency-based approaches achieve good detection rates on Generative Adversarial Networks (GANs)-based generated deepfakes, they often struggle with recent diffusion model-generated images. In particular, existing approaches rarely exploit complementary multi-domain representations or systematically evaluate cross-generator robustness. To address these challenges, we propose a multi-domain deepfake detection framework called SGFF-Net (Spatial-Gradient-Frequency Fusion Network) that integrates spatial, gradient, and DWT (Discrete Wavelet Transform)-based frequency representations within a dual residual learning architecture. Experimental results show that the SGFF-Net achieves 98.95\% accuracy in intra-dataset evaluation and improves performance in both cross-model (70.46\%) and cross-paradigm (69.94\%) settings. Incorporating multi-source training and data augmentation further enhances robustness, increasing accuracy from 70.46\% to 79.80\% in cross-model evaluation, from 69\% to 78\% in cross-paradigm evaluation, and from 61.50\% to 75.80\% on real-world data. Unlike single-domain detectors, the SGFF-Net learns complementary forensic cues across spatial, gradient, and wavelet-frequency domains, resulting in greater robustness under cross-generator and cross-paradigm evaluation. The results further show that combining multi-domain representations with data diversity and augmentation substantially improves generalization, providing practical insights for developing more reliable deepfake detection systems.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19350

Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models

作者:

Amogh Sheth↗Biruk Assefa↗Yi Wen Huang↗Andrew Lin↗Yuhao Ge↗

Large language models (LLMs) excel at multi-step reasoning but incur substantial inference cost. We introduce Causal Attribution Pruning (CAP), a training-free method that identifies critical attention heads by measuring their causal impact on reasoning tasks and uses these head-level scores to guide fine-grained weight pruning. For each attention head, CAP estimates the expected performance degradation when the head is masked during forward passes on a small calibration set of reasoning problems. These causal scores are then converted into weight-level importance values for the corresponding projection matrices. Unlike magnitude-only or activation-based criteria, CAP's interventional measurement directly captures each head's functional contribution, yielding relative accuracy gains of up to 61% over Wanda on ARC-Challenge at 20% sparsity. We evaluate CAP on GSM8K, StrategyQA, and ARC-Challenge using Llama-3-8B-Instruct and Mistral-7B-Instruct at 10%, 20%, and 50% sparsity. At moderate sparsity (10-20%), CAP improves over Wanda in most model-benchmark configurations. with especially large gains on ARC-Challenge for Llama-3. Our results suggest that attention-head-level causal attribution can better preserve reasoning performance on downstream benchmarks than correlational pruning criteria at equivalent sparsity, while remaining limited by coarse MLP attribution at 50% sparsity.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11688

Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agents

作者:

Youwang Deng↗

Long-horizon LLM agents are not trusted to run unattended: with no human watching, they confidently report success they never verified. We treat honesty – bounding what an agent may claim at termination – as a first-class metric for unattended autonomy, distinct from capability. We present Autopilot, an execution model that makes silent fabricated success structurally impossible rather than merely rarer. Autopilot externalizes all working state into a durable, gated finite-state machine that a scheduler advances one stateless tick at a time; a hard floor forbids any terminal "done" claim whose falsifiable gate did not actually execute and pass. We prove a No-False-Success theorem – under gate soundness, floor enforcement, and plan coverage, termination implies the goal holds – whose only trust points are empirically measurable, and show the worst case degrades to an honest stall, never a fabricated success. Because each tick rehydrates only the state machine, per-step context cost is constant in the horizon. Across a 3,150-cell paired corpus (70 tasks $\times$ 3 systems $\times$ 3 models $\times$ 5 seeds, including 50 SWE-bench Lite tasks across 11 OSS repos), Autopilot fabricates on 0.95% of cells [95% CI 0.38–1.62] while Reflexion and StateFlow baselines fabricate on 8.10% [6.48–9.81] and 25.05% [22.48–27.62] respectively. The headline contrast lives in the hard regime: on SWE-bench Lite, the firewall reduces fabrication from 33.7% (StateFlow) to 0.67%, a paired difference of $-33.07$ pp [95% CI $-36.53, -29.73$]. The mechanism is the gate, not the model: all ten Autopilot fabrications come from the strongest model, while two weaker mid-tier models never fabricate across 700 paired cells. The firewall trades coverage for honesty by design – an honest stall is recoverable; a confident wrong output shipped downstream is not.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2510.11709

Adversarial Attacks Leverage Interference Between Features in Superposition

作者:

Edward Stevinson↗Lucas Prieto↗Melih Barsbey↗Tolga Birdal↗

Why do adversarial examples exist, and why do they transfer between models? Existing explanations appeal to high-dimensional geometry, non-robust patterns in the input, and decision boundary structure, but none provides a representation-level mechanism that explains why specific perturbations succeed and why attacks transfer between models. In this paper, we show that adversarial vulnerability can stem from efficient information encoding in neural networks. Specifically, vulnerability can arise from superposition - the phenomenon where networks represent more concepts than they have dimensions, forcing non-orthogonal representation and thus interference. This interference causes perturbations targeting one representation to affect others, creating vulnerabilities determined by interference patterns. In synthetic settings with precisely controlled superposition, we establish that superposition suffices to create adversarial vulnerability. The resulting attacks are predictable: PGD-discovered perturbations align with theoretically optimal perturbations derived from the interference geometry. Models trained on similar data develop similar interference patterns, explaining attack transferability. We then show that successful attacks on image classifiers exhibit the structure predicted by our proposed mechanism. These findings reveal that adversarial vulnerability can be a byproduct of networks' representational compression, complementing existing explanations based on data properties or architectural factors.

阅读与讨论 → 访问原文 →

14.

PLOS Computational Biology 2026-05-29 DOI: HASH:cc669b926902037f882a9e0dc528ff9f

Structural and dynamic basis of NOD2 tandem CARD association and NOD1/2–RIP2 signaling complexes

作者:

Jitendra Maharana↗

by Jitendra Maharana, Aritra Bej, Debasish Biswal, Debashis Panda, Arjun Sharma NOD1 and NOD2, founding members of the NOD-like receptor (NLR) family, play a crucial role in host defense against bacterial infections. Recognition of peptidoglycan-derived ligands triggers ATP-dependent oligomerization of the NACHT domain, exposing the CARD domains that recruit the adaptor protein RIP2 via CARD–CARD interactions to activate the NF-κB signaling cascade. Although NOD1/2-RIP2 interactions and RIP2CARD filament assembly are established, the precise interfaces that stabilize hetero–CARD filaments remain poorly defined. Here, we integrate in silico structural modeling with molecular dynamics (MD) simulations to elucidate structurally compatible arrangements of NOD1–RIP2 and NOD2–RIP2 hetero–CARD filaments. Our results reveal that NOD1CARD subunits form a structurally compatible homomeric scaffold via canonical (type-I–III) interfaces, accommodating multiple tiers of RIP2CARD rings at both filament termini. Meanwhile, the NOD2 tandem CARDs adopt multiple discrete conformations, reflecting a more intricate structural mechanism. In stable filament conformations, tandem CARDs converge at the type-II interface, with RIP2CARD rings stacking onto CARDa (top-down) and CARDb (bottom-up) interfaces, highlighting the structural role of NOD2CARDb in RIP2-mediated CARD–CARD interaction. In silico mutagenesis, involving charge-reversal and alanine scanning of key interfacial residues, disrupts NOD1–RIP2 and NOD2–RIP2 interactions at both top-down and bottom-up interfaces, leading to rapid interface destabilization within 0.1–0.4 μs of simulation. Together, these results reveal conserved and receptor-specific mechanisms governing NOD1/2–RIP2 CARD–CARD interactions and provide deeper structural and dynamic insights into the complex structural mechanisms for NLR-mediated inflammatory signaling.

阅读与讨论 → 访问原文 →

15.

arXiv (math.PR) 2026-06-12 DOI: arXiv:2510.25740

A mathematical study of the excess growth rate

作者:

Steven Campbell↗Ting-Kam Leonard Wong↗

arXiv:2510.25740v2 Announce Type: replace-cross Abstract: The excess growth rate, defined as the gap in Jensen's inequality for the logarithm, is a fundamental functional in portfolio theory. In this paper, we present a mathematical study motivated by information theory. We begin by establishing its properties and showing that it has rich connections with information theoretic concepts such as the Helmholtz free energy, L. Campbell's measure of average code length and large deviations. Our main results consist of three axiomatic characterization theorems of the excess growth rate, in terms of (i) the relative entropy, (ii) the gap in Jensen's inequality, and (iii) the logarithmic divergence that generalizes the Bregman divergence. Furthermore, we study maximization of the excess growth rate and compare it with the growth optimal portfolio. Our results not only provide theoretical justifications of the significance of the excess growth rate, but also establish new connections between information theory and quantitative finance.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12422

Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering

作者:

Zewei Tian↗Alex Liu↗Lief Esbenshade↗Michael Xiao↗Zachary Zhang↗Yulia L\'apicus↗Thomas Han↗Kevin He↗Min Sun↗

arXiv:2606.12422v1 Announce Type: cross Abstract: The integration of large language models (LLMs) into educational assessment represents a transformative shift in classroom grading practices. While automated scoring systems and machine learning techniques have existed for decades, generative AI (GenAI) now enables educators to implement standards-based grading (SBG) with unprecedented efficiency and scale. This paper examines the theoretical foundations and evaluates an LLM grader that uses commercially available foundation models with context and prompt engineering to score student work against a rubric. Drawing on an empirical interrater agreement study using Massachusetts Comprehensive Assessment System (MCAS) data, we observed the Quadratic Weighted Kappa (QWK) and Proportional Reduction in Mean-Squared Error (PRMSE) across mathematics, science, and ELA, using Claude Sonnet 4, Haiku 4.5, GPT-5, and GPT-5 Mini. The results demonstrate that LLM graders, especially when based on foundational models with more parameters, achieve substantial agreement with human raters in mathematics and science assessments, while the performances vary in ELA, suggesting generic foundation models can be effective at scoring in given contexts. Additional analysis of teacher and student feedback reveals strong acceptance of AI-generated narrative feedback but skepticism toward numerical scores, suggesting that LLMs function most effectively as formative tools rather than summative evaluators. Our findings indicate that thoughtfully designed hybrid models that combine AI efficiency with teacher judgment can reduce workload, enhance feedback quality, and support equitable assessment practices without displacing professional expertise.

阅读与讨论 → 访问原文 →

17.

medRxiv (Medicine) 2026-06-18 DOI: HASH:f2be237771fdfea26f7e95656b356052

Cost-effectiveness of a virtual fracture clinic versus traditional in-person fracture clinic care for adults with acute simple fractures: a protocol for a health economic evaluation within the RECITAL trial

作者:

Charteris↗Traeger↗A. C↗Maher↗C. G↗Copp↗Pickles↗Teng↗M. J↗Khoudair↗Warnock↗Shaw↗…

ABSTRACT Introduction Traditional in-person fracture clinics are often overcrowded and inconvenient for patients. Virtual fracture clinics aim to address some of these concerns by improving the efficiency of the orthopaedic service and reducing unnecessary interventions while maintaining safety and quality of care. The RECITAL trial is a non-inferiority randomised controlled trial comparing follow-up care provided at a virtual fracture clinic for people with acute simple fractures to follow-up care provided at an in-person fracture clinic. This study describes the protocol for an economic evaluation of RECITAL where the primary aim is to investigate the cost-effectiveness of a virtual fracture clinic compared with traditional in-person fracture clinic care from a health system perspective. Methods and analysis The RECITAL trial recruited 312 participants with acute simple fractures and randomised them to receive follow-up care provided at a virtual fracture clinic or follow-up care provided at an in-person fracture clinic. We will conduct a within-trial analysis from a health system perspective (primary analysis), as well as a health service, patient and societal perspective. The economic evaluation will estimate the difference in the cost of resource inputs on an intention to treat basis used by participants in the two arms of the trial, allowing comparisons to be made between the in-person and virtual fracture clinics. Data for intervention costs and healthcare utilisation will be collected from trial records, hospital electronic medical records and district performance units. The results of the economic evaluation will be expressed in terms of incremental cost per utility weight gained at 12 weeks and will be plotted on a cost-effectiveness plane. Bootstrapping by resampling will be used to estimate 95% confidence intervals around costs and outcomes, and to calculate the confidence intervals around the incremental cost-effectiveness ratio. A cost-effectiveness acceptability curve (CEAC) will be plotted, which will provide information about the probability that an intervention is cost-effective, given the level of a decision makers willingness to pay for each additional outcome. Ethics and Dissemination The trail was approved by the SLHD Ethics Review Committee (RPAH Zone) (X23-0200 and 2023/ETH01038). The findings will be disseminated through a peer-reviewed journal and conference presentations. Trial registration number The trial was prospectively registered on the Australian New Zealand Clinical Trials Registry (ANZCTR; 12623000934640)

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2601.03792

VietMed-MCQ: A Consistency-Filtered Data Synthesis Framework for Vietnamese Traditional Medicine Evaluation

作者:

Huynh Trung Kiet↗Dao Sy Duy Minh↗Nguyen Dinh Ha Duong↗Le Hoang Minh Huy↗Long Nguyen↗Dien Dinh↗

Large Language Models (LLMs) have demonstrated remarkable proficiency in general medical domains. However, their performance significantly degrades in specialized, culturally specific domains such as Vietnamese Traditional Medicine (VTM), primarily due to the scarcity of high-quality, structured benchmarks. In this paper, we introduce VietMed-MCQ, a novel multiple-choice question dataset generated via a Retrieval-Augmented Generation (RAG) pipeline with an automated consistency check mechanism. Unlike previous synthetic datasets, our framework incorporates a dual-model validation approach to ensure reasoning consistency through independent answer verification, though the substring-based evidence checking has known limitations. The complete dataset of 3,190 questions spans three difficulty levels and underwent validation by one medical expert and four students, achieving 94.2 percent approval with substantial inter-rater agreement (Fleiss' kappa = 0.82). We benchmark seven open-source models on VietMed-MCQ. Results reveal that general-purpose models with strong Chinese priors outperform Vietnamese-centric models, highlighting cross-lingual conceptual transfer, while all models still struggle with complex diagnostic reasoning. Our code and dataset are publicly available to foster research in low-resource medical domains.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17298

Reasoning Text-to-Video Retrieval for Operating Room Clips via Action-Driven Digital Twins

作者:

Yiqing Shen↗Hao Ding↗Mathias Unberath↗

Text-to-video retrieval in operating rooms (OR) is an enabling technology for OR safety, as it allows stakeholders to retrieve and inspect recordings of specific events. However, because the most safety-critical events may not follow the common structure, to unlock its full potential text-to-video retrieval must be able to handle implicit queries that require reasoning to identify the right video (e.g., the step right before clipping). However, existing methods rely on global embeddings that cannot reason over such queries. We propose OR3, a text-to-video retrieval method that converts clips into action-driven digital twins (ActDTs), grouping concurrent subject-action-object triplets under non-overlapping temporal intervals. Moreover, rather than cross-modal matching through paired encoders, OR3 performs imagination-based retrieval where an LLM generates hypothetical ActDTs from queries. This enables intra-modal matching via a single encoder trained with ActDT-tailored hard negatives. Finally, evidence-grounded refinement revises imagined ActDTs based on discrepancies with top candidates to capture procedure-specific patterns. We construct a benchmark from MM-OR with 276 implicit queries across four reasoning categories over 386 clips from robotic knee procedures. OR3 achieves 57.6 R@1 and 77.3 R@5, outperforming the strongest baseline. These results demonstrate that OR3 enables fine-grained discrimination between visually similar OR video clips through temporal action reasoning.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14772

ScoutVLA: UAV-Centric Active Perception via a Dual-Expert VLA Model for Open-World Embodied Question Answering

作者:

Wenhao Lu↗Zhengqiu Zhu↗Xiaofeng Wang↗Xiaoran Zhang↗Yatai Ji↗Yong Zhao↗Yue Hu↗Yingzhen Nie↗Jinlong Zhu↗Zheng Zhu↗

Aerial Embodied Question Answering (EQA) requires Unmanned Aerial Vehicles (UAVs) to actively perceive the environment and answer natural language questions. Existing outdoor EQA systems usually stop once the target enters the UAV's field of view, leaving the fine-grained viewpoint adjustment needed for evidence-seeking questions largely unresolved. To address this issue, we introduce FG-EQA, a fine-grained active perception EQA benchmark with more than 40K simulated trajectories and 1K real-world trajectories. Drawing inspiration from the ``waggle dance'' of scout bees, which iteratively adjust their flight paths to verify target information, we propose ScoutVLA, an evidence-driven Vision-Language-Action model for outdoor EQA. To emulate this active exploration behavior, ScoutVLA features a decoupled dual-expert architecture: a vision-language expert infers the semantic intent to identify missing evidence, while an independent action expert employs high-DoF flow matching to generate continuous viewpoint-refinement trajectories. To balance the competing demands of continuous control and semantic reasoning, we devise a decoupled training strategy with a knowledge insulation mechanism that prevents the action gradients from erasing the model's multimodal reasoning ability. Extensive simulated experiments and a qualitative real-world field study both verify the superiority of ScoutVLA over the state-of-the-art baselines, demonstrating a 10.48$\boldsymbol{\times}$ higher average strict success rate and a 7.72$\boldsymbol{\times}$ higher average QA correctness.

阅读与讨论 → 访问原文 →

21.

arXiv (quant-ph) 2026-06-19 DOI: arXiv:2504.05237

Measuring Rényi entropy with an Echo Protocol

作者:

Yi-Neng Zhou↗Robin L\"owenberg↗Julian Sonner↗

arXiv:2504.05237v3 Announce Type: replace Abstract: We present efficient and practical protocols to measure the second Rényi entropy, whose exponential is known as the purity. Our approach is based on expressing the purity in terms of transition probabilities generated by an echo-type forward-backward evolution sequence, making it applicable to quantum many-body systems. Notably, our approach does not rely on random-noise averaging, a feature that can be extended to protocols to measure out-of-time-order correlation functions, as we demonstrate. By way of example, we show that our protocols can be practically implemented in superconducting qubit-based platforms, as well as in cavity-QED trapped ultra-cold gases.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12882

HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness

作者:

Xiaoxuan Wang↗Haixin Wang↗Alexander Taylor↗Jason Cong↗Yizhou Sun↗Wei Wang↗

arXiv:2606.12882v1 Announce Type: new Abstract: Large language models are increasingly deployed as agents for long-horizon tasks, yet their performance is shaped not only by model capability and environment design, but also by the harness that mediates agent–environment interaction. Existing harnesses are largely manually engineered, making them difficult to scale as trajectories grow longer and interactions become more complex. In this work, we ask whether harness can be generated by a learnable plug-in module that can be trained in an end-to-end fashion. We introduce HarnessBridge, a lightweight learnable harness controller that parameterizes the agent–environment interface as a bidirectional projection. HarnessBridge learns two bidirectional projections: observation projection, which distills raw trajectories into compact, decision-relevant states, and action projection, which converts proposed actions into executable transitions or trajectory-grounded rejections. We train HarnessBridge on a harness supervision dataset via unified instruction tuning. On Terminal-Bench~2.0 and SWE-bench Verified, HarnessBridge matches or surpasses strong specialized harnesses while substantially reducing token usage and trajectory length, and generalizes from smaller generators to larger commercial models.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.19531

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

作者:

Yuyang Zhang↗Wenyao Zhang↗Zekun Qi↗He Zhang↗Haitao Lin↗Jingbo Zhang↗Yao Mu↗Xiaokang Yang↗Wenjun Zeng↗Xin Jin↗

World Action Models (WAMs) commonly rely on video generation to bridge visual world modeling and robot control. However, video-based WAMs face three coupled limitations: dense multi-frame future tokens make inference costly, full video prediction spends capacity on action-irrelevant temporal and appearance details, and long-horizon future imagination may introduce errors that mislead action prediction. These issues raise a simple question: Does world action model really need video generation? We propose ImageWAM, a simple WAM framework that repurposes pretrained image editing models for robot action prediction. In contrast to video generation, image editing provides a better-matched prior: it only needs to model a target-frame transformation, focuses on action-relevant current-to-target visual differences, and grounds task instructions to localized visual changes through edit pretraining. In practice, ImageWAM does not decode the target frame at inference time; instead, it conditions a flow-matching action expert on the KV caches produced by image-editing denoising, using them as a compact world-action context. ImageWAM outperforms standard VLA baselines and matching competitive WAMs without additional policy pretraining across different simulator and real-world experiments. It also reduces FLOPs to 1/6 and latency to 1/4 of video-based WAMs. Attention analysis further shows that editing caches focus on task-relevant change regions, supporting image editing as an effective alternative to video-based world-action modeling.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11387

Small Experiments, Cheaper Decisions: A Case Study in Staged Promotion for Micro-Pretraining

作者:

Felipe Chavarro Polania↗

Short pretraining runs can reduce experimental cost, but they can also over-promote configurations that only look strong at tiny budgets. We study an auditable staged-promotion protocol for a fixed micro-pretraining runner on two heterogeneous host blocks: Windows A100 and Linux L40S. Starting from twelve prior-screened configurations, we use staged budgets of 2 minutes, 5 minutes, 10 minutes, 60 minutes, and 12 hours, with frozen promotion rules before expensive continuations. The early screens are intentionally treated as unstable: the 5- and 10-minute rankings are host-sensitive, and the eventual 12-hour top-ranked condition is not the mean-best condition at the replicated 10-minute gate. Because seed ranges differ across stages, these changes are operational promotion evidence, not within-seed curves. A replicated 60-minute gate keeps the Staged Factorial Screening bridge reference in the promoted set, where it ranks first in all four 60-minute host-seed cells. In the final 12-hour confirmation package, the bridge condition ranks first in all four host-seed cells across two seeds; the greedy comparator does not meet the frozen 0.010 val_bpb near-equivalence rule; and the cheaper d8/ar48 (depth-8, aspect-48) sentinel does not meet the frozen 0.020 mean-gap rule. The executed 12-hour branch spends 144 GPU-hours, and the full staged protocol records 169.2 training GPU-hours including screening stages. Continuing all four 60-minute candidates would spend 192 GPU-hours, while continuing all nine replicated 10-minute candidates would spend 432 GPU-hours. The latter numbers are accounting counterfactuals for unrun continuations, not evidence that skipped candidates could not have overtaken the reference. The result is a bounded cost-allocation finding, not a claim of global optimality, capacity-normalized superiority, or superiority over adaptive hyperparameter optimization methods.

阅读与讨论 → 访问原文 →

25.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.16418

A short proof of the modified Kretschmann-Schlingemann-Werner conjecture

作者:

Satvik Singh↗

arXiv:2606.16418v1 Announce Type: new Abstract: Let $\Phi_1, \Phi_2 : \mathbb{M}_d(\mathbb{C})\to \mathbb{M}_n(\mathbb{C})$ be two quantum channels with respective Stinespring isometries $V_1, V_2 : \mathbb{C}^{d}\to \mathbb{C}^{n} \otimes \mathbb{C}^{m}$ on any common dilation space $\mathbb{C}^{m}$. We prove that there exists a unitary $U$ on $\mathbb{C}^{m}$ such that $\|V_1-({\bf1}\otimes U)V_2\|_\infty\leq\sqrt{2\|\Phi_1-\Phi_2\|_\diamond},$ thus resolving vom Ende's modification of the Kretschmann-Schlingemann-Werner conjecture in the affirmative.

阅读与讨论 → 访问原文 →