探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2604.11556

FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning

作者:

Haoran Ding↗Zhaoguo Wang↗Haibo Chen↗

arXiv:2604.11556v2 Announce Type: replace-cross Abstract: LLM-assisted software development has become increasingly prevalent, and can generate large-scale systems, such as compilers. It becomes crucial to strengthen the correctness of the generated code. However, automated reasoning for large-scale systems remains challenging due to code complexity. Hoare logic offers an approach to decomposing a large system into smaller components and reasoning about them separately (i.e., compositional reasoning). However, existing works still struggle to scale, because Hoare logic requires writing formal specifications for each function, imposing a heavy human burden. The problem is exacerbated when code is generated by LLMs, as developers lack a deep understanding of each function's expected behavior. This paper presents FM-Agent, the first framework that realizes automated compositional reasoning for large-scale systems. Leveraging LLMs, FM-Agent introduces a top-down paradigm to automatically generate function-level specifications. Specifically, FM-Agent derives the specification of a function from how its callers expect the function to behave, so the generated specifications can reflect the developer's intent of a function even if the implementation is buggy. Developers' intent is usually expressed in natural language, while existing verifiers only support formulas. Therefore, FM-Agent generalizes Hoare-style inference to reason about functions against natural-language specifications. Finally, to confirm bug existence and explain bug causes, FM-Agent automatically generates test cases to trigger potential bugs. In our evaluation, FM-Agent successfully reasons about large-scale systems within 2 days, each of which has up to 143k LoC. These systems have already been tested by their developers, but FM-Agent still finds 522 newly discovered bugs. These bugs can cause serious consequences, including system crashes and incorrect execution results.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2603.27450

FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies

作者:

Chenxiao Gao↗Edward Chen↗Tianyi Chen↗Bo Dai↗

arXiv:2603.27450v2 Announce Type: replace Abstract: Thanks to their remarkable flexibility, diffusion models and flow models have emerged as promising candidates for policy representation. However, efficient reinforcement learning (RL) upon these policies remains a challenge due to the lack of explicit log-probabilities for vanilla policy gradient estimators. While numerous attempts have been proposed to address this, the field lacks a unified perspective to reconcile these seemingly disparate methods, thus hampering ongoing development. In this paper, we bridge this gap by introducing a comprehensive taxonomy for RL algorithms with diffusion/flow policies. To support reproducibility and agile prototyping, we introduce a modular, JAX-based open-source codebase that leverages JIT-compilation for high-throughput training. Finally, we provide systematic and standardized benchmarks across Gym-Locomotion, DeepMind Control Suite, and IsaacLab, offering a rigorous side-by-side comparison of diffusion-based methods and guidance for practitioners to choose proper algorithms based on the application. Our work establishes a clear foundation for understanding and algorithm design, a high-efficiency toolkit for future research in the field, and an algorithmic guideline for practitioners in generative models and robotics. Our code is available at https://github.com/typoverflow/flow-rl.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.11891

Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation

作者:

Mehmet Turan Yard{\i}mc{\i}↗

arXiv:2606.11891v1 Announce Type: cross Abstract: Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy. A natural design choice is whether to use a single (unified) critic that estimates the combined value of all objectives, or separate (dual) critics with disjoint reward signals. We present a controlled comparison on the Unitree G1 humanoid (23 active DoF) in NVIDIA Isaac Lab, training loco-manipulation policies through a sequential curriculum spanning 13 levels from stationary reaching to walking with variable-orientation targets. In standardized evaluation, dual-critic policies reach targets 3.5$\times$ faster (6.5 vs. 22.6 simulation steps), achieve 2$\times$ higher throughput (14.3 vs. 7.0 validated reaches per 1,000 steps), and attain higher validated reach rates (65.2% vs. 53.8%) compared to the unified-critic policy. Notably, additional anti-gaming reward mechanisms provide no further improvement beyond the architectural change alone (60.9% vs. 65.2%). These results have direct implications for the emerging paradigm of RL fine-tuning of imitation-learned policies: when refining a pre-trained manipulation policy with RL, a unified critic risks suppressing the learned behavior through competing locomotion gradients. These findings demonstrate that critic architecture is a primary - and often overlooked - design choice in multi-objective humanoid RL, with greater impact than reward engineering on reaching efficiency.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2503.23688

Mapping Geopolitical Bias in 11 Large Language Models: A Bilingual, Dual-Framing Analysis of U.S.-China Tensions

作者:

William Guey↗Wei Zhang↗Pierrick Bougault↗Vitor D. de Moura↗Jos\'e O. Gomes↗

Large language models are how hundreds of millions of people now encounter contested political questions, raising a subtle measurement problem: a model that simply agrees with whatever it is told can masquerade as biased, contaminating any claim that models hold political opinions. We address this by importing balanced keying from survey psychometrics, posing each proposition and its swapped reverse and signing the response so acquiescence cancels and genuine conviction accumulates. The result is a reproducible, quantitative instrument that maps geopolitical stance across 11 models and 2 languages (19,712 responses). Developer origin, query language and issue domain emerge as three near-equal, additive factors; every model, including those built in the United States, leans more Pro-China in Mandarin; and two models with identical agreement bias are told apart, one neutral, one biased. We release it as an open, interactive tool that extends to any contested-opinion domain.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15834

AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems

作者:

Yajie Zhou↗Ao Li↗Ashwin Silla↗Zaoxing Liu↗Vyas Sekar↗

arXiv:2606.15834v1 Announce Type: new Abstract: The computer systems community has recently seen growing interest in AI-driven system evolution, where AI agents iteratively rewrite systems. Frameworks such as AdaEvolve and Engram report 12-60% score improvements over human-designed algorithms. While these results are promising, there are practical concerns if these AI-evolved programs can perform worse on unseen workloads and exhibit scalability regressions. Given the speed and scale of AI-generated code, we need automated mechanisms to uncover such identify hidden weaknesses in AI-evolved systems programs. To this end, we develop AIChilles that takes as input a baseline program $P$ and an AI-evolved program $P'$, AIChilles searches for valid workloads where $P'$ regresses relative to $P$ in correctness, runtime, memory usage, or output quality. To tackle the diversity in system applications, weakness types and potential bugs, AIChilles combines deterministic workload-parameter extraction, agent-based constraint inference, differential oracles, and code-frequency coverage to discover diverse failures. Across five system applications and 30 AI-evolved programs, AIChilles finds 49 distinct hidden weaknesses. We also show that explicitly including AIChilles in the AI-driven development lifecycle can mitigate several of these weaknesses.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2410.00812

Generative causal testing to bridge data-driven models and scientific theories in language neuroscience

作者:

Richard Antonello↗Chandan Singh↗Shailee Jain↗Aliyah Hsu↗Sihang Guo↗Jianfeng Gao↗Bin Yu↗Alexander Huth↗

Representations from large language models are highly effective at predicting BOLD fMRI responses to language stimuli. However, these representations are largely opaque: it is unclear what features of the language stimulus drive the response in each brain area. We present generative causal testing (GCT), a framework for generating concise explanations of language selectivity in the brain from predictive models and then testing those explanations in follow-up experiments using LLM-generated stimuli.This approach is successful at explaining selectivity both in individual voxels and cortical regions of interest (ROIs), including newly identified microROIs in prefrontal cortex. We show that explanatory accuracy is closely related to the predictive power and stability of the underlying predictive models. Finally, we show that GCT can dissect fine-grained differences between brain areas with similar functional selectivity. These results demonstrate that LLMs can be used to bridge the widening gap between data-driven models and formal scientific theories.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15566

LLM-Assisted Stance Detection in Scientific Discourse: A Test Case in Bayesian Cognitive Science

作者:

Eyup Engin Kucuk↗Tarik Kelestemur↗\"Omer Da\u{g}lar Tanrikulu↗

Qualitative coding is central to social science, but expert annotation is difficult to scale. LLMs offer a possible extension, yet require careful validation when the target construct is interpretive, theoretically loaded, and only indirectly expressed. We study this problem in a difficult case: detecting whether authors treat Bayesian models as descriptions of mental and neural mechanisms (realism) or as useful mathematical tools (instrumentalism). Our method combines a theory-driven codebook, expert-coded reference annotations, a diagnostic-gated prompt-optimization search yielding a shared zero-shot prompt for three frontier LLMs (GPT-5.1, Claude Sonnet 4.6, Gemini 3 Pro Preview), and multi-rater reliability analysis. The final prompt achieved a held-out combined reliability score of 0.76 (harmonic mean of ICC = 0.79 and $\alpha$ = 0.74), with all diagnostics satisfied. Deployed on 6,858 quotes from 210 articles, the three LLMs reached substantial quote-level agreement (ICC = 0.80; $\alpha$ = 0.76; combined = 0.78) and near-perfect article-level rank stability ($r$ = 0.96-0.97 across rater pairs). The corpus was predominantly weakly realist, but article-level stances were rarely uniform: only 1.4% of articles used a single band, while 59.5% spanned four or more. Low-level perception/motor articles scored 8.8 Realism points higher than high-level cognition articles ($p < .001$, $d = 0.60$), quantifying a long-held qualitative intuition. We present this as an expert-led case study; the framework is intended to generalize to similar theoretically demanding tasks, not to all qualitative analysis.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19399

VERITAS: Verifier-Guided Proof Search for Zero-Shot Formal Theorem Proving

作者:

Manish Acharya↗Zhenyu Liao↗Yueke Zhang↗Kevin Leach↗Yu Huang↗Yifan Zhang↗

arXiv:2606.19399v1 Announce Type: cross Abstract: LLM-based formal provers often collapse rich verifier signals (syntax errors, type mismatches, partial goal progress) into a binary pass/fail bit. We present VERITAS, a zero-shot framework that routes every verifier signal back into proof search through a two-phase protocol: Best-of-N sampling first, then a critic-guided MCTS pass that ingests Phase 1 failures as explicit negative examples. The protocol preserves every theorem solved by its own Phase 1 sweep, so Phase 2's additional solves are attributable to feedback-driven exploration. VERITAS reaches 40.6% on miniF2F (vs. an independently run Best-of-5 at 36.9%, Portfolio 26.2%) and 7.3% on VERITAS-CombiBench, a 55-theorem combinatorics benchmark we release on which Best-of-5 (1.8%) falls below Portfolio (3.6%), exposing that unguided sampling hurts when correct lemma names must be recovered iteratively from verifier feedback. Artifacts are available on GitHub.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.19149

OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing

作者:

Nahum Korda↗Gadi Evron↗

arXiv:2606.19149v1 Announce Type: cross Abstract: Automated vulnerability discovery in large codebases remains challenging: traditional static analysis produces high false-positive rates, while dynamic approaches such as fuzzing require substantial infrastructure and often target narrow classes of bugs. Recent advances in large language models (LLMs) enable semantic reasoning about program behavior, but applying LLMs to repository-scale security analysis introduces challenges related to context management, cost, and verification. We present OpenAnt, an open-source vulnerability discovery system that integrates static program analysis with LLM-based reasoning in a multi-stage pipeline. OpenAnt introduces three key techniques. First, codebases are decomposed into self-contained analysis units filtered by reachability from external entry points, reducing the analysis surface by up to 97% while preserving attack-relevant code. Second, candidate vulnerabilities undergo adversarial verification through constrained attacker simulation, where the model evaluates exploitability under realistic attacker capabilities. Third, findings are validated through dynamic verification, in which exploit environments are generated automatically, executed in sandboxed containers, and discarded after use. Evaluation on widely used open-source projects including OpenSSL, WordPress, and Flowise shows that this architecture can identify previously unknown vulnerabilities while maintaining manageable analysis cost and substantially reducing false positives. Our results suggest that closed-loop vulnerability discovery pipelines, combining semantic reasoning with exploit validation, provide a practical path toward scalable automated security analysis. OpenAnt is released as open source under the Apache 2.0 license at https://github.com/knostic/OpenAnt.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2502.05163

Enhancing LLM Safety Through a Theoretical Minimax Game Lens

作者:

Yihe Deng↗Yu Yang↗Junkai Zhang↗Wei Wang↗Bo Li↗

The rapid advancement of large language models (LLMs) necessitates effective mechanisms to ensure their responsible deployment by accurately distinguishing unsafe content from benign content. While substantial safety datasets are available in English, multilingual safety modeling remains underexplored due to limited open-source safety datasets in other languages. Even within English datasets, safe yet sensitive corner-case content is scarce, leading to shortcut learning by models and non-trivial false-positive rates. To mitigate these issues, we introduce a novel minimax reinforcement learning (RL) framework wherein a data generator and a classifier model co-evolve, facilitating the production of high-quality synthetic multilingual safety data. We theoretically formalize this interaction as a minimax game and rigorously demonstrate convergence to a Nash equilibrium. Empirical evaluations confirm that our synthetic data generation method significantly enhances the classifier model performance, enabling a substantially smaller model to surpass the state-of-the-art by nearly 10% on English benchmarks while achieving 4.5x faster inference speed. These results establish a scalable and efficient methodology for synthetic data generation, advancing the development of safer and more robust multilingual LLM deployments.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19534

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

作者:

Yueyi Sun↗Yuhao Wang↗Jason Li↗Ye Tian↗Tao Zhang↗Jacky Mai↗Yihan Wang↗Haochen Wang↗Jinbin Bai↗Ling Yang↗Yunhai Tong↗

Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDLM, a multimodal diffusion language model optimized for efficient parallel region perception. Built upon PerceptionDLM-Base, a strong foundational baseline that achieves state-of-the-art performance among open-source diffusion MLLMs, our architecture fully leverages the parallel decoding nature of DLMs. Specifically, we introduce efficient prompting and structured attention masking to enable simultaneous perception of multiple masked regions, allowing the model to generate region descriptions in parallel at both the sequence and token levels. This design significantly improves inference efficiency compared with existing approaches that process regions sequentially. To systematically evaluate the parallelism property of visual perception capability for DLMs, we construct a new Parallel Detailed Localized Captioning Benchmark (ParaDLC-Bench) by scaling the DLC-Bench to include multiple region masks per image, enabling joint evaluation of both caption quality and inference efficiency. Experiments demonstrate that PerceptionDLM maintains competitive performance in region captioning while achieving substantial speed improvements for multi-region perception tasks. Our results highlight the potential of multimodal diffusion language models for efficient, parallel visual perception. To the best of our knowledge, we are the first to achieve parallel region caption and perception by leveraging the advantages of diffusion language models. Code, models, and datasets are released.

阅读与讨论 → 访问原文 →

12.

bioRxiv (Bioinfo) 2026-06-16 DOI: HASH:716564125cb93e76fe1f8b9852ff739e

scIsoAgent enables autonomous isoform-resolved characterization and sequence-informed interpretation of long-read single-cell transcriptomes

作者:

Zhao↗Liu↗Li↗Xu↗Wang↗

Alternative isoform usage can alter gene function independently of total gene expression, creating a need to resolve transcript isoforms at single-cell resolution. Long-read single-cell RNA sequencing meets this need by linking cellular identity to transcript isoforms and sequence-level features. Realizing its full biological value requires reproducible workflows that connect specialized long-read analysis with biological interpretation. Existing large language model (LLM)-based biomedical agents support general omics analysis, but are not designed for isoform-resolved long-read single-cell workflows. Here, we present scIsoAgent, an autonomous LLM-powered scientific agent for long-read single-cell RNA-seq analysis. scIsoAgent turns heterogeneous long-read single-cell inputs into traceable isoform-resolved workflows, using stage-aware planning and persistent computational context to support both execution and interpretation. Across complementary evaluations, this design improved the continuity from analysis planning to executable, interactive workflows compared with general-purpose LLM baselines. In real-data reanalysis, scIsoAgent recovered major findings from published long-read single-cell resources and extended a representative differential transcript usage event into a sequence-informed functional hypothesis. By linking full-length isoform sequences with model-inferred transcript properties, scIsoAgent connects observed isoform usage with potential sequence-level functional consequences. These results demonstrate that autonomous scientific agents can transform fragmented long-read single-cell analysis into coherent, reproducible workflows for isoform-resolved discovery and biological interpretation.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13832

Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security Response

作者:

Jose Luis Lima de Jesus Silva↗

arXiv:2606.13832v1 Announce Type: cross Abstract: Autonomous network-security response systems promise to reduce Security Operations Centre (SOC) reaction latency, but reward-only multi-agent reinforcement learning (MARL) can improve security reward while remaining non-deployable. We present a safety-contract graph MARL framework and instantiate it as ACD$^3$-GAT (Adaptive Constrained Counterfactual Decisioning with a Graph Attention Network encoder), an architecture that separates simulator observations from reusable operational budgets, constrained optimization, graph state encoding, and counterfactual action screening. We evaluate the method in CAGE Challenge 4, where agents operate under budgets for Mean Time to Recover (MTTR), false-positive response, and firewall change-management disruption. Across the benchmark, every unconstrained method violates the SOC downtime budget in 100% of evaluated episodes, with mean downtime proxy costs of 311-430 against a budget of 50. This complements prior CAGE Challenge 4 findings by showing that reward-only learning lacks operational discipline. Constrained MAPPO-GAT (C-MAPPO-GAT) isolates Lagrangian operational-cost control and budget-aware screening, while ACD$^3$-GAT adds budget context, CVaR tail-risk estimation, opponent-belief state, and Graph Counterfactual Risk Propagation (G-CRP). The replicated comparison includes three 200-episode seeds for IPPO, MAPPO-GAT, C-MAPPO-GAT, and ACD$^3$-GAT. C-MAPPO-GAT reduces downtime violation from 100% to 0.3% and mean downtime cost from 355.4 to 15.5 relative to MAPPO-GAT. ACD$^3$-GAT reduces mean downtime cost to 48.2 with a 13.8% violation rate, placing it on the safety-contract frontier rather than at the most conservative compliance point. Topology-seed and coupled adaptive Red-process stress tests preserve this contrast and show lower worst adaptive degradation for safety-constrained policies than reward-only MAPPO-GAT.

阅读与讨论 → 访问原文 →

14.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2606.13857

Local correlations in long-range dual-unitary kicked Hamiltonian chains

作者:

Vladimir Al. Osipov↗Marc Cedric Spyra↗Jana Carolina Schumann↗Thomas Guhr↗Boris Gutkin↗

arXiv:2606.13857v1 Announce Type: new Abstract: Many-body Floquet models with exact space–time symmetry, such as the kicked Ising spin chain (KIC), provide natural examples of systems with dual-unitary dynamics. The requirement of exact space–time symmetry is, however, highly restrictive, as it permits only nearest-neighbor interactions. Based on a pair of Hadamard matrices, we construct a wide family of dual-unitary kicked spin chains with long-range interactions. We show that local two-point correlations in such models propagate along the light-cone edges \( |n| = r|t| \), where \(r\) is the interaction range, and can be derived analytically for operators with local support. This approach is illustrated using the example of a kicked Ising spin chain with next-to-next-neighbor interactions.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19805

ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number

作者:

Zijie Meng↗

arXiv:2606.19805v1 Announce Type: cross Abstract: Transferring the camera motion of a reference video to a freshly generated one lets creators reuse cinematic moves. Yet reference and target often live at incompatible scales – a sweep across a galaxy versus a nudge across a desk – and naively reusing the recovered trajectory yields either imperceptible or violently exaggerated motion. We trace this to a geometric fact: translation-induced image motion scales as ||T||/Z, so a monocular trajectory is meaningful only up to a depth-scale gauge. We distill this into the Parallax Number Pi = ||Delta T|| / Zbar, a dimensionless, gauge-invariant descriptor of how strongly a camera move is felt, and prove that it – not the raw trajectory – is the quantity that scale-faithful transfer must preserve. ParaScale is a plug-and-play module that reads Pi off any reference video and re-realizes it against the target scene's own depth, per frame, leaving rotation untouched. Sitting between pose extraction and pose injection, it requires no retraining and drops into any pose-conditioned generator. We further introduce the Parallax Consistency Error (PCE), a scale-symmetric metric that – unlike the similarity-aligned TransErr – exposes scene-scale mismatch. Across scale regimes spanning four orders of magnitude and multiple backbones, ParaScale keeps the realized parallax on the identity line and cuts PCE by more than 3x over uncalibrated transfer with no loss of visual fidelity.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2602.14789

On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials

作者:

Rotem Mulayoff↗Sebastian U. Stich↗

arXiv:2602.14789v2 Announce Type: replace Abstract: The dynamical stability of the iterates during training plays a key role in determining the minima obtained by optimization algorithms. For example, stable solutions of gradient descent (GD) correspond to flat minima, which have been associated with favorable features. While prior work often relies on linearization to determine stability, it remains unclear whether linearized dynamics faithfully capture the full nonlinear behavior. Recent work has shown that GD may stably oscillate near a linearly unstable minimum and still converge once the step size decays, indicating that linear analysis can be misleading. In this work, we explicitly study the effect of nonlinear terms. Specifically, we derive an exact criterion for stable oscillations of GD near minima in the multivariate setting. Our condition depends on high-order derivatives, generalizing existing results. Extending the analysis to stochastic gradient descent (SGD), we show that nonlinear dynamics can diverge in expectation even if a single batch is unstable. This implies that stability can be dictated by a single batch that oscillates unstably, rather than an average effect, as linear analysis suggests. Finally, we prove that if all batches are linearly stable, the nonlinear dynamics of SGD are stable in expectation.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13111

M\"OVE: A Holistic LLM Benchmark for the German Public Sector

作者:

Camilla Dalerci↗Thilo Michael↗Robin Schaefer↗Daniel Weinland↗

We present M\"OVE (Modelle für die \"Offentliche Verwaltung Evaluieren), a holistic benchmark for evaluating large language models (LLMs) in the context of the German public sector. While LLMs are increasingly adopted in public administration, model selection remains largely ad hoc, and existing benchmarks offer limited guidance: they are predominantly English-centric, US-centric in content, and focus exclusively on task performance. M\"OVE addresses these gaps by evaluating 39 models across two complementary dimensions. Performance criteria cover summarization, question answering, and topic extraction. Governance criteria assess hallucination tendencies, energy consumption, provider transparency, and alignment with German constitutional values and knowledge about positions by German political parties. In total, we utilize ten German-language datasets, including gold- and silverstandard datasets that we constructed to reflect public-administration domains. We employ a multi-metric evaluation strategy combining classical NLP metrics, embedding-based methods, and LLM-as-a-judge approaches. Our results show that no single model dominates across all criteria: top performers differ between tasks, and model size alone is a poor predictor of quality. We further evaluate the benchmark itself, analyzing its statistical precision, LLM judge reliability, the impact of our private datasets on model rankings, the sensitivity of our results to prompt formulation, and the validity of our energy consumption estimates. M\"OVE is designed as a living benchmark under active development; results are publicly available at https://moeve.bundesdruckerei.de/.

阅读与讨论 → 访问原文 →

18.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2510.08447

Unifying Quantum Smoothing Theories with Extended Retrodiction

作者:

Mingxuan Liu↗Ge Bai↗Valerio Scarani↗

arXiv:2510.08447v2 Announce Type: replace Abstract: Estimating the state of an open quantum system monitored over time requires incorporating information from past measurements (filtering) and, for improved accuracy, also from future measurements (smoothing). While classical smoothing is well understood within a Bayesian framework, its quantum generalization has been challenging, leading to distinct and seemingly incompatible approaches. In this work, we demonstrate that quantum state smoothing hinges on a uniquely quantum feature: the fundamental dependence of retrodiction on prior correlations. We introduce auxiliary systems into the prior belief to capture correlations formed during preparation and evolution and develop a comprehensive framework for quantum state smoothing based on extended Bayesian retrodiction. This framework identifies all previous approaches as different choices of the extended prior, and naturally extends it to other choices that have not been considered before. We also give an information-theoretic characterization of the choices of prior, in terms of the average entropy of the smoothed states. Our results establish quantum state smoothing as a fundamentally retrodictive process just like classical smoothing, with proper quantum features clearly identified.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14723

Disagreement-Based Cross-Model Routing for Implicit Video Question Answering

作者:

Durga Sandeep Saluru↗

We study multiple-choice video question answering on the ImplicitQA benchmark, where the correct answer is never explicitly shown but must be inferred from off-screen events, line-of-sight cues, causal structure, and cross-shot spatial layout. On this benchmark a single frontier video LLM already operates near its accuracy ceiling, and we observe that conventional self-consistency strategies – majority voting across repeated samples of the same model – can hurt rather than help, because the model's errors on hard questions are correlated. We propose disagreement-based cross-model routing, a pure inference-time procedure that requires no labels and no training. We triple-sample a native-video model (Gemini 3.1 Pro Preview) at temperature zero, exploit the genuine sample-to-sample variance of its video-processing pipeline to identify the roughly 20% subset of questions where the three samples disagree, and route only that subset to a second model from a different family (Claude Opus 4.8) that consumes uniformly sampled frames with adaptive thinking. On the 1001-question validation set with public ground truth – our main evaluation – the method improves AvgAcc by +1.43 over the best single sample of the primary model, with per-category gains concentrated on Motion & Trajectory (+5.49), Inferred Counting (+3.45), and Vertical Spatial Reasoning (+1.82) – the categories most dependent on cross-shot reference resolution. The same pipeline applied to the held-out 172-question CVPR 2026 ImplicitQA challenge test set achieves 82.03 AvgAcc / 79.71 MacroAvgAcc (+1.81 over the best single sample of the primary model), confirming the validation result on an independent split.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14049

FoleyGenEx: Unified Video-to-Audio Generation with Multi-Modal Control, Temporal Alignment, and Semantic Precision

作者:

Shiyao Wang↗Xijuan Zeng↗Hui Wang↗Shiwan Zhao↗Feng Deng↗Chen Zhang↗Yong Qin↗

We present FoleyGenEx, a unified video-to-audio (VTA) framework integrating multi-modal control, frame-level temporal alignment, and fine-grained semantics, enabling synchronized, versatile audio synthesis for diverse tasks. Existing VTA methods either have multi-modal control but weak temporal alignment or strong alignment but lack reference audio conditioning and semantic precision. FoleyGenEx fills this gap via three core innovations: a conditional injection mechanism for audio-controlled VTA and Foley extension, a multi-modal dynamic masking strategy preserving training synchronization, and an adverb-based data augmentation algorithm leveraging signal processing and large language models to enhance textual supervision with nuanced semantics. Experiments on AudioCaps, VGGSound, and Greatest Hits demonstrate its competitive controllable VTA performance against existing methods. Demo samples are available at https://foleygenex.github.io/FoleyGenEx.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.11266

Seeing Before Colliding: Anticipatory Safe RL with Frozen Vision-Language Models

作者:

Samuel Tetteh↗Cody Fleming↗

arXiv:2606.11266v1 Announce Type: new Abstract: The cost signal that constrained-RL algorithms optimize against is almost always reactive: the simulator emits a non-zero cost only after a collision has begun, and the Lagrange multiplier of PPO-Lagrangian grows only after the episode budget has been exceeded. At race speeds, where collisions are instantaneous and irreversible, any safety mechanism that waits for cost to accumulate is structurally too late. We present VLM-Safe-RL, a framework that integrates a frozen vision-language model into the CMDP Lagrangian update as an anticipatory cost term. The framework comprises four contributions: (i) Decoupled Dual-Path CLIP, independent reward/cost paths that respect the CMDP's factorization; (ii) VLM-Lagrange, an augmented multiplier update that incorporates a per-step VLM cost as an anticipatory term; (iii) Confidence Gating, a Bayes-optimal weight derived from a logistic noise model on the CLIP margin; and (iv) VLMPPOLag, the composed algorithm. On Safety-Gymnasium FormulaOne L2, our principal evaluation ($n{=}5$ seeds, $10^{6}$ steps, budget $d_{lim}{=}25$) VLMPPOLag$+$Conf is the only configuration in our default budget comparison that simultaneously retains substantive return ($J_r{\approx}40$) and holds cost within budget on a majority of seeds; the five constraint-aware baselines (PPOLag, CPO, CPPOPID, CPO-CLG, PPOLag-RND) each fail at least one requirement. The mechanism generalizes to held-out MetaDrive Medium (catastrophe rate $41\%{\to}26\%$, 95\% bootstrap CI $[-26,-5]$\,pp) and shows directionally consistent transfer to Bullet Safety-Gym; we report honestly where it does not (MetaDrive Easy/Hard, Qwen2-VL backbone) and trace the Hard failure to a Lagrangian-regulation pathology rather than the VLM signal itself. To our knowledge, this is the first work to use frozen VLM signals as an anticipatory cost term inside the CMDP Lagrangian update.

阅读与讨论 → 访问原文 →

22.

medRxiv (Medicine) 2026-06-16 DOI: HASH:26dbc55e1b694ceee03bffba6bd73d69

Daily Healthy Eating Index (HEI-2020) scoring reveals diet quality patterns masked by aggregation

作者:

Singh↗Salathe↗

The Healthy Eating Index (HEI-2020) is conventionally computed by aggregating intake across days before scoring. Digital food logging enables an alternative: scoring each day and averaging daily scores. These methods are not equivalent. The HEI's density-based structure and component caps cause aggregation to inflate adequacy scores when intake is irregular. Using Food & You data, we show daily HEI correlates more strongly with microbiome diversity, and recommend co-reporting both metrics.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.13818

Uncertainty Estimation and Generalization Bounds for Modern Deep Learning

作者:

Luis A. Ortega↗

arXiv:2606.13818v1 Announce Type: new Abstract: This thesis investigates how Bayesian principles can deepen our understanding of modern deep learning systems. While neural networks achieve remarkable predictive performance, their ability to generalize and to quantify uncertainty remains only partly understood. This thesis approaches this challenge from both methodological and theoretical angles: unifying Bayesian inference, function-space modeling, and large-deviation theory under a common probabilistic perspective. On the methodological side, the thesis introduces the Deep Variational Implicit Process (DVIP), a scalable Bayesian framework that extends implicit processes to deep architectures. Complementing this, two post-hoc methods – the Variational Linearized Laplace Approximation (VaLLA) and the Fixed-Mean Gaussian Process (FMGP) – are proposed to equip pretrained deterministic networks with calibrated uncertainty estimates. The theoretical contributions focus on one of the central open questions in modern machine learning: why do large, over-parameterized neural networks generalize so well? To address this, the thesis develops a unified probabilistic framework that connects three key mechanisms – diversity, smoothness, and stochasticity – within the language of PAC-Bayesian and large-deviation theory.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20244

SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs

作者:

Bo Yin↗Xiaobin Hu↗Chengming Xu↗Ruolin Shen↗Mo Yang↗Jiangning Zhang↗Peng-Tao Jiang↗Cheng Tan↗Shuicheng YAN↗

arXiv:2606.20244v1 Announce Type: cross Abstract: Vision-language models (VLMs) often underperform on evidence intensive tasks because decisive visual evidence are small, localized, and easy to overlook, leading to failures in evidence readout even when high-level reasoning is intact. Prior inference-time visual interventions can improve grounding without retraining, but they are largely open-loop and lack a mechanism to verify whether highlighted evidence is actually used. We study answer-span prediction entropy as a model-internal feedback signal and show that naive entropy minimization is ambiguous, since low entropy may arise from evidence-grounded confidence or shortcut collapse. To resolve this ambiguity, we introduce low-entropy anchors and an entropy-shaping objective that reduces answer uncertainty while preserving baseline high-confidence tokens. We instantiate this principle in SPOT-E, a plug-and-play test-time method that produces question-conditioned spotlights, optimized per instance via light-weight tuning based on Group Relative Policy Optimization (GRPO). Across all benchmarks and different VLM families, SPOT-E yields consistent gains and improved robustness under visual corruptions. Code is publicly available at: \url{https://github.com/YinBo0927/SPOT-E}

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19830

JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines

作者:

Jianwen Sun↗Chuanhao Li↗Zizhen Li↗Yukang Feng↗Fanrui Zhang↗Yifei Huang↗Yu Dai↗Kaipeng Zhang↗

Current AI-driven game development has made substantial progress in asset generation, gameplay design, and web-based game coding, yet project-level code engineering on professional game engines remains largely unexplored due to the absence of large-scale datasets and deterministic evaluation methods. We present JamSet and JamBench, the first project-level game code framework dataset and benchmark built on a professional game engine. Our key insight is that Game Jam competitions, community events where developers build complete games under tight time constraints, yield thousands of open-source projects suitable for this purpose. Building on the Godot engine's text-based format and headless execution mode, we design a deterministic verification pipeline from file integrity to runtime behavior collection, distilling 8,133 verified projects from over 240,000 repositories. Of these, 300 manually verified projects form JamBench; the rest constitute JamSet. JamBench defines theme-driven generation and code completion tasks, evaluated through a pipeline combining compilation pass rates, Structural Completeness Score (SCS), and Behavioral Alignment Score (BAS). Evaluation of 9 frontier models reveals a capability cliff as project scale increases, with runtime pass rates dropping from 80.4% on small projects to 5.7% on large ones (Task2a). Code Agents improve compilation rates yet yield no gains in runtime behavioral quality, indicating that the bottleneck lies in architectural design rather than syntactic correctness. Experiments validate JamSet as effective training data. All data and code are publicly available.

阅读与讨论 → 访问原文 →