探索全球前沿学术脉络

01.

Science (Express) 2026-05-06 DOI: 10.1126/science.aec3187

A 481-meter-high landslide-tsunami in a cruise ship–frequented Alaska fjord | Science

作者: 未知作者

Early in the morning of 10 August 2025, a >64 × 10 6 m 3 landslide struck Tracy Arm fjord in Alaska. The landslide was preconditioned by glacial retreat caused by climate change. The resulting 481 m runup megatsunami followed an initial 100-m-high breaking wave traveling >70 m s −1 . The landslide was preceded by several days of microseismicity, which increased in rate and magnitude until ~1 hour before failure. The landslide produced globally observed long-period seismic waves equivalent in size to a M5.4 earthquake. A long-period (~66 s) global seismic signal, produced by a landslide-induced seiche trapped within the fjord, persisted for up to 36 hours, the second time a days-long seiche has been thus observed. With fjord regions increasingly visited by cruise ships, and climate change making similar events more likely, this unanticipated, near-miss event highlights the growing risk from landslides and tsunamis in coastal environments.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.05692

Benchmarking Counterfactual Prediction in Epidemic Time Series with Time-Varying Interventions

作者:

Wenhao Mu↗Facundo Yan↗Anik Mumssen↗Marisa Eisenberg↗Alexander Rodr\'iguez↗

arXiv:2606.05692v2 Announce Type: replace-cross Abstract: Deep learning has enabled significant advances in time-series causal inference, yet progress remains constrained by the lack of realistic benchmarks with observable counterfactual outcomes. Existing datasets either rely on real-world observations without ground-truth counterfactuals or on simplified simulations that fail to capture complex causal dynamics. To address this gap, we develop a large-scale benchmark for counterfactual prediction in epidemic time series under dynamic interventions. Unlike existing benchmarks, it supports static and time-varying treatments, as well as both single-policy and multi-policy intervention settings, enabling evaluation of causal inference methods across a broad range of causal inference scenarios. Leveraging a calibrated agent-based model grounded in real-world demographic, mobility, epidemiological, and policy data, we generate realistic counterfactual trajectories across more than 150 U.S. counties. Using this benchmark, we evaluate widely used and state-of-the-art causal inference methods, revealing substantial performance differences and highlighting the challenges of realistic time-series causal reasoning.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2508.05287

FlowState: Sampling-Rate-Equivariant Time-Series Forecasting

作者:

Lars Graf↗Thomas Ortner↗Stanis{\l}aw Wo\'zniak↗Angeliki Pantazi↗

arXiv:2508.05287v3 Announce Type: replace-cross Abstract: Existing time series foundation models (TSFMs), often based on transformer variants, lack adaptability to different sampling rates, struggle with generalization across varying context and target lengths, and are computationally inefficient. We introduce FlowState, a novel TSFM architecture that achieves sampling-rate-equivariant forecasting through a unified design that pairs a state space model (SSM) encoder with a functional basis decoder (FBD). This design enables continuous-time modeling and dynamic time-scale adjustment, allowing FlowState to inherently generalize across all possible temporal resolutions, and dynamically adjust the forecasting horizons without retraining. We further propose an efficient pretraining strategy that improves robustness and accelerates training. Despite being one of the smallest TSFMs, FlowState achieves state-of-the-art results on the widely used GIFT-Eval benchmark, while demonstrating superior adaptability to unseen sampling rates. Our detailed analyses confirm the effectiveness of its components, and we demonstrate its unique ability to adapt to varying input sampling rates.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18688

Dual-Channel Grounded World Modeling (DCGWM): Structural Prevention of Objective Interference Collapse via Heterogeneous External Grounding with Inward-Only Gradient Flow

作者:

Akshay Hazare↗

arXiv:2606.18688v1 Announce Type: cross Abstract: Joint Embedding Predictive Architectures (JEPAs) are a leading approach to world model representation learning. We identify a failure mode in JEPA-based world models grounded against two qualitatively distinct external signals: physical dynamics (sparse, high-magnitude, constraint-satisfying gradient corrections) and social-behavioral dynamics (diffuse, distribution-matching corrections). We term this Objective Interference Collapse (OIC): we argue that joint learning in a shared latent space causes the dominant channel to systematically collapse the subordinate channel's representational subspace, in a manner not resolvable by loss weighting alone. We propose Dual-Channel Grounded World Modeling (DCGWM), designed to structurally prevent OIC through a partitioned latent space (physical subspace Z_p, behavioral subspace Z_b) with inward-only gradient flow. A Physical Grounding Channel updates only Z_p via VICReg-style alignment to physical measurements; a Social-Behavioral Grounding Channel updates only Z_b via alignment to trajectories from an emergent multi-agent simulation. An Inter-Channel Interface Module couples the subspaces at the task level without cross-subspace gradients. An Asymmetric Grounding Adherence Loss penalizes rollout drift with a hard hinge for physical violations and a soft KL for behavioral divergence. A Generative Rendering Layer is architecturally isolated from the latent world model. We present three theoretical results: the partition removes the gradient-interference pathway implicated in OIC; each grounded subspace inherits anti-collapse guarantees from its alignment objective; and generative isolation is necessary under a stated assumption on the generative objective's geometry. This manuscript establishes the problem formulation and architecture; experimental validation is ongoing and will be reported in a future revision.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20183

Effective Dimension Governs Generalization in Quantum Kernel Vision Models

作者:

Jian Xu↗Delu Zeng↗John Paisley↗Qibin Zhao↗

arXiv:2606.20183v1 Announce Type: new Abstract: Recent quantum vision models-quantum vision transformers and quantum convolutional networks-report two striking but unexplained empirical phenomena: (i) ansatze with more, or more uniformly distributed, entanglement generalize better, and (ii) injecting quantum noise can improve test accuracy rather than degrade it. These observations are currently treated as curiosities, discovered by grid search and explained, if at all, by hand. We show that both are manifestations of a single, measurable quantity: the effective dimension $d_eff$ of the (noise-shaped) quantum feature kernel. Working primarily with quantum-kernel vision models-a quantum feature map read out by a kernel classifier-we give a spectral account in which entanglement structure and quantum noise are two knobs that move $d_eff$; in an overfitting regime, contracting $d_eff$ acts as ridge-like regularization. We analyze the mechanism: an exact decomposition of the depolarized kernel $K_p=(1-p)^2K+\tfrac{p(2-p)}{D}\mathbf{1}\mathbf{1}^\top$ with $d_eff(K_p)\to1$, a contraction result (and its boundary) for amplitude damping, a kernel-machine capacity bound, and a capacity/alignment risk decomposition; the monotone contraction operative in our entangled experiments is verified empirically, not proven in general. Along the one-parameter depolarizing family the collapse is instead exact by construction; we use it only to confirm the kernel decomposition to machine precision and at up to $12$ qubits, not as evidence for $d_eff$. Amplitude damping contracts $d_eff$ and lifts test accuracy by up to $+13\%$ along an inverted-U sweet spot; the effect's sign flips between the over- and under-fitting regimes; noise injection matches an explicit spectral-filtering frontier. Our results organize two reported anecdotes into a single measurable principle for designing quantum-vision models.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11092

RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning

作者:

Yichao Zhong↗Yidan Lu↗Yuhang Lu↗Tianyang Tang↗Haoguang Mai↗Yixuan Pan↗Tianyu Li↗Li Chen↗Jingbo Wang↗Zhongyu Li↗Peng Lu↗Hongyang Li↗…

arXiv:2606.11092v2 Announce Type: replace-cross Abstract: Elite humanoid soccer shooting requires whole-body stability, high-impulse whole-body interactions, and accuracy to targets. Motion tracking-driven reinforcement learning (RL) provides stability in whole-body movement coordination, but a fixed reference makes it hard to adapt to varied ball positions and strike timings; in contrast, task reward-driven RL struggles to explore and discover valid kicks from scratch. We therefore introduce RoboNaldo, a three-stage motion-guided curriculum RL framework for high-impulse humanoid interaction. A single human-kick reference is used as a scaffold and progressively shifts optimization towards shooting performance. The curriculum first learns a stable whole-body kicking prior, then adapts the kick to free-kick settings where the ball is stationary at random positions, and finally extends it to moving-ball shooting through a locomotion-command and kick-trigger interface. A high-level heuristic planner controls this interface during training, while alternative high-level controllers can drive the same low-level policy at inference. In simulation, RoboNaldo demonstrates free-kick shot error 48.6% lower and shoot velocity 2.96x than prior work baselines. In real world on a Unitree G1 with onboard perception, RoboNaldo attains 0.73 m and 0.86 m average target shooting error from 3 m away in free-kick and moving-ball cases, accordingly. And the post-contact ball velocity reaches 13.10 m/s, which is 59-71% of reported professional open-play shot speed. Project page: https://opendrivelab.com/RoboNaldo.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2512.03818

Improving Alignment Between Human and Machine Codes: An Empirical Assessment of Prompt Engineering for Construct Identification in Psychology

作者:

Kylie L. Anglin↗Stephanie Milan↗Brittney Hernandez↗Claudia Ventura↗

Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the prompt. While literature on prompt engineering is expanding, few studies focus on classification tasks, and even fewer address domains like psychology, where constructs have precise, theory-driven definitions that may not be well represented in pre-training data. We present an empirical framework for optimizing LLM performance for identifying constructs in texts via prompt engineering. We experimentally evaluate five prompting strategies – codebook-guided empirical prompt selection, automatic prompt engineering, persona prompting, chain-of-thought reasoning, and explanatory prompting - with zero-shot and few-shot classification. We find that persona, chain-of-thought, and explanations do not fully address performance loss accompanying a badly worded prompt. Instead, the most influential features of a prompt are the construct definition, task framing, and, to a lesser extent, the examples provided. Across three constructs and two models, the classifications most aligned with expert judgments resulted from a few-shot prompt combining codebook-guided empirical prompt selection with automatic prompt engineering. Based on our findings, we recommend that researchers generate and evaluate as many prompt variants as feasible, whether human-crafted, automatically generated, or ideally both, and select prompts and examples based on empirical performance in a training dataset, validating the final approach in a holdout set. This procedure offers a practical, systematic, and theory-driven method for optimizing LLM prompts in settings where alignment with expert judgment is critical.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12071

On the Limits of LLM-as-Judge for Scientific Novelty Assessment

作者:

Soumitra Sinhahajari↗Navonil Majumder↗Soujanya Poria↗

arXiv:2606.12071v1 Announce Type: cross Abstract: LLMs are increasingly used to generate and judge scientific ideas. This makes novelty evaluation a central problem. Full idea evaluation is difficult because it often requires judging a method, its feasibility, and its empirical promise. We therefore study a cleaner upstream object: the research question (RQ). RQ generation is a prerequisite for scientific ideation, and RQs can be compared against questions pursued in real papers. We introduce RQ-Bench, a benchmark built from recent arXiv papers. For each paper, we reconstruct author-anchored RQs from its cited background, gaps, and contributions. These RQs are not the only valid questions for the same background. They are author-anchored reference points for testing novelty judgments. We evaluate model-generated RQs with standalone LLM judging, comparative LLM judging, and human expert evaluation. LLM judges consistently rate model-generated RQs as highly novel, producing a novelty mirage; in comparative evaluations, this preference becomes even stronger. Domain experts, however, reach the opposite conclusion and prefer the author-anchored reference questions. We further find that many generated RQs are narrow or source-bound, a dimension that LLM judges often miss unless explicitly tested. Overall, the contradictory novelty evaluations between LLM judges and human experts raise a serious concern about the reliability of using LLMs to assess the scientific novelty of research questions.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16342

When the Past Matters: FlashBack Memory for Precipitation Nowcasting

作者:

Yuhao Du↗Boxiao Huang↗Chengrong Wu↗Jiankai Zhang↗

Accurate precipitation nowcasting is crucial for disaster mitigation and socio-economic planning, yet existing methods often struggle with false alarms, missed events, and long range dependency modeling at high spatiotemporal resolution. To address these challenges, we propose FlashBack Memory (FB), a module that dynamically retrieves key historical states and integrates them via an adaptive fusion gate, enhancing the spatiotemporal representation capability of recurrent-based models. We incorporate FB into PredRNN, PredRNNpp, MIM, MotionRNN, and PredRNN-V2, and evaluate on CIKM2017, Shanghai2020, and SEVIR datasets. Experimental results demonstrate that FB significantly improves MSE, MAE, SSIM, and CSI metrics, particularly for high-intensity rainfall and long-sequence predictions, while reducing false alarms and missed events and enhancing temporal consistency and spatial localization. The proposed method provides a general and efficient memory enhancement mechanism, improving the overall performance of recurrent-based precipitation nowcasting models.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13317

SkillCAT: Contrastive Assessment and Topology-Aware Skill Self-Evolution for LLM Agents

作者:

Kunfeng Chen↗Qihuang Zhong↗Juhua Liu↗Bo Du↗

Skill self-evolution methods for LLM agents aim to turn execution trajectories into reusable skill documents, but current pipelines typically learn from one trajectory per task, merge candidate skill patches before checking them, and load the full skill corpus before inference. We propose SkillCAT, a training-free framework that separates this process into three stages. Contrastive Causal Extraction (CCE) samples multiple trajectories for each task and compares same-task success/failure pairs to identify evidence that explains outcome differences. Assessment-Augmented Evolution (AAE) replays each candidate patch on source-task clones and keeps only patches that improve or preserve task outcomes before hierarchical skill patch merging. Topology-Aware Task Execution (TTE) compiles the evolved skills into a routable sub-skill topology, so inference loads only the capability nodes relevant to the task. We evaluate SkillCAT on common agent benchmarks, including SpreadsheetBench, WikiTableQuestions, and DocVQA, and further test cross-model and out-of-distribution generalization. Across these settings, SkillCAT raises the average score over baselines by up to 40.40%, demonstrating reliable skill evolution without model training.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17514

Unlocking LLM Code Correction with Iterative Feedback Loops

作者:

Le Zhang↗Suresh Kothari↗

arXiv:2606.17514v1 Announce Type: cross Abstract: Large Language Models have shown remarkable capabilities in code generation. However, most existing evaluations focus only on single-attempt accuracy and overlook the iterative refinement process that is central to real-world programming. This study presents a systematic investigation of LLMs' ability to rectify their own code through execution feedback. Using real-world programming problems across four models and two major programming languages, this study evaluates performance using iterative refinement framework where LLMs receive compiler error messages and testcase feedback after each attempt. This study introduces metrics to evaluate code failures, analyze rectification patterns, and compare the effectiveness of reasoning and non-reasoning models, offering actionable insights into both the understanding and practical application of feedback loops in LLM-driven code generation systems. Results show that reasoning models consistently improve over iterations, substantially outperforming non-reasoning models in leveraging feedback, while syntactic and runtime errors are far more tractable than logical or algorithmic failures.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17504

Two-Stage Fine-Tuning of ResNet50 for High-Sensitivity Melanoma Detection on Dermoscopic Images

作者:

Aryan Bhagat↗

Melanoma is the most dangerous form of skin cancer with five-year survival rates exceeding 99% when detected early but falling sharply once the disease spreads. This paper proposes and evaluates a two-stage fine-tuning approach for ResNet50 applied to binary melanoma classification on dermoscopic images. The core challenges addressed are class imbalance and suboptimal transfer learning from single-stage fine-tuning. After stratified train/validation/test splitting, random oversampling was applied exclusively to the training set to achieve a 1:1 class balance. Stage 1 trained only the classification head with the ResNet50 base frozen, while Stage 2 fine-tuned all layers jointly at a low learning rate of 1e-5 to prevent catastrophic forgetting of learned visual features. On an independent test set of 3,826 images, the model achieved an AUC-ROC of 0.9559, accuracy of 88.34%, sensitivity of 87.56%, specificity of 89.13%, and F1-score of 88.29%. An ablation study confirms the two-stage protocol significantly outperforms single-stage fine-tuning, with sensitivity gains of over 4%. Grad-CAM visualizations demonstrate correct lesion localization. A fully deployable Streamlit detection application is provided alongside all training code.

阅读与讨论 → 访问原文 →

13.

medRxiv (Medicine) 2026-06-22 DOI: HASH:94aabd33acfb6378c8bba41d3c6699ab

Evidence-guided AI regularization for suicidal ideation prediction in pediatric bipolar disorder

作者:

Jabbar Abdl Sattar Hamoudi↗Wu↗M.-J↗Sanches↗Zunta-Soares↗G. B↗Soutullo↗C. A↗Soares↗J. C↗Mwangi↗

Background: Suicide prediction models in psychiatry often rely on purely data-driven feature selection, which can produce unstable and clinically opaque predictor sets in modest-sized samples. We developed Evidence-Based AI LASSO (EBAL), an evidence-guided regularization framework that incorporates curated clinical evidence into feature-specific penalty factors for interpretable prediction. Methods: Baseline data from 136 youth with confirmed bipolar spectrum disorder in the Greater Houston Area Bipolar Registry were analyzed using 20 candidate clinical predictors. Forty higher-level evidence documents on suicidality and related predictor domains were curated through a structured evidence synthesis workflow and indexed as an auditable evidence corpus. An open-weight large language model assigned feature-specific penalty factors using a prespecified scoring rubric, and these penalties were used to fit a weighted LASSO model. EBAL was compared with a standard evidence-agnostic LASSO using nested leave-one-out cross-validation. Results: For suicidal ideation, EBAL achieved an AUROC of 0.768, balanced accuracy of 0.757, sensitivity of 0.758, and specificity of 0.757. The standard LASSO achieved an AUROC of 0.760 and balanced accuracy of 0.715. EBAL improved balanced accuracy (+0.042, p=0.010) and Matthews correlation coefficient (+0.079, p=0.010), while retaining fewer stable predictors than standard LASSO (11/20 vs 18/20). The strongest positive predictors were current depressed mood, duration of mood disorder illness, and comorbid generalized anxiety disorder. For suicidal behavior, both models performed near chance and retained all candidate predictors. Limitations: The study was cross-sectional, single-site, and modest in sample size, with no external validation cohort. Conclusions: EBAL produced a sparser and more clinically coherent model for suicidal ideation in pediatric bipolar disorder, but did not improve prediction of suicidal behavior. These findings support evidence-guided regularization as a transparent strategy for aligning psychiatric prediction models with prior clinical knowledge while preserving interpretability.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11671

Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security

作者:

Tu Lan↗Chaowei Xiao↗

arXiv:2606.11671v1 Announce Type: cross Abstract: Agent skills let LLM agents reuse instructions, resources, tools, and workflows, but they also create a new place for malicious behavior to hide. A skill may look benign in its documentation or code while becoming harmful only when it is invoked with particular user requests, local assets, persistent state, or multi-step tool interactions. This makes purely static vetting brittle. We present Runtime Skill Audit (RSA), a dynamic analysis method that audits skills by asking what the skill-mediated agent actually does under targeted runtime conditions. Instead of testing every skill with the same generic tasks, RSA profiles risk-relevant interfaces, prepares the execution context needed to exercise them, and assigns security labels from the resulting trace evidence. We instantiate RSA on OpenClaw and evaluate it on 100 skills against representative static baselines. RSA achieves 90.0\% accuracy with an 88.0\% true positive rate and an 8.0\% false positive rate, improving accuracy by 13.0 percentage points over the best static baseline. Under self-evolving attacks, static detectors collapse after one or two rounds, while RSA continues to detect 19–20 out of 20 malicious skills across rounds.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.19338

Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games

作者:

Shengyuan Ding↗Xilin Wei↗Xinyu Fang↗Haodong Duan↗Dahua Lin↗Jiaqi Wang↗Yuhang Zang↗

Deploying multimodal foundation models as closed-loop policies increasingly requires conditioning actions on observations that are no longer visible. However, existing benchmarks either expose the full state, conflate hidden-state reconstruction with other agent skills, or test recall only after an episode has ended. We introduce RNG-Bench (Reconstructive Non-Markov Games), a benchmark suite designed to isolate a base model's ability to reconstruct past observations and act on them during multi-step interaction. RNG-Bench includes two complementary games: Matching Pairs, where card identities briefly revealed at specific locations must later be recalled, and 3D Maze, where egocentric views must be integrated into a spatial map. Both games are evaluated under a unified harness with three controlled difficulty axes: grid size, visual pattern, and observation modality. The benchmark further introduces a head-to-head duel protocol to control for instance-level variance and a Memory Gap metric that disentangles forgetting from poor action selection. The hardest configurations require contexts of roughly 128K tokens and 350 image inputs per episode, and remain far from saturated by frontier MLLMs. Memory Gap analysis shows that most residual errors stem from forgetting earlier observations rather than from suboptimal decision making. Finally, fine-tuning Qwen3.5-9B on optimal-policy rollouts and filtered model demonstrations improves performance on RNG-Bench and transfers to existing benchmarks without degrading general multimodal capability.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2601.23278

FOCUS: DLLMs Know How to Tame Their Compute Bound

作者:

Kaihua Liang↗Xin Tan↗An Zhong↗Hong Xu↗Marco Canini↗

Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost. In this work, we identify a key inefficiency in DLLM decoding: while computation is parallelized over token blocks, only a small subset of tokens is decodable at each diffusion step, causing most compute to be wasted on non-decodable tokens. We further observe a strong correlation between attention-derived token importance and token-wise decoding probability. Based on this insight, we propose FOCUS, an inference system designed for DLLMs. By dynamically focusing computation on decodable tokens and evicting non-decodable ones on-the-fly, FOCUS increases the effective batch size, alleviating compute limitations and enabling scalable throughput. Empirical evaluations demonstrate that FOCUS achieves up to 3.52$\times$ throughput improvement over the production-grade engine LMDeploy in large-batch settings, while preserving or improving generation quality across multiple benchmarks.

阅读与讨论 → 访问原文 →

17.

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 →

18.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.19026

A Hybrid LSTM–Vision Transformer Architecture for Predicting HRRR Forecast Errors

作者:

David Aaron Evans↗Jay C. Rothenberger↗Kara J. Sulia↗Nick P. Bassill↗Chris D. Thorncroft↗

arXiv:2606.19026v1 Announce Type: cross Abstract: Forecast errors in high-resolution numerical weather prediction (NWP) systems are often linked to unresolved planetary boundary layer (PBL) processes, convection, terrain-induced circulations, and other vertically structured atmospheric phenomena. Previous work demonstrated that Long Short-Term Memory (LSTM) networks can successfully predict forecast errors in the High-Resolution Rapid Refresh (HRRR) model using mesonet observations, but we believe performance degradation is linked to periods of complex vertical atmospheric evolution. To address this limitation, we develop a hybrid LSTM-Vision Transformer (LSTM-ViT) framework that combines temporal sequence learning from surface observations with atmospheric profiles from the New York State Mesonet profiler network. The LSTM-ViT framework is trained to predict HRRR hourly precipitation, 10 m wind speed, and 2 m temperature forecast errors at individual mesonet stations. Across all three predictors, incorporation of profiler-derived atmospheric structure improves forecast error prediction skill relative to the baseline LSTM architecture, with the largest gains occurring at shorter forecast lead times and during periods of enhanced PBL activity. Improvements are particularly pronounced for precipitation forecast error, where the LSTM-ViT framework achieves approximately a twofold increase in predictive skill relative to the baseline LSTM while better capturing convectively driven error evolution and reducing degradation associated with PBL processes. These results demonstrate that combining temporal sequence learning with vertically informed attention mechanisms provides a physically meaningful pathway for improving forecast error prediction in operational NWP systems. Our research offers forecasters enhanced guidance regarding model bias and forecast confidence.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2605.30837

Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense

作者:

Shuhao Zhang↗Jiarui Li↗Qi Cao↗Ruiyi Zhang↗Pengtao Xie↗

arXiv:2605.30837v2 Announce Type: replace-cross Abstract: Prompt-injection detectors are heterogeneous: each is strong on a different slice of attacks, and none is always reliable. Yet existing systems still treat detection as a fixed single-detector pipeline, committing every request to one detector's blind spots. We reframe defense as detector allocation: given a heterogeneous pool, decide per request which detectors to run and whether to escalate to an LLM judge. Our framework SCOUT (Scalable and Controllable Outcome-prediction for Uncertainty-aware Triage) makes this decision dynamic by predicting each detector's per-sample reliability and latency from how it behaved on similar past inputs, and exposes a single safety-utility threshold to the operator (where utility bundles benign-pass rate and wall-clock). To evaluate this setting, we build SCOUT-450, a benchmark that captures the structurally complex, agent-facing injections that older prompt-injection sets under-represent. On SCOUT-450, a safety-oriented operating point reduces attack-success rate by 46% and total wall-clock by 40% relative to an always-on GPT-4o judge, at a 5.1-point benign-utility drop. SCOUT also transfers to three external benchmarks (BIPIA, IPI, and IHEval), improving the safety-utility frontier.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12169

OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language Models

作者:

Negin Baghbanzadeh↗Pritam Sarkar↗Michael Colacci↗Abeer Badawi↗Adibvafa Fallahpour↗Arash Afkanpour↗Leonid Sigal↗Ali Etemad↗Elham Dolatabadi↗

High-stakes clinical use of large vision-language models (LVLMs) requires reasoning that is grounded in visual evidence and clinical knowledge, not just correct final answers. We introduce OpenMedReason, a large-scale, open multimodal medical reasoning corpus comprising approximately 450K image-question-answer instances whose reasoning traces are primarily derived from curated biomedical, human-authored scientific articles. OpenMedReason provides high-fidelity supervision beyond synthetic chains of thought, covering diverse medical domain vision modalities such as radiological scans, microscopic images, visible light photographs, charts, and others. We complement it with OpenMedReason-Bench, a held-out benchmark that allows fine-grained evaluation of LVLMs along three complementary axes of capability, including perception, medical knowledge, and rationale, enabling diagnostic evaluation beyond final-answer accuracy. OpenMedReason is a rich training resource that exhibits its effectiveness in both supervised fine-tuning (SFT) and reinforcement-based alignment. Training with OpenMedReason yields a 20% average improvement in VQA accuracy over the base model and achieves performance within 4.2% of the strongest comparable-scale medical LVLMs. Fine-grained performance analysis confirms that the gains are not concentrated in any single axis: OpenMedReason improves perception, medical knowledge, and rationale jointly, and its reasoning traces are preferred over those of the base model in 86.1% of pairwise comparisons. We release the code and dataset at huggingface.co/datasets/neginb/OpenMedReason.

阅读与讨论 → 访问原文 →

21.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2505.10530

Exploring Variational Entanglement Hamiltonians

作者:

Yanick S. Kind↗Benedikt Fauseweh↗

arXiv:2505.10530v3 Announce Type: replace Abstract: Recent advances in analog and digital quantum-simulation platforms have enabled exploration of the spectrum of entanglement Hamiltonians via variational algorithms. In this work we analyze the convergence properties of the variationally obtained solutions and compare them to numerically exact calculations in quantum critical systems. We demonstrate that interpreting the cost functional as an integral permits the deployment of iterative quadrature schemes, thereby reducing the required number of measurements by more than an order of magnitude even in the presence of noise. We further show that a modified ansatz captures deviations from the Bisognano-Wichmann form in lattice models, improves convergence, improves trainability and provides a cost-function-level diagnostic for quantum phase transitions. Finally, we establish that a low cost value does not by itself guarantee convergence in trace distance. Nevertheless, it faithfully reproduces degeneracies and spectral gaps, which are essential for applications to topological phases.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2602.08986

Improving Detection of Rare Nodes in Hierarchical Multi-Label Learning

作者:

Isaac Xu↗Martin Gillis↗Ayushi Sharma↗Benjamin Misiuk↗Craig J. Brown↗Thomas Trappenberg↗

arXiv:2602.08986v2 Announce Type: replace-cross Abstract: In hierarchical multi-label classification, a persistent challenge is enabling model predictions to reach deeper levels of the hierarchy for more detailed or fine-grained classifications. This difficulty partly arises from the natural rarity of certain classes (or hierarchical nodes) and the hierarchical constraint that ensures child nodes are almost always less frequent than their parents. To address this, we propose a weighted loss objective for neural networks that combines node-wise imbalance weighting with focal weighting components, the latter leveraging modern quantification of ensemble uncertainties. By emphasizing rare nodes rather than rare observations (data points), and focusing on uncertain nodes for each model output distribution during training, we observe improvements in recall by up to a factor of five on benchmark datasets, along with statistically significant gains in $F_{1}$ score. We also show our approach aids convolutional networks on challenging tasks, as in situations with suboptimal encoders or limited data.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2508.04086

ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients"

作者:

Zhongyi Zhou↗Kohei Uehara↗Haoyu Zhang↗Jingtao Zhou↗Lin Gu↗Ruofei Du↗Zheng Xu↗Tatsuya Harada↗

Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like depth-first search (DFS). This leads to inevitable annotation failures and low efficiency in data generation. We introduce ToolGrad, an agentic framework that inverts this paradigm. ToolGrad first constructs valid tool-use chains through an iterative process guided by textual "gradients", and then synthesizes corresponding user queries. This "answer-first" approach led to ToolGrad-500, a dataset generated with more complex tool use, lower cost, and almost 100% pass rate. Experiments show that ToolGrad models outperform those trained on expensive baseline datasets and proprietary LLMs. The ToolGrad source code, dataset, and models are available at https://github.com/zhongyi-zhou/toolgrad.

阅读与讨论 → 访问原文 →

24.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.15467

Hardy and Cabello Arguments in Spatial and Temporal Frauchiger-Renner Scenarios

作者:

Ehsan Erfani Maharat↗Ali Ahanj↗Mohsen Sarbishaei↗

arXiv:2606.15467v1 Announce Type: new Abstract: We investigate Hardy- and Cabello-type logical structures within spatial and temporal extensions of the Frauchiger–Renner (FR) framework, embedding these constructions directly into the FR multi-observer architecture. In the spatial multi-observer scenario, both Hardy and Cabello contradictions arise, with the Cabello construction yielding the stronger violation,$\(\Delta_Cabello^{\max}=0.1078\)$, which exceeds the maximal Hardy probability $\(P_{H}^{\max}=\frac{5\sqrt{5}-11}{2}\approx 0.09017\)$. We then develop a sequential temporal FR protocol based on coherent multi-observer measurements performed on a single spin-$\tfrac12$ system. In this temporal setting, the Hardy contradiction disappears identically due to dynamical constraints imposed by sequential state updates, whereas a finite Cabello-type violation survives, \(\Delta_Cabello^{\max}\approx 0.0674\). Our results establish a fundamental structural distinction between spatial entanglement and temporal multi-observer correlations in FR-type logical scenarios, and demonstrate that certain observer-independent description failures persist even without spacelike separation.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2604.06961

Auditing Demographic Bias in Facial Landmark Detection for Fair Human-Robot Interaction

作者:

Pablo Parte↗Roberto Valle↗Jos\'e M. Buenaposada↗Luis Baumela↗

Fairness in human-robot interaction critically depends on the reliability of the perceptual models that enable robots to interpret human behavior. While demographic biases have been widely studied in high-level facial analysis tasks, their presence in facial landmark detection remains unexplored. In this paper, we conduct a systematic audit of demographic bias in this task, analyzing the age, gender, and race biases. To this end, we introduce a controlled statistical methodology to disentangle demographic effects from confounding visual factors. Our analysis demonstrates that visual confounders, particularly head pose and face resolution, heavily outweigh the impact of demographic attributes. Notably, after accounting for these confounders, performance disparities across gender and race vanish. However, we identify a statistically significant age-related bias, with higher localization errors for older individuals. This shows that fairness issues can emerge even in low-level vision components and can propagate through the HRI pipeline. We argue that auditing and correcting such biases is a necessary step toward trustworthy and equitable robot perception systems.

阅读与讨论 → 访问原文 →