探索全球前沿学术脉络

01.

Science (Express) 2026-05-28 DOI: 10.1126/science.aeb2672

A Hormone Cell Atlas maps the human endocrine system at cellular resolution | Science

作者: 未知作者

Hormones act across tissues and organs to coordinate physiological functions. Drawing inspiration from the Human Cell Atlas, we analyzed expression of 379 hormone and receptor genes in a transcriptomic dataset comprising 14 million single cells and nuclei across 47 human tissues. Using hormone2cell, we mapped putative hormone-producing and hormone-receiving cell types, defining tissue-specific and cross-tissue endocrine signatures. We predicted non-classical sites of hormone expression, including secretin in plasmacytoid dendritic cells, inferred convergent hormone action and endocrine feedback loops, and implicated cell populations in monogenic endocrine disorders. In a cross-tissue integration of adipocyte datasets, we uncovered dynamic endocrine programs across depots, within adipocyte subtypes and through adipogenic differentiation. Cumulatively, the Hormone Cell Atlas ( hormonecellatlas.org.uk ) provides a comprehensive framework for dissecting hormonal impact on health and disease.

阅读与讨论 → 访问原文 →

02.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2606.12545

Spectral analysis of equilibration: information leakage in isolated quantum systems

作者:

Andr\'e T. Ces\'ario↗Marcos G. Alpino↗Reinaldo O. Vianna↗Tiago Debarba↗

arXiv:2606.12545v1 Announce Type: new Abstract: We develop a unified dynamical-spectral framework for equilibration in isolated quantum systems based on a subspace coarse-graining approach. Central to our formulation is the Leakage Fidelity Function (LFF), defined as the probability that a unitarily evolving state escapes the support of its initial subspace. This quantity provides a direct, operational measure of information flow and memory loss without invoking ensemble assumptions or perturbative arguments. We derive universal bounds on temporal fluctuations of the LFF, in terms of the spectral gap structure and the square of the effective dimension, evincing that large spectral delocalization suppresses fluctuations and guarantees equilibration on average. By introducing spectral power distributions and associated entropic measures, we establish a quantitative link between phase mixing, gap participation, and dynamical stability. We further investigate the equilibration timescale by connecting the LFF to quantum speed limits, thereby revealing the average time required for equilibration. Our results provide a state-dependent, geometrically transparent perspective on how spectral complexity and subspace information leakage jointly govern irreversibility in closed quantum many-body systems.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.18195

Learning from the Self-future: On-policy Self-distillation for dLLMs

作者:

Yifu Luo↗Zeyu Chen↗Haoyu Wang↗Xinhao Hu↗Yuxuan Zhang↗Zhizhou Sha↗Shiwei Liu↗

On-policy self-distillation (OPSD) has proven effective for post-training large language models (LLMs), yet its application to diffusion LLMs (dLLMs) remains unexplored. Existing OPSD methods are inherently autoregressive-centric. They inject privileged information via left-to-right prefix conditioning with token-level divergence supervision, a design that fundamentally conflicts with the arbitraryorder generation of dLLMs. We introduce d-OPSD, the first OPSD framework tailored for dLLMs. Our approach makes two core contributions. First, we reframe self-teacher construction by using self-generated answers as suffix conditioning, enabling the student model to learn from "self future-experience" rather than privileged prefixes. Second, we shift supervision from token-level to step-level, aligning training with the iterative denoising process of dLLMs. Experiments across four reasoning benchmarks show that d-OPSD consistently outperforms RLVR and SFT baselines with superior sample efficiency, requiring only around 10% of the optimization steps by RLVR and opening a promising pathway for dLLM posttraining. The code is available at https://github.com/xingzhejun/d-OPSD.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2510.21605

S3OD: Towards Generalizable Salient Object Detection with Synthetic Data

作者:

Orest Kupyn↗Hirokatsu Kataoka↗Christian Rupprecht↗

Salient object detection exemplifies data-bounded tasks where expensive pixel-precise annotations force separate model training for related subtasks like DIS and HR-SOD. We present a method that dramatically improves generalization through large-scale synthetic data generation and ambiguity-aware architecture. We introduce S3OD, a dataset of over 139,000 high-resolution images created through our multi-modal diffusion pipeline that extracts labels from diffusion and DINO-v3 features. The iterative generation framework prioritizes challenging categories based on model performance. We propose a streamlined multi-mask decoder that handles the inherent ambiguity in salient object detection by predicting multiple valid interpretations. Models trained only on synthetic data achieve 20-50% error reduction in cross-dataset generalization, while fine-tuned versions reach state-of-the-art performance across DIS and HR-SOD benchmarks.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18596

Better Adherence, Richer Context: A Field Evaluation of LLM-Powered Conversational Voice Diaries for Sleep

作者:

Amama Mahmood↗Bokyung Kim↗Honghao Zhao↗Molly E. Atwood↗Luis F. Buenaver↗Michael T. Smith↗Chien-Ming Huang↗

arXiv:2606.18596v1 Announce Type: cross Abstract: Sleep diaries are central to behavioral sleep medicine and cognitive behavioral therapy for insomnia, yet daily completion is difficult to sustain, and static forms often provide limited context for interpreting night-to-night sleep variation. We designed an LLM-powered conversational voice diary that delivers clinically grounded morning and evening sleep diary questions through proactive smart-speaker prompts, structured conversational intake, and adaptive follow-up dialogue. We evaluated the system in a four-week between-subjects field study with 30 university students, comparing it with a text-based mobile diary using matched diary items, reporting windows, and reminder intervals. Compared with the text-based diary, the conversational voice diary showed higher adherence and elicited more detailed contextual self-report about routines, stressors, environmental conditions, and other sleep-related factors. Participants also described the voice diary as easier to integrate into daily routines, despite longer perceived completion time. However, voice-based conversational intake produced lower completeness for some structured diary fields, revealing a trade-off between expressive richness and structured precision. These findings show both the promise and the challenge of using LLM-powered conversational voice assistants for longitudinal health self-report.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2510.08807

Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation

作者:

Zhenyu Zhao↗Hongyi Jing↗Xiawei Liu↗Jiageng Mao↗Abha Jha↗Hanwen Yang↗Rong Xue↗Sergey Zakharov↗Vitor Guizilini↗Yue Wang↗

arXiv:2510.08807v2 Announce Type: replace-cross Abstract: From loco-motion to dextrous manipulation, humanoid robots have made remarkable strides in demonstrating complex full-body capabilities. However, the majority of current robot learning datasets and benchmarks mainly focus on stationary robot arms, and the few existing humanoid datasets are either confined to fixed environments or limited in task diversity, often lacking human-humanoid interaction and lower-body locomotion. Moreover, there are a few standardized evaluation platforms for benchmarking learning-based policies on humanoid data. In this work, we present Humanoid Everyday, a large-scale and diverse humanoid manipulation dataset characterized by extensive task variety involving dextrous object manipulation, human-humanoid interaction, locomotion-integrated actions, and more. Leveraging a highly efficient human-supervised teleoperation pipeline, Humanoid Everyday aggregates high-quality multimodal sensory data, including RGB, depth, LiDAR, and tactile inputs, together with natural language annotations, comprising 10.3k trajectories and over 3 million frames of data across 260 tasks across 7 broad categories. In addition, we conduct an analysis of representative policy learning methods on our dataset, providing insights into their strengths and limitations across different task categories. For standardized evaluation, we introduce a cloud-based evaluation platform that allows researchers to seamlessly deploy their policies in our controlled setting and receive performance feedback. By releasing Humanoid Everyday along with our policy learning analysis and a standardized cloud-based evaluation platform, we intend to advance research in general-purpose humanoid manipulation and lay the groundwork for more capable and embodied robotic agents in real-world scenarios. Our dataset, data collection code, and cloud evaluation website are made publicly available on our project website.

阅读与讨论 → 访问原文 →

07.

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 →

08.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2604.18543

ClawEnvKit: Automatic Environment Generation for Claw-Like Agents

作者:

Xirui Li↗Ming Li↗Ion Stoica↗Cho-Jui Hsieh↗Tianyi Zhou↗

Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dataset, but an automated pipeline capable of generating diverse, verified environments on demand. To this end, we introduce ClawEnvKit, an autonomous generation pipeline that instantiates this formalism from natural language descriptions. The pipeline comprises three modules: (1) a parser that extracts structured generation parameters from natural language input; (2) a generator that produces the task specification, tool interface, and scoring configuration; and (3) a validator that enforces feasibility, diversity, structural validity, and internal consistency across the generated environments. Using ClawEnvKit, we construct Auto-ClawEval, the first large-scale benchmark for claw-like agents, comprising 1,040 environments across 24 categories. Empirically, Auto-ClawEval matches or exceeds human-curated environments on coherence and clarity at 13,800x lower cost. Evaluated across 4 model families and 8 agent harness frameworks, we find that harness engineering boosts performance by up to 15.7 percentage points over a bare ReAct baseline, completion remains the primary axis of variation with no model saturating the benchmark, and automated generation enables evaluation at a scale previously infeasible. Beyond static benchmarking, ClawEnvKit enables live evaluation: users describe a desired capability in natural language and obtain a verified environment on demand, turning evaluation into a continuous, user-driven process. The same mechanism serves as an on-demand training environment generator, producing task distributions that adapt to an agent's current weaknesses rather than being bounded by existing user logs.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19690

Multi-Granular Attention-Driven Reinforcement Learning Framework for Web Intelligent Enhancement Systems

作者:

Navin Chhibber↗Deepak Singh↗Anokh Kishore↗Nikita Chawla↗K. Anguraj↗

arXiv:2606.19690v1 Announce Type: new Abstract: From the past few years, web intelligent enhancement systems increasingly rely on heterogeneous and dynamic web data to deliver personalized, context-aware services. However, traditional machine learning, deep learning, and reinforcement learning models often struggle with semantic understanding, adaptability, and scalability in continuously evolving web environments. In this research, a Multi-Granular Attention-based Reinforcement Web Intelligent Enhancement System (MGAR-WIES) is proposed to address the challenges by integrating semantic graph modeling, attention mechanisms, and adaptive reinforcement learning. Initially, heterogeneous web data comprising structured, semi-structured and unstructured sources are collected and preprocessed for generating unified feature representations. These representations are transformed into a dynamic semantic graph, where entities and their relationships are modeled by using graph embeddings enhanced by attention mechanisms for capturing both local relevance and global contextual dependencies. Subsequently, an adaptive multi-agent reinforcement learning strategy leverages the attention-aware semantic states to optimize personalized web actions like content recommendation, navigation optimization, and service adaptation. Finally, the continuous online feedback is further integrated to update graph representations and learning policies in real time by ensuring sustained adaptability and performance. The proposed MGAR-WIES acheived better results in terms of accuracy (80%) when compared with existing approaches.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12552

Crossing the Validation Crisis: Cross-Validation Reduces Benchmarking Variance Surprisingly Well

作者:

C\'elestin Eve↗Ga\"el Varoquaux↗Thomas Moreau↗

arXiv:2606.12552v1 Announce Type: new Abstract: Modern machine learning progresses through empirical work, benchmarking new methods to evaluate relative performance. However, the statistical variability inherent to evaluation - exacerbated by the stochastic nature of many algorithms - often makes performance estimation unreliable due to the limited test samples available, leading to a validation crisis in which genuine advances are difficult to discern. In this work, we show that cross-validation improves markedly confidence when evaluating and comparing learning algorithm performances. We introduce the concept of sample gain, which quantifies the virtual data augmentation achieved by using multiple cross-validation splits to reduce benchmarking variance. Experiments on both synthetic and real-world datasets (histopathologic scans and NLP fine-tuning) demonstrate that multiple splits can substantially improve the reliability and stability of performance estimates, with diminishing returns often setting in later than expected. We also introduce a procedure to dynamically early-stop cross-validation by estimating from the first few folds if subsequent folds will bring large sample gains. Our findings highlight the value of pushing cross-validation on available samples to achieve robust and reliable benchmarking.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2505.23593

Federated Foundation Language Model Post-Training Should Focus on Open-Source Models

作者:

Nikita Agrawal↗Ruben Mayer↗

arXiv:2505.23593v4 Announce Type: replace Abstract: Post-training of foundation language models has emerged as a promising research domain in federated learning (FL) with the goal to enable privacy-preserving model improvements and adaptations to user's downstream tasks. Recent advances in this area adopt centralized post-training approaches that build upon black-box foundation language models where there is no access to model weights and architecture details. Although the use of black-box models has been successful in centralized post-training, their blind replication in FL raises several concerns. Our opinion is that using black-box models in FL contradicts the core principles of federation such as data privacy and autonomy. In this paper, we critically analyze the usage of black-box models in federated post-training, and provide a detailed account of various aspects of openness and their implications for FL.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11437

The Power of Test-Time Training for Approximate Sampling

作者:

Noah Golowich↗Ankur Moitra↗Dhruv Rohatgi↗

arXiv:2606.11437v1 Announce Type: cross Abstract: Efficiently sampling from a complex probability distribution is a fundamental problem which has become increasingly pertinent in recent years with the rise of generative AI, as sophisticated sampling procedures from LLMs have been proposed to solve challenging reasoning problems. The efficacy of such sampling algorithms is limited, however, by the relationship between the LLM and the particular sampling task at hand, which has motivated the framework of test-time training (TTT). TTT works by updating a model's weights in response to partial generations and reward feedback received at inference time, thus adapting to the particular problem. In this work, we propose a formalization for TTT as the problem of producing a sample from a given probability measure $\mu^\star$ belonging to a known class ${F}$ of distributions, given an oracle $\hat \mu$ which yields approximate density estimates for $\mu^\star$. This is closely related to the problem of reducing sampling to approximate counting studied in seminal works of Jerrum, Valiant & Vazirani (1986) and Jerrum & Sinclair (1989): namely, when ${F}$ is the class of all distributions, it coincides exactly with the aforementioned counting-to-sampling reduction. In this paper, we first show a quadratic lower bound on the query complexity of sampling from $\mu^\star$ given query access to $\hat \mu$ (for sufficiently large classes ${F}$), thus showing that the random walk approach proposed by Jerrum & Sinclair (1989) and refined by Hayes & Sinclair (2010), is optimal. This answers an open question posed by Hayes & Sinclair. We then show that this lower bound can be circumvented if the size of ${F}$ is bounded appropriately. As we discuss, this latter result can be viewed as an abstraction of TTT, and thus represents a starting point for the development of a principled theoretical framework for TTT.

阅读与讨论 → 访问原文 →

13.

medRxiv (Medicine) 2026-06-22 DOI: HASH:ab832c1c75b9d8d315a8a3f945908280

Disentangling adiposity-related and non-adiposity-related genetic pathways for type 2 diabetes

作者:

Su↗C.-Y↗Lu↗

OBJECTIVE To identify circulating proteins associated with type 2 diabetes (T2D) risk through pathways not fully explained by body mass index (BMI), and to assess therapeutic actionability. RESEARCH DESIGN AND METHODS We applied GWAS-by-subtraction within a genomic structural equation model to European ancestry summary statistics for T2D (74,124 cases, 824,006 controls) and BMI (n = 681,275), partitioning T2D liability into BMI-related and BMI-subtracted components. We then performed proteome-wide Mendelian randomization (MR) using cis-protein quantitative trait loci from four plasma proteomics cohorts: ARIC, deCODE, Fenland, and the UK Biobank Pharma Proteomics Project. Prioritized proteins passed sensitivity analyses with alternative MR methods and were supported by colocalization evidence. Tissue-resolution regulatory support was assessed using cis-eQTL colocalization across GTEx and pancreatic islet, subcutaneous adipose, and whole-blood resources. Actionability was evaluated using the druggable genome and Open Targets. RESULTS GWAS-by-subtraction attenuated the genetic correlation between BMI and BMI-subtracted T2D from 0.54 (SE 0.02) to 0.35 (SE 0.02). Proteome-wide MR prioritized 29 proteins for BMI-subtracted T2D. Thirteen showed eQTL colocalization in at least one tissue, implicating liver and intermediary metabolism (GCDH, NOTCH2), pancreatic islet biology (CTRB2, MANBA), adipose and Wnt signaling (RSPO3, GALNT3), and whole blood regulatory signals (PAM, SNUPN). Sixteen proteins were classified within druggable-genome Tiers 1-3, and five had existing Open Targets compounds. CONCLUSIONS Integrating GWAS-by-subtraction, proteome-wide MR, and colocalization nominated 29 proteins associated with T2D liability not fully explained by BMI. These findings highlight genetically supported targets for follow-up studies of T2D therapies that complement weight-centered approaches.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17627

Divide, Deliberate, Decide: A Multi-Agent Framework for Fine-Grained Egocentric Action Recognition

作者:

Alessandro Sottovia↗Alessandro Torcinovich↗Oswald Lanz↗

Fine-grained action recognition in egocentric video is challenging for Vision-Language Models (VLMs): actions often differ only in small visual cues, and a single model tends to be biased toward a subset of these cues. We propose Divide, Deliberate, Decide, a fully-local, zero-shot multi-agent framework in which (i) a VLM orchestrator chunks the video and proposes a top-k candidate label list per segment, (ii) an ensemble of heterogeneous VLM specialists, drawn from different open model families, engages in a structured deliberation that includes a peer-consultation round of questions, and (iii) agent rankings are aggregated with a Borda count and the orchestrator re-ranks its own prediction in light of the specialists' evidence. The entire pipeline runs locally with no fine-tuning. Experiments show that our method positively improves zero-shot action recognition performance over the baseline, highlighting the influence of a heterogeneous deliberation step, showing that the gain stems from decorrelated model priors rather than from additional compute.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2604.10242

MedVeriSeg: Teaching LISA-Like Medical Segmentation Models to Verify Query Validity Without Extra Training

作者:

Qinyue Tong↗Xiaozhen Wang↗Ziqian Lu↗Jun Liu↗Yunlong Yu↗Zheming Lu↗

Despite recent progress in text-prompt-based medical image segmentation, existing LISA-like MLLM-based methods typically generate masks regardless of whether the target specified in the query is present, leading to hallucinated segmentation. In this work, we propose MedVeriSeg, a training-free query verification framework that enables LISA-like medical segmentation models to reject false segmentation queries. MedVeriSeg first quantifies the response quality between the [SEG] token and image features through a Similarity Response Quality Scoring Module. To further improve robustness, it employs a Lightweight Routed Multi-Agent Verification Module, which fuses quantitative score evidence with qualitative agent evidence to comprehensively verify the validity of the query. To support systematic evaluation, we construct MedVeriSeg-Bench, a benchmark designed for query verification in medical image segmentation. Experimental results demonstrate that MedVeriSeg effectively identifies false segmentation queries and reduces hallucinated segmentation, while maintaining a high acceptance rate for valid queries, thereby largely preserving the segmentation utility of LISA-like medical segmentation models.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19388

Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?

作者:

Li Gu↗Zihuan Jiang↗Linqiang Guo↗Zhixiang Chi↗Ziqiang Wang↗Huan Liu↗Yuanhao Yu↗Tse-Hsun Chen↗Yang Wang↗

Recent advances in mobile agents are dominated by the GUI paradigm, in which agents perceive UI information and emit screen interactions. However, mobile platforms also expose a command-line interface (CLI) that provides direct access to device services and data. We argue CLI deserves first-class consideration alongside GUI. We evaluate three coding agents (Claude Code, Terminus-2, mini-swe-agent) across four model APIs on AndroidWorld and MobileWorld without any mobile-specific post-training, comparing against three reproducible GUI baselines (GUI-Owl-1.5-32B, MAI-UI, Qwen3-VL-32B). Claude Code (Opus 4.7) reaches 71.8\% and 51.9\%, outperforming every reproducible GUI baseline (69.3/68.1/57.8\% on AndroidWorld; 43.2/26.3/13.3\% on MobileWorld), while every other CLI configuration remains competitive. To establish the paradigm's ceiling, we provide oracle CLI solutions that reach 88.8\% on AndroidWorld (103/116 tasks CLI-solvable) and 86.3\% on MobileWorld (101/117 tasks CLI-solvable), indicating substantial room for future improvement. To cover everyday user intents beyond the GUI scope, we introduce the CLI-Advantage Task Suite, comprising 45 templates across five categories: bulk operations, multi-condition filtering, aggregation, cross-app workflows, and hidden device state. Every CLI agent outperforms every GUI baseline in all five categories, with substantially fewer steps per task (10.7 vs.\ 18.6). To support future research on mobile CLI agents, we will open-source agent implementations, oracle solutions, the CLI-Advantage suite, and evaluation infrastructure.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19636

Hard or Just Unreached? Diagnosing the Sampling Blind Spot in Math-Reasoning Difficulty Estimation

作者:

Luca Zhou↗Sajel Shah↗Emanuele Rodol\`a↗Roberto Dess\`i↗

arXiv:2606.19636v1 Announce Type: cross Abstract: Math and science reasoning benchmarks rely on pass@k, the fraction of sampled chains that reach gold, as the canonical per-example difficulty signal. The same signal drives RL with verifiable rewards, math data curation, synthetic curricula, and verifier training. We show this proxy has a persistent blind spot on its hardest stratum: on the eight free-form math cells we test (GSM8K and MATH across four open-weight models), 10.3-22.9% of the examples that no sampling seed solves in six tries are instead solved at matched compute by a six-chain deterministic regime. These are greedy decoding plus five cheap residual-stream perturbations applied via activation grafting, while greedy alone solves at most 6% on these math cells. Recovery scales with the additional budget, across perturbations whose mechanistic distinctness we verify across all twelve cells (cross-kind fix-set Jaccard

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12207

Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends

作者:

Jinshan Lai↗Jianwei Hu↗Baoyang Jiang↗Fengchun Zhang↗Leyuan Wang↗Haotian Li↗Yida Wang↗Tingxuan Huang↗Xi Ren↗Qiang Ma↗

arXiv:2606.12207v1 Announce Type: cross Abstract: Embodied intelligence now spans navigation, household assistance, manipulation, autonomous driving, aerial agents, and multimodal large-model control. This expansion has made benchmark construction a central bottleneck for reliable evaluation. Unlike static datasets, embodied benchmarks combine task specifications, environments, robot data, demonstrations, annotations, metrics, evaluation scripts, and release policies into a single evaluation system. This survey reviews the literature through a five-stage construction pipeline: requirement and task construction, data acquisition, data cleaning and annotation, benchmark suite generation and metric definition, and evaluation execution with diagnostic feedback. For each stage, the survey analyzes the transition from manual curation to traditional automation, foundation-model assistance, and agentic closed-loop workflows. It also compares qualitative construction costs across human labor, data and asset acquisition, compute and simulation, validation and debugging, governance and maintenance, and rework risk. The main conclusion is that automation does not simply reduce benchmark cost. Instead, it often shifts cost toward validation, auditability, version control, and long-term governance. Progress in embodied evaluation will therefore depend not only on larger benchmark suites, but also on construction pipelines that are diagnosable, auditable, and responsibly refreshable.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14762

Scribby: A Multi-Level LLM Framework for Semantic Video Analysis

作者:

Julian Abelarde↗Hugo Garrido-Lestache Belinchon↗

As video content continues to expand across educational platforms, recorded lectures, and live-streamed entertainment, the need for efficient and structured analysis of long-form footage has increased [1]. Although many existing AI programs provide high-level video summaries based on AI-generated transcripts [2,3,4,5], these approaches are often limited to coarse overviews and lack detailed analysis of a video's structure, thematic progression, and semantic relationships, all of which are required for comprehensive video analysis. This paper proposes an LLM-based video summarization framework that balances macro-level comprehension with micro-level semantic analysis [6,12,13]. The first stage of the process indexes the video at a micro level by (1) analyzing the full transcript, (2) analyzing individual transcript sentences, and (3) grouping these sentences by semantic similarity using an LLM as a judge [6,13]. Contextual continuity is retained during sentence-level processing by incorporating both the global transcript analysis and adjacent sentence information into each evaluation prompt. This framework establishes a foundation for video analysis tools that visualize semantic chunking and semantic matching through relevance-based heatmaps. Limitations and future expansions of the framework are also discussed.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2508.10523

Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies

作者:

Ayushman Sarkar↗Zhenyu Yu↗Mohd Yamani Idna Idris↗

Visual reasoning matters for many computer vision tasks that go beyond surface-level object detection and classification. Despite progress in relational, symbolic, temporal, causal, and commonsense reasoning, existing surveys typically cover only one part of the problem, such as visual question answering, scene-graph generation, neuro-symbolic AI, or multimodal chain-of-thought, and rarely analyze reasoning types, methodologies, and evaluation protocols together. This survey addresses that gap. Following a structured literature review, we group visual reasoning into five major types (relational, symbolic, temporal, causal, and commonsense) and examine how each is implemented across methods that range from graph-based models, memory networks, attention mechanisms, and neuro-symbolic systems to reasoning with vision-language models (VLMs) and multimodal large language models (MLLMs), including visual chain-of-thought, visual programming, and tool-augmented and test-time reasoning. We then review evaluation protocols for functional correctness, structural consistency, and causal validity, and we analyze their limits in generalizability, reproducibility, faithfulness, and explanatory power. We also identify open challenges: scaling to complex scenes, integrating symbolic and neural paradigms more deeply, the shortage of comprehensive benchmarks, language-prior shortcuts and hallucination in foundation models, and reasoning under weak supervision. Finally, we set out a research agenda for vision systems and argue that connecting perception and reasoning is necessary for transparent, trustworthy, and cross-domain models, especially in high-stakes settings such as autonomous driving and medical diagnostics.

阅读与讨论 → 访问原文 →

21.

arXiv (quant-ph) 2026-06-17 DOI: arXiv:2603.20718

Frequency-Division Multiplexed CV-QKD System

作者:

Jaehyeok Han↗Donghyeok Le↗Minseok Ryu↗Syed Assad↗Yong-Su Kim↗Sunghyun Bae↗

arXiv:2603.20718v2 Announce Type: replace Abstract: We propose a frequency-division multiplexed (FDM) continuous-variable quantum key distribution (CV-QKD) system with enhanced spectral efficiency through optimized channel spacing of low-symbol-rate signals. A four-channel 10-Mbaud FDM-CV-QKD system was experimentally demonstrated using Gaussian modulation, a transmitted local oscillator, and homodyne detection. Despite the inter-channel interference, under a finite-size scenario (m=1.25x10^6), the system achieved a 3.6-fold back-to-back secret key rate gain and outperformed the single-channel frequency-upconverted signal up to 26.8 km.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17657

Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games

作者:

Zirui Cheng↗Zeyu Shen↗Thomas L. Griffiths↗Peter Henderson↗

arXiv:2606.17657v1 Announce Type: new Abstract: People make decisions differently in strategic interactions. Some update beliefs like a Bayesian; others exhibit biases like motivated reasoning. Although creators of large language models use simulated humans for safety evaluations and training, they often fail to cover this breadth of human behavior. We argue that cognitive science and economics provide a convenient tool for doing so, making use of mathematical models of human decision-making. We propose an approach that we call Equation-to-Behavior Prompting for guiding large language models to match cognitive models, and evaluate this approach on persuasion games based on legal decision-making. We find that large models can approximate equation-based specifications – Bayesian updating, affine distortion, motivated updating, and Grether's $\alpha$-$\beta$ model – using prompting, but small models fail to do so. However, training small models with reinforcement learning to adhere to mathematical rules, Equation-to-Behavior RL, reduces belief error by 26.5% in out-of-distribution parameterizations. We show that these simulations can help create diverse training environments; training small models to consider different kinds of decision-makers improves average belief change by 2.5%–12% over Bayesian-only training, even when persuading GPT-5-mini. Our work could improve human simulations for training and evaluation in increasingly realistic settings, and could also enable novel research into more complicated mathematical models of human decision-making.

阅读与讨论 → 访问原文 →

23.

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 →

24.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13507

Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data

作者:

Qixu Chen↗Satoshi Nakamura↗

Large-scale mined corpora provide abundant training data for end-to-end speech-to-speech translation (S2ST) but may contain noise, misalignment, and semantic errors. Filtering noisy data is crucial to maintain robust speech translation performance. We study how to train an audio-language model to make keep/drop decisions on paired speech directly from audio. To obtain reliable supervision without manual labels, we adopt a scalable two-stage Rank-to-Distill strategy. A lightweight ranker generates keep/drop pseudo-labels from noisy speech pairs, then trains an audio large language model to predict keep/drop directly from raw paired speech. The resulting model jointly captures acoustic fidelity and cross-lingual semantic consistency for the selection of speech-conditioned data. Experiments on CVSS-C and SpeechMatrix show consistent improvements over unfiltered training, yielding up to +1.4 ASR-BLEU for end-to-end S2ST.

阅读与讨论 → 访问原文 →

25.

bioRxiv (Bioinfo) 2026-06-16 DOI: HASH:249acf2e221e33b45c3a20f8365e7957

FlowBench: separating planning, fault recovery and interpretation in agentic bioinformatics

作者:

Kurjan↗Cribbs↗A. P↗

Agentic large language model (LLM) systems are being deployed in bioinformatics faster than they are understood, and single-metric evaluations conflate capabilities that fail independently. We introduce FlowBench, a benchmark that decomposes agentic bioinformatics performance into planning, fault recovery, biological interpretation, and end-to-end output-fidelity. Existing systems achieve high plan completeness, but their closed, single-provider designs prevent attribution of performance to scaffolding versus the underlying model. We therefore built FlowAgent, a modular, provider-agnostic framework whose components can be selectively disabled and whose backbone model can be swapped across providers on a shared harness, and used it to evaluate 23 models from three main providers. Three findings emerge. First, generating a valid workflow plan from a named toolchain is largely solved, whereas inferring an appropriate toolchain from biological intent alone is uniformly difficult regardless of model tier, compressing all models into a narrow 44-57% pass-rate band. Second, ablation shows that the dependency-structured plan and a completeness-reflection step drive performance, while adding a same-context validator-driven retry makes structural quality worse. Third, fault recovery and data-grounded interpretation remain unsolved. Models frequently propose fixes that force a clean exit while leaving the underlying data invalid, and data-grounded interpretation lags internal-knowledge recall by a consistent margin. Safety does not emerge from capability, and reasoning-tier models were among the least reliable at recognising unrecoverable faults. Once planning saturates, agent architecture and refusal calibration, not model scale, are the productive frontier.

阅读与讨论 → 访问原文 →