Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
medRxiv (Medicine) 2026-06-15

Excitation-Inhibition Balance in Schizophrenia Spectrum Disorders: EEG Criticality Reflects Frontal Metabolites and a Potential Compensatory Mechanism

Background The excitation-inhibition (E-I) balance is essential for normal brain functioning, while deviations from this balance have been implicated in several psychiatric disorders. However, the extent to which electroencephalography (EEG) and proton magnetic resonance spectroscopy (1H-MRS) E-I markers are altered in schizophrenia spectrum disorders (SSD), how they converge across modalities, and how they relate to cognitive performance and clinical symptoms remain insufficiently characterized. Methods We recruited 111 healthy controls (HC) and 113 individuals with SSD. All participants underwent resting-state EEG and 1H-MRS. Metabolites were measured either in the anterior cingulate cortex (ACC; NSSD = 63, NHC = 58) or in the left dorsolateral prefrontal cortex (lDLPFC; NSSD = 50, NHC = 53), from which gamma-aminobutyric acid (GABA), glutamate + glutamine (Glx), and the Glx/GABA ratio were extracted. Extracted EEG E-I markers included oscillatory activity, aperiodic activity, functional E-I, microstates, multiscale entropy, and neuronal avalanche criticality. Results MRS results showed no group differences in GABA, Glx, or the Glx/GABA ratio. In contrast, most EEG-derived E-I markers indicated increased cortical inhibition in SSD, including steeper aperiodic exponents, prolonged microstate durations, and greater prevalence of subcritical states. However, functional E-I showed a divergent pattern, suggesting balanced dynamics in SSD and relatively inhibition-weighted dynamics in HC. Across groups, higher ACC and lDLPFC GABA predicted a lower kappa index, whereas a higher lDLPFC Glx/GABA ratio was associated with a higher kappa index. In SSD, reduced avalanche criticality was associated with better cognition and less severe symptoms. Conclusion Several EEG-derived E-I proxies, but not MRS measures, indicate an increased cortical inhibition in SSD. Criticality indices best capture frontal neurochemical metabolites and improvements in clinical symptoms, potentially reflecting inhibitory compensation mechanisms in SSD.

02.
arXiv (CS.CL) 2026-06-24

EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answering

Large language models are increasingly used to answer questions over annual reports, earnings decks, and analyst notes, yet their outputs remain difficult to verify in high-stakes financial workflows. A fluent answer can blend directly grounded statements, weak synthesis, and unsupported claims across narrative text, tables, and charts. We present EvidenceLens, a visual analytics prototype that treats financial question answering as a claim-evidence alignment problem. The system decomposes an answer into atomic claims, summarizes support composition and confidence, support gaps, and coordinates claim-level inspection with source passages, table cells, and chart regions. Its core visual representation is a multimodal claim-evidence matrix that makes coverage, contradiction, and modality imbalance immediately visible. To support reproducibility, we also specify a JSON-based artifact schema, a lightweight multimodal alignment pipeline, and a deterministic review-priority ranking that maps backend signals into an auditable visual structure. Through representative report-auditing scenarios, we show how EvidenceLens helps analysts distinguish grounded claims from overconfident synthesis that conventional chat interfaces flatten.

03.
arXiv (CS.CV) 2026-06-12

EquiDexFlow: Contact-Grounded SE(3)-Equivariant Dexterous Grasp Generative Flows

Most learned dexterous grasp generators relegate contact forces to a downstream verification step, so a kinematically-plausible pose can still violate the conditions for a stable physical grasp. We address this with EquiDexFlow, an SE(3)-equivariant flow-matching model that jointly predicts wrist pose, joint angles, fingertip contacts, surface normals, and contact forces from an object point cloud. Our architecture projects contacts onto the object surface and forces into the Coulomb friction cone by construction, so placement and friction compliance hold without loss penalties. We prove end-to-end SE(3) equivariance and verify it empirically over 200 rotations, with wrist residuals below $0.04^\circ$ and exactly zero joint deviation. Trained on 8,100 force-closure grasps across 81 objects for the 16-DoF Allegro Hand, our model achieves zero friction violations, the best composite score, and the lowest wrench residual among all ablation variants. We retarget decoded fingertip contacts to a 16-DoF LEAP Hand via per-finger inverse kinematics, and our hardware-feasible refinement places every joint at least 5% inside its actuator envelope while preserving wrench balance. On the physical robot, retargeted EquiDexFlow-decoded grasps complete open-loop pick-and-hold trials on all six test objects, with every asymmetric object succeeding at both the canonical pose and a $120^\circ$ co-rotation. Videos, code, and checkpoints are available at https://equidexflow.github.io.

04.
arXiv (CS.AI) 2026-06-15

Applicability Condition Extraction for Therapeutic Drug-Disease Relations

arXiv:2606.14031v1 Announce Type: new Abstract: Identifying conditions that a certain drug takes therapeutic effect on a target disease is crucial for clinical decision-making support. However, most existing biomedical information extraction methods have focused on identifying only relations between drugs and diseases, while largely overlooking the context-specific conditions where such relations can apply. To address this problem, we introduce the task of applicability condition extraction for therapeutic drug–disease relations from biomedical research literature. We create the first dataset that has manually annotated triples of drugs, diseases, and applicability conditions on biomedical paper abstracts with 1,119 drug-disease pairs. Using this dataset, we systematically evaluate the performance of a range of existing methods. In addition, we propose a new method that enhances LoRA to consider relations between drugs and diseases. Our method consistently outperforms strong baselines across different evaluation settings. The source code and dataset of this paper can be obtained from: https://github.com/guantingluo98/Drug-ACE

05.
arXiv (CS.AI) 2026-06-24

Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs

arXiv:2511.20892v4 Announce Type: replace Abstract: Large language models (LLMs) often produce incorrect or outdated content after being employed. Efficient and accurate knowledge updates without costly retraining are a major challenge. This problem is particularly challenging in lifelong settings, where complex, unstructured knowledge must coexist without interference. We introduce RILKE (Representation Intervention for Lifelong KnowledgE Control), a robust and scalable method that treats knowledge control as interventions within the model's representation space. Leveraging representation-space expressiveness, we identify two key properties enabling RILKE to achieve fine-grained control over complex, unstructured knowledge while maintaining general utility with frozen base weights. During training, RILKE learns paraphrase-robust and edit-localized modules that limit each update to a low-dimensional subspace to minimize cross-edit interference. At inference, a query-adaptive router selects the appropriate module to guide the model's generation. Across LLaMA and Qwen models, RILKE scales effectively to large-scale benchmarks, demonstrating high edit success and strong paraphrase generalization while preserving general utility with modest memory overhead. These results show RILKE is an effective and scalable solution for lifelong knowledge control in LLMs.

06.
arXiv (CS.AI) 2026-06-16

ControlMap: Controllable High-Definition Map Generation for Traffic Scenario Simulation

arXiv:2606.15930v1 Announce Type: cross Abstract: Simulation is central to validating autonomous driving systems, yet current pipelines are limited by insufficient scenario diversity due to costly High Definition (HD) map creation. Scaling HD maps requires expensive data collection and manual processing. Moreover, existing generative models lack the fine-grained control necessary to target specific road topologies during generation. This paper presents a data-driven pipeline for controllable HD map generation using latent diffusion and ControlNet for spatial conditioning. To our knowledge, we are the first to inject spatial guidance signals into a diffusion model for HD map synthesis. Furthermore, our model supports adjustable conditioning strength through classifier-free guidance and city-level style transfer via city label conditioning. To complement existing metrics, we introduce two novel metrics to evaluate adherence to the control signal and similarity to ground-truth maps. Experiments demonstrate that our model generates realistic HD maps that faithfully follow input road topologies while accurately preserving city-specific details.

07.
arXiv (CS.CL) 2026-06-17

From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models

Interpretability methods routinely use population-level summary statistics over observed model behaviour to license claims about the effects of targeted interventions on specific computations; in Pearl's terms, they treat rung-1 associational evidence as if it supported rung-2 interventional conclusions, a move whose validity is rarely tested. We examine one concrete instance: the use of routing statistics in Mixture-of-Experts (MoE) pruning, where utilization rates, activation norms, and routing weight distributions are treated as predictors of which experts can be removed without functional cost. A token-level interventional audit across three high-redundancy MoE architectures (OLMoE-1B-7B-0924, Qwen1.5-MoE-A2.7B, DeepSeek-V2-Lite) finds no observational metric predicts causal expert importance in any model: across all 60 metric-layer combinations effect sizes stay below Cohen's $d = 0.23$, and no metric is reliably positive under our corrected, dual-test criterion. A per-token routing weight control, run with identical $n$, rules out insufficient power, recovering a signal whose CI excludes zero at OLMoE's final MoE layer ($d = +0.231$, 95\% CI $[+0.09, +0.37]$, $p = 0.0013$). Existing pruning methods succeed in this regime not by identifying dispensable experts but because early-layer redundancy renders most selection criteria interchangeable. Our results provide an explicit counterexample to the common inferential step from population-level observational summaries to token-level interventional claims about expert importance, and illustrate how interventional audits can calibrate the evidential standards for interpretability claims.

08.
arXiv (CS.AI) 2026-06-11

SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving

arXiv:2606.11244v1 Announce Type: cross Abstract: Efficient large language model (LLM) serving is increasingly constrained by deployment cost. Quantization is a key technique for reducing serving cost, yet even state-of-the-art 4-bit quantizers exhibit a noticeable quality gap from FP16, particularly for smaller models where low-bit serving is most beneficial. We identify a fundamental cause of this gap: quantization error is highly input-dependent and varies substantially across tokens, while existing post-quantization compensation methods are static and apply identical corrections to all inputs. As a result, easy tokens are over-corrected while hard tokens remain under-corrected. We present SPEAR, a system for post-quantization error-adaptive recovery that improves low-bit LLM serving. SPEAR introduces lightweight Error Compensators (ECs) modulated by per-token gates and places them only at the most error-sensitive layers identified through a CKA-guided entropy-aware diagnostic. This focuses a small parameter budget where it is most effective. Efficient deployment of ECs presents several systems challenges, including additional computation, tensor-parallel synchronization caused by input-dependent gating, and latency instability across configurations. SPEAR addresses these issues through adaptive kernel-fusion dispatch, combining an epilogue-integrated peer-reduction kernel with P2P dual-write to fuse the post-EC computation into low-bit GEMMs, and an SLO-constrained EC-aware scheduler for predictable serving performance. Across challenging per-channel quantization settings, SPEAR recovers 56-75% of the perplexity gap between W4 and FP16 while adding less than 1% model memory overhead and maintaining latency comparable to a widely used 4-bit serving deployment.

09.
arXiv (CS.LG) 2026-06-25

Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Trainig-Time Reward Hacking in Code Generation

arXiv:2604.23488v2 Announce Type: replace Abstract: Reward hacking in code generation, where models exploit evaluation loopholes to obtain high reward without correctly solving the intended task, poses a critical challenge for Reinforcement Learning (RL) and the deployment of reasoning models. Existing studies often rely on explicitly prompted hacking trajectories, but it remains unclear whether monitors trained on such data can detect reward hacks that arise without direct hacking instructions during RL training. In this work, we introduce Trace-and-Amplify, a framework for scalable curation of reward-hacking trajectories that arise during RL training without explicit hacking instructions. The framework uses unit-test tracers to identify hacking solutions when they occur and retains such trajectories for monitor training and evaluation. Through controlled comparisons between monitors trained on prompt-elicited hacking trajectories and training-time reward-hacking trajectories collected by Trace-and-Amplify, we find that (1) prompt-elicited-data-trained monitors often fail to generalize to trajectories curated by our framework, and (2) monitors trained on our Trace-and-Amplify trajectories demonstrate stronger generalizability to unseen hacking types. Our results indicate that prompted reward hacking data may not fully reflect training-time reward-hacking behaviors, and that relying solely on these data can lead to misleading conclusions. Codebase is available at https://github.com/LichenLillc/CoTMonitoring.git

10.
arXiv (CS.AI) 2026-06-19

Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manufacturing

arXiv:2606.20087v1 Announce Type: new Abstract: Additive manufacturing process optimization requires precise parameter control to minimize defects such as porosity. Traditional reinforcement learning (RL) approaches using discrete action spaces suffer from slow convergence and susceptibility to local optima, limiting their effectiveness for high-precision manufacturing tasks. This study addresses these limitations by employing a continuous action space combined with a novel architecture that integrates a multi-head attention mechanism with the Soft Actor-Critic (SAC) algorithm. The attention-based feature extractor enhances the agent's ability to capture subtle variations in low-dimensional input features, enabling more effective exploration-exploitation balance for navigating value spaces with local minima. We validate our approach on porosity prediction and process parameter optimization in laser powder bed fusion, demonstrating faster convergence and higher final reward values compared to standard RL methods including DQN, PPO, TD3, and vanilla SAC. The proposed methodology achieves a convergence value of 322.79 within 14 episodes, outperforming existing approaches while maintaining stability throughout training.

11.
medRxiv (Medicine) 2026-06-22

The impact of changes in age-based eligibility criteria on seasonal influenza vaccine uptake in England between 2019 and 2024: A retrospective cohort study

Objectives: To examine changes in seasonal influenza vaccine uptake among clinical risk groups over periods of differing age-based eligibility. Design: Retrospective cohort study. Setting: Individuals in England registered in the Clinical Practice Research Datalink Aurum. Participants: Between 1,239,802 (2019/20) and 1,289,330 (2023/24) individuals aged 40-69 years in clinical risk groups. Interventions: Natural experiment involving temporary expansion of age-based eligibility for influenza vaccination to include 50-64-year-olds from 2020/21 to 2022/23. Main outcome measures: Influenza vaccine uptake from 1st September to 28th February, incidence rate ratio (IRR) of vaccine uptake across consecutive seasons within age groups, and the ratio of IRRs between age groups. Results: Influenza vaccine uptake increased in all age groups in 2020/21 relative to 2019/20. The increase was larger in individuals aged 50-64 years (13.3%; IRR 1.50, 95% CI 1.50-1.51) compared with those aged 40-49 years (8.3%; IRR 1.35, 95% CI 1.34-1.35) and 65-69 years (6.8%; IRR 1.34, 95% CI 1.33-1.35). From 2020/21 to 2022/23, vaccine uptake decreased, with a more pronounced decline among those aged 40-49 years (-5.4%) compared with age-eligible groups (50-64 years: -3.0%; 65-69 years: -3.1%). The reversion of age eligibility in 2023/24 was associated with a larger decrease in uptake among those aged 50-64 years (-9.6% vs 2022/23; IRR 0.79, 95% CI: 0.79-0.79) compared with those aged 40-49 years (-4.9%; IRR 0.87, 95% CI: 0.87-0.88) and 65-69 years (-3.3%; IRR 0.97, 95% CI: 0.96-0.97). Patterns were broadly consistent across clinical risk groups. Conclusions: The COVID-19 pandemic saw a general increase in seasonal influenza vaccine uptake in clinical risk groups. This increase was larger and more sustained in 50-64 year-olds who had also become eligible based on age. Our findings highlight the potential gains in vaccine coverage among clinical risk groups based on expanded age-based eligibility.

12.
arXiv (CS.LG) 2026-06-12

How Reliable are Fairness Audits with Unreliable Data?

arXiv:2506.23033v3 Announce Type: replace Abstract: Fairness audits are a key component of responsible machine-learning deployment. Yet, audit-recommendation reliability under incomplete protected-label access is still poorly understood. In this work, we focused on protected-label missingness in fairness mitigation audits. We introduced a seed-calibrated stress test to separate missingness effects from seed-to-seed movement already present under complete labels. Across ACS/Folktables tasks, missingness settings that retain some protected labels usually do not move selected mitigation methods beyond a complete-label seed-to-seed baseline. At $0%$ protected-label access, candidates collapse to an empirical-risk-minimization baseline and deterministic tie-breaking rather than revealing a broad missingness effect. We also found that threshold optimization can turn fairness gains on a single protected axis into intersectional harm above a seed baseline, and this threshold-optimizer finding persists under random-forest validation. Overall, our results highlight that protected-label missingness should be reported with seed-null calibration, candidate-set context, and intersectional consequences before it is treated as evidence of audit fragility.

13.
arXiv (CS.LG) 2026-06-12

Positional Encoding in the Context of Memristor-Based Analog Computation for Automatic Speech Recognition

arXiv:2606.13379v1 Announce Type: new Abstract: Memristors provide a new chance for resource-efficient computation of neural models for natural language processing by enabling analog execution of vector-matrix-multiplication. Yet, computations on these devices are currently subject to larger distortion, both in weight programming and execution. In this work, we identify large output values of transformed positional encodings to cause major degradation within analog-to-digital conversion (ADC) as part of memristor-based computation. By adjusting the proportion of weight and precision bits of the ADC of specific memristor layers, we reduce the degradation of the execution by ~50% relative, while keeping the estimated energy consumption stable. Additionally, we investigate scenarios where the ADC cannot be modified. In that case the degradation can be reduced by ~30% relative after removing encoding-related linear transformations.

14.
arXiv (CS.CL) 2026-06-16

Compositional Reasoning Depth Predicts Clinical AI Failure: Empirical Evidence Consistent with Transformer Compositionality Limits in Electronic Health Record Question Answering

作者:

Aggregate accuracy benchmarks conceal a systematic structure in how large language models fail at electronic health record (EHR) question answering: questions requiring more inferential steps produce disproportionately more errors. Motivated by theoretical results on transformer compositionality limits, we introduce a pre-specified hop-count taxonomy – the number of distinct reasoning steps required to answer a clinical question from an EHR – as a principled predictor of model failure. We annotate 313 clinician-generated MedAlign EHR question-answer pairs across four hop levels and evaluate 301 questions in a within-model ablation (claude-sonnet-4-6, zero-shot vs. extended thinking) and cross-architecture replications (gpt-4o and gpt-5.4-2026-03-05, zero-shot). All three models, spanning two providers and two OpenAI generations (GPT-4 and GPT-5), show monotone accuracy decline with hop count: Claude Sonnet zero-shot falls from 30.6% (hop=1) to 17.6% (hop=4) (Cochran-Armitage z=-2.30, p=0.011; OR per hop 0.72, 95% CI [0.56,0.92], p=0.008); GPT-4o replicates this (37.8% to 14.7%; OR 0.58 [0.45,0.75], p

15.
arXiv (CS.LG) 2026-06-16

Conditional Score-Based Modeling of Effective Langevin Dynamics

arXiv:2604.23952v2 Announce Type: replace-cross Abstract: Stochastic reduced-order models are widely used to represent the effective dynamics of complex systems, but estimating their drift and diffusion coefficients from data remains challenging. Standard approaches often rely on short-time trajectory increments, state-space partitioning, or repeated simulation of candidate models, which become unreliable or computationally expensive for high-dimensional systems, coarse temporal sampling, or unevenly sampled data. We introduce a data-driven calibration method based on a novel relationship between the coefficients of a stochastic reduced model and the conditional score of the finite-time transition density, defined as the gradient of the logarithm of the transition density with respect to the initial state. The resulting identity expresses derivatives of lagged correlation functions as stationary expectations over observed lagged pairs involving this conditional score and the unknown model coefficients. This formulation allows the drift and diffusion structure to be constrained directly from finite-lag statistics, without differentiating trajectories, partitioning state space, or repeatedly integrating candidate reduced models during calibration, yielding a least-squares fitting problem over stationary lagged pairs. We validate the approach on three systems of increasing complexity: an analytically tractable Cox–Ingersoll–Ross diffusion, a two-dimensional nonequilibrium diffusion with affine multiplicative noise, and a periodic soft-spin stochastic Landau–Lifshitz chain. Across these tests, the inferred models preserve the invariant statistics while reproducing finite-lag dynamical correlations. The framework provides a scalable route for learning stochastic reduced-order models from data that reproduce prescribed statistical and dynamical properties.

16.
arXiv (CS.CL) 2026-06-24

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge. We study archive-grounded reasoning: locating sparse evidence across a large, messy collection of workplace files, reconciling inconsistent terminology, units, and time conventions, and computing an answer. Existing benchmarks address only parts of this setting and none jointly stresses archive-groundedness, agentic exploration, and cross-domain coverage. We introduce Agora, a benchmark pairing 362 questions with eight domain collections of 9,664 authentic documents and 372M tokens, far exceeding any model's context window, so agents must explore deliberately rather than scan exhaustively. Agora is built by an agentic pipeline combining cross-document task synthesis, leakage-preventing obfuscation, and difficulty filtering. Evaluating eight models, we find the task far from solved: even the strongest reaches only 59.4% accuracy, with notable variation across domains.

17.
arXiv (CS.CL) 2026-06-19

Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs

Automatic Speech Recognition (ASR) has become a key technology for human–AI interaction. However, code-switching ASR (CS-ASR) remains particularly challenging due to the severe scarcity of multilingual CS speech resources across diverse language pairs. Existing approaches primarily improve CS-ASR performance through synthetic CS speech generation or pair-specific fine-tuning on limited bilingual datasets. Nevertheless, these approaches face an inherent scalability limitation, as support for CS must be developed separately for language pairs whose number grows combinatorially with the number of supported languages. In this work, we investigate whether CS capabilities learned from a limited set of seen language pairs can generalize to unseen language pairs through model merging and domain generalization methods. Our experiments show that merged bilingual CS-ASR models modestly generalize to unseen language pairs, suggesting limited transfer of bilingual CS capabilities across language pairs.

18.
arXiv (CS.CV) 2026-06-16

Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning

Content-Preserving Style transfer, given content and style references, remains challenging for Diffusion Transformers (DiTs) due to entangled content and style features. With a reverse triplet synthesis pipeline to build a million-scale training set and a dual-branch Style-Content DiT (SC-DiT) that decouples style and content via separate ROPE embeddings and causal masking, we observe that such a one-stage training paradigm on mixed style categories causes semantic styles to dominate, hindering texture style learning, and harming content preservation. To address these issues, we propose Style-CCL, a Multi-Stage Curriculum Continual Learning framework that trains SC-DiT from semantic (easy) to texture (hard) styles, and from clean to synthetic data, with Random Memory Rehearsal across stages to avoid catastrophic forgetting. Extensive experiments demonstrate that our Style-CCL achieves state-of-the-art performance in three core metrics: style similarity, content consistency, and aesthetic quality.

19.
arXiv (CS.LG) 2026-06-18

Acceleration of an algebraic multigrid pressure solver using graph neural networks

arXiv:2606.19251v1 Announce Type: cross Abstract: Solving the pressure-Poisson equation remains the primary computational bottleneck in incompressible unstructured flow solvers primarily due to the inherent sensitivity of traditional linear solvers to mesh irregularities. This work introduces a data-driven algebraic multigrid (AMG) smoother that uses a modified graph convolutional isomorphism network (GCIN). The graph neural network predicts optimal polynomial coefficients to construct a sparse pseudo-inverse operator across diverse grid topologies. The coefficients are optimized to reduce the residual after each V-cycle iteration. By directly capturing the algebraic structure of the system from the sparse coefficient matrix, the proposed method maintains the solver's linearity while adapting to local anisotropies in unstructured grids. Our framework demonstrates significant performance gains by reducing the number of V-cycles required for a given tolerance and delivering wall-clock speedups from 4% to 37% across diverse benchmarks. Notably, the model exhibits robust generalization by maintaining efficiency on meshes up to 128 times larger than those seen in training, and by accelerating the solver's convergence on unseen industry-relevant problems such as the AirfRANS dataset.

20.
arXiv (CS.AI) 2026-06-19

Reward as An Agent for Embodied World Models

arXiv:2606.19990v1 Announce Type: new Abstract: While RL has become a promising tool for refining world models, existing methods largely rely on conservative rollouts near the training distribution, limiting exploration, behavioral diversity, and richer dynamic discovery. In this work, we challenge this conservative paradigm. We argue that the core limitation is not exploration itself, but the lack of reliable verification strategies to support broader exploration. Without reliable verification, expanded exploration becomes highly susceptible to reward hacking, where policies exploit imperfect rewards without achieving genuine improvement. To evaluate this motivation, we instantiate our method in embodied world models, where physical plausibility, and task completion provide a rigorous testbed for scalable RL under complex dynamics. On the verification side, we introduce Reward as an Agent, an agentic reward framework that actively evaluates generated behaviors to provide robust reward signals and mitigate reward hacking under distribution shifts. On the exploration side, we introduce Dynamic-Aware Rollout Diversification through DynDiff-GRPO, which explicitly expands action-space exploration to diversify trajectories, broaden state-action coverage, and encourage richer embodied behaviors beyond conservative rollout regimes. By unifying Reward as an Agent with DynDiff-GRPO, we enable RL on a more reliable reward foundation with substantially diversified sampling, effectively mitigating reward hacking while yielding significant accuracy gains across multiple open-source world models, thereby demonstrating that broader exploration can scale successfully when grounded in robust verification.

21.
arXiv (CS.CV) 2026-06-24

SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks

Sign language models are typically trained on datasets captured under constrained conditions, with limited viewpoint, background, and signer-identity diversity, leading to poor robustness under real-world distribution shifts. We introduce SignNet-1M, a large-scale augmented dataset spanning ASL, CSL, and German Sign Language (DGS). SignNet-1M synthesizes realistic variations along three axes: (i) novel-view rendering (rotation and zoom) via 3D Gaussian Splatting (3DGS), (ii) scene/identity editing via diffusion models for background replacement and signer substitution while preserving sign motion and linguistic content, and (iii) post-rendering augmentations that emulate capture and compression artifacts (e.g., pose/temporal perturbations and video-level corruptions) to better match in-the-wild recordings. Beyond data release, we provide a unified benchmark suite across downstream tasks (e.g., translation and recognition) and ablations that isolate each augmentation component. Experiments across backbones show that training with SignNet-1M consistently improves generalization under cross-view, cross-background, cross-identity, and post-rendering shifts, while maintaining strong in-distribution performance. The dataset, full augmentation pipeline, and benchmark are available at https://signnet.chatsign.ai/.

22.
arXiv (math.PR) 2026-06-18

On the Singular Control of a Diffusion and its Running Infimum or Supremum

arXiv:2501.17577v2 Announce Type: replace-cross Abstract: We study a class of singular stochastic control problems for a one-dimensional diffusion $X$ in which the performance criterion to be optimised depends explicitly on the running infimum $I$ (or supremum $S$) of the controlled process. We introduce two novel integral operators that are consistent with the Hamilton-Jacobi-Bellman equation for the resulting two-dimensional singular control problems. The first operator involves integrals where the integrator is the control process of the two-dimensional process $(X,I)$ or $(X,S)$; the second operator concerns integrals where the integrator is the running infimum or supremum process itself. Using these definitions, we prove a general verification theorem for problems involving two-dimensional state-dependent running costs, costs of controlling the process, costs of increasing the running infimum (or supremum) and exit times. Finally, we apply our results to explicitly solve an optimal dividend problem in which the manager's time-preferences depend on the company's historical worst performance.

23.
arXiv (CS.AI) 2026-06-17

SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs

arXiv:2606.17952v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) architectures enable scaling LLM parameters under a fixed inference budget by activating only a small subset of experts via top-$k$ routing. While this preserves causality and suits autoregressive language models, the discrete top-$k$ operator is not differentiable, forcing a fixed number of active experts per input and resulting in inefficient use of computation. We propose SoftMoE, which replaces discrete routing with a truncated soft top-$k$ LapSum relaxation, allowing gradient-based optimization of expert routing. We further parameterize the mean number of active experts per layer and impose a global budget constraint, enabling the model to learn how to allocate expert capacity across layers. SoftMoE remains fully compatible with autoregressive modeling and achieves performance comparable to or better than sparse MoE on language modeling and downstream tasks, while activating significantly fewer experts. Notably, the learned allocation is highly non-uniform, with later layers activating more experts. The source code is publicly available$^\dagger$.

24.
arXiv (CS.LG) 2026-06-19

Convex training of Lipschitz-regularized shallow neural networks

arXiv:2606.19652v1 Announce Type: new Abstract: In this work, we introduce a training procedure for shallow neural networks that promotes robustness against adversarial attacks. We solve a non-convex Lipschitz-regularized training program by introducing a convex restriction that can be efficiently solved to global optimality. Our approach can be employed as a post-processing step by taking a pre-trained network as an initial solution to then solving the convex program whose optimal network is guaranteed to be no worse than the initial one. We illustrate the improvements of our training procedure with experiments using real world datasets for regression tasks under an adversarial setting. We show numerically that solving our proposed convex program yields networks with lower objective values on the Lipschitz-regularized program compared to existing methods. Additionally, we show that on certain datasets, networks obtained using our convex training program are both more accurate and robust with respect to adversarial attacks.

25.
arXiv (CS.LG) 2026-06-11

IAPO: Input Attribution-Aware Policy Optimization for Tool Use in Small Multimodal Agents

arXiv:2606.11652v1 Announce Type: new Abstract: This paper investigates reinforcement learning (RL) methods for improving tool-calling capabilities in multimodal small language model (SLM) agents. While existing works have explored various reward designs to improve agentic tool-calling ability, these approaches face inherent limitations for SLM training, especially under multimodal scenarios. First, many existing methods evaluate tool use correctness through exact matching against certain ground-truth or predefined formats. However, this assumption is often unsuitable for multimodal tasks, where multiple tool use paths may be valid and annotated tool trajectories are typically unavailable. Second, such sparse and brittle binary rewards provide little guidance on how to improve the underlying decision process, making them particularly difficult for multimodal SLM to learn from. To address these issues, we propose Input Attribution-Aware Policy Optimization (IAPO), an RL algorithm for improving tool use in multimodal SLM by aligning the model's attribution across input components with that of a stronger teacher. Experiments on Qwen2.5-VL-3B show that the proposed method improves visual question answering accuracy by an average of 3% across six test sets compared with existing visual tool use work, by helping the model attend to the most relevant input evidence.