Explore the Frontier of Global Academia

01.

medRxiv (Medicine) 2026-06-11 DOI: HASH:db82bb6e2205e02a4bd7e244ccabcfc2

Neighborhood socioeconomic status associated with post-stroke cognitive impairment: a retrospective cohort study

Authors:

Siegel↗Corlin↗Miller↗Cote↗Leung↗L. Y↗

Background: Late complications after stroke (LCAS), including cognitive symptoms, impact quality of life and recovery. It is not known if neighborhood-level measures of socioeconomic status (SES) influence LCAS. This study assessed associations between SES measures, including neighborhood income inequality (Gini) and area deprivation index (ADI), and cognitive symptoms after acute ischemic stroke (AIS) in a hospital leveraging active surveillance of LCAS. Methods: This retrospective cohort study included 512 patients hospitalized with AIS at Tufts Medical Center with subsequent follow-up (between zero and three months or between three and twelve months) in the Stroke Clinic from 1/1/2018 - 12/31/2022. Using ZIP code data, patients were characterized as low Gini (low inequality) and high ADI (high deprivation) (Gini = 5) by state medians. These variables were combined, indicating patients who were living in both a low Gini and high ADI neighborhood to evaluate the effects of living in a homogeneously deprived area. There were 206 and 281 patients in the low Gini and high ADI groups respectively. 140 patients lived in a low Gini and high ADI neighborhood. The multivariable logistic analysis assessed the likelihood of cognitive symptoms, adjusting for age, race, ethnicity, sex, NIH Stroke Scale (NIHSS), thrombolysis, active LCAS surveillance, poverty, and ADI-Gini combination. Results: There were no associations between high ADI (OR: 1.03, 95% CI: 0.67 ? 1.57) or low Gini (OR: 1.74, 95% CI: 0.98 ? 3.07) alone and cognitive symptoms after AIS. However, the combined variable demonstrated increased likelihood of cognitive symptoms in the high ADI-low Gini group (OR: 1.82, 95% CI: 1.08 ? 3.06). Conclusions: This study suggests that individuals living in homogeneously deprived neighborhoods report higher likelihood of cognitive symptoms after AIS. Further studies with increased power are needed to investigate the underlying causes of these disparities and to develop interventions to reduce these complications.

Read & Discuss → View Source →

02.

arXiv (math.PR) 2026-06-24 DOI: arXiv:2606.24271

Deep numerical schemes for systems of Ergodic BSDEs with applications to regime-switching forward utilities

Authors:

Guillaume Broux-Quemerais↗Sarah Kaakai↗Anis Matoussi↗Wissal Sabbagh↗

arXiv:2606.24271v1 Announce Type: cross Abstract: In this paper, we introduce two neural-network-based numerical schemes for solving systems of coupled ergodic Backward Stochastic Differential Equations (eBSDEs), motivated by the approximation of optimal strategies within the framework of forward utilities in a regime-switching stochastic factor model. Our approach builds on the representation of such models through systems of eBSDEs introduced in [HLT20]. We first establish a link between the solution of the system of ergodic BSDEs and that of an associated multidimensional BSDE with random terminal time, given by the hitting time of the positive recurrent stochastic factor. Building on this representation, we introduce a locally additive deep learning scheme obtained by minimizing aggregated local error terms. We then present a new Deep Galerkin Method (DGM) inspired algorithm that minimizes the residual of the associated ergodic PDE system, relying on a representation of the ergodic cost. Finally, we apply this framework to regime-switching forward utilities in a stochastic factor model. We first derive a general consistency SPDE that characterizes regime-switching forward utilities and retrieve their representation with systems of ergodic BSDEs in the homothetic case. Numerical experiments demonstrate the performance of the proposed methods, with a particular focus on the impact on forward preferences of taking into account regime switches.

Read & Discuss → View Source →

03.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2510.02149

Reinforcement Learning with Action-Triggered Observations

Authors:

Alexander Ryabchenko↗Wenlong Mou↗

arXiv:2510.02149v2 Announce Type: replace Abstract: We introduce Action-Triggered Sporadically Traceable Markov Decision Processes (ATST-MDPs), a reinforcement learning framework for partial observability in which full state observations occur stochastically at each step, with probability determined by the chosen action. We derive Bellman equations tailored to this setting and establish the existence of an optimal policy. Exploiting the fact that sporadic observations reveal the full state, we provide an equivalent formulation in which agents commit to action-sequences between consecutive observations. Under the linear MDP assumption, we show that the value function over such action-sequences admits a linear representation in a finite-dimensional feature map, enabling standard regression-based methods. As an application, we derive ATST-LSVI-UCB, an optimistic algorithm achieving regret $\widetilde{O}(\sqrt{Kd^3(1-\gamma)^{-3}})$ for episodic learning with geometrically distributed horizons, where $K$ is the number of episodes, $d$ the feature dimension, and $\gamma$ the discount factor (episode continuation probability), matching the known rate for linear MDPs with full observability.

Read & Discuss → View Source →

04.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.19025

FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs

Authors:

Lorenzo Sani↗Zeyu Cao↗Meghdad Kurmanji↗Alex Iacob↗Andrej Jovanovic↗Yan Gao↗Wanru Zhao↗Nicholas D. Lane↗

arXiv:2606.19025v1 Announce Type: cross Abstract: Pre-training Large Language Models (LLMs) typically demands large-scale infrastructure with tightly coupled hardware accelerators. While increasing model and dataset scale remains the dominant driver of performance, Mixture-of-Experts (MoEs) architectures have recently achieved state-of-the-art results by decoupling parameter count from computational cost. This efficiency enables training massive models on constrained compute budgets, yet it typically requires the high-speed interconnects of a single datacenter. To overcome these physical limits, recent approaches such as DiLoCo and Photon use low-communication data-parallel methods to enable scaling across geographically distributed, weakly connected data centers. However, these methods suffer from a fundamental inefficiency: they require full model replicas at every site, which imposes prohibitive memory constraints and communication overheads. In this work, we introduce FoMoE, a system that breaks the full-replica paradigm by partitioning expert layers across workers. We demonstrate that FoMoE: (I) reduces communication costs by up to 1.42x over efficient baselines and 45.44x over DDP via partial expert replication in the studied regimes; (II) achieves empirical throughput speedups of up to 1.4x through a novel skip-token mechanism; and (III) shows stable routing in the trained proxy regimes and projects the communication/memory benefits to 100B-scale configurations through system modelling.

Read & Discuss → View Source →

05.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2606.24231

FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning

Authors:

Xirui Li↗Zhe Liu↗Xiaoqing Ye↗Wenhua Han↗Yifeng Pan↗Junyu Han↗Hengshuang Zhao↗

arXiv:2606.24231v1 Announce Type: new Abstract: Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action vocabulary, while anchor-based methods generate proposals dynamically yet suffer from sparse supervision constrained to a single ground-truth trajectory. In this work, we propose FlowR2A, which resolves this tension by reframing simulation-based rewards from discriminative targets into generative conditions. By learning the reward-conditioned action distribution from dense trajectory-reward pairs with a flow-matching decoder, FlowR2A unifies the dense supervision of scoring-based methods with the proposal generation of anchor-based methods in a single generative model, forcing the model to internalize the correlation between an action and its outcomes in safety, progress, comfort, and rule compliance. To balance hard safety constraints against soft progress objectives, we introduce fine-grained per-timestep reward conditioning and reward noise augmentation. The generative formulation naturally supports controllable test-time sampling via reward guidance and anchored sampling, producing high-quality proposals. FlowR2A achieves state-of-the-art results on the NAVSIM v1 and v2 benchmarks, with multimodal proposals of substantially higher quality than prior methods.

Read & Discuss → View Source →

06.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2605.15980

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

Authors:

Xiaoxuan He↗Siming Fu↗Zeyue Xue↗Weijie Wang↗Ruizhe He↗Yuming Li↗Dacheng Yin↗Shuai Dong↗Haoyang Huang↗Hongfa Wang↗Nan Duan↗Bohan Zhuang↗…

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days per experiment. Existing efficiency methods reduce costs through sliding window subsampling training timesteps, but fundamentally compromise optimization, exhibiting severe instability and failing to reach full trajectory performance. We present Flash-GRPO, a single-step training framework that outperforms full trajectory training in alignment quality under low computational budgets while substantially improving training efficiency. Flash-GRPO addresses two critical challenges: iso-temporal grouping eliminates timestep-confounded variance by enforcing prompt-wise temporal consistency, decoupling policy performance from timestep difficulty; temporal gradient rectification neutralizes the time-dependent scaling factor that causes vastly inconsistent gradient magnitudes across timesteps. Experiments on 1.3B to 14B parameter models validate Flash-GRPO's effectiveness, demonstrating substantial training acceleration with consistent stability and state-of-the-art alignment quality.

Read & Discuss → View Source →

07.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.19092

Context-Aware Optimization of Follow-Up Intervals for Type 2 Diabetes Care Using Markov Decision Processes

Authors:

Parisa Lotfibagha↗Kristen Miller↗William J. Gallagher↗Elizabeth B. Selden↗Muge Capan↗

arXiv:2606.19092v1 Announce Type: cross Abstract: Chronic disease management relies on regular patient-provider interactions to follow-up on disease progression and control. For Type 2 Diabetes (T2D), current guidelines prescribe fixed time intervals between subsequent primary care visits for all patients, overlooking heterogeneity in clinical trajectories and patient characteristics. This study introduces a Contextual Markov Decision Process (CMDP) model to optimize subpopulation-specific follow-up interval decisions using Electronic Health Record (EHR) data from 22,154 T2D patients across 10 primary care clinics. Contexts are identified by: i) dimensionality reduction of variables representing the individual health trajectories utilizing Principal Component Analysis, and ii) assigning patients to contexts via principal components and additional patient-level features using clustering. Two distinct contexts emerged, representing a lower- and a higher-risk subpopulation. CMDP-derived policies recommend: (i) follow-up within 1 month if lab value at current visit is unmeasured; (ii) up to 3 months for elevated lab values or recent hospitalizations; and (iii) 6 to 12 months for sustained glycemic control, with shorter follow-up intervals for patients in high-risk context. The optimal policies achieved lower expected cumulative cost than benchmarks (e.g., in the higher-comorbidity context, the CMDP policy reduced cost by about 34.8%, and in the lower-comorbidity context by about 6.4%, relative to an American Diabetes Association-like fixed interval follow-up policy. These findings demonstrate how context-aware approaches can inform adaptive follow-up strategies, and have the potential to advance chronic care management in primary care by synthesizing machine learning and probabilistic decision models.

Read & Discuss → View Source →

08.

arXiv (math.PR) 2026-06-18 DOI: arXiv:2605.05420

A Unified Approach to Beta Moments, Combinatorial Identities, and Random Walks

Authors:

Puja Pandey↗Palaniappan Vellaisamy↗

arXiv:2605.05420v2 Announce Type: replace Abstract: The study of random walks has increasingly been popular across diverse disciplines such as statistics, mathematics, quantum physics, where they are used to model paths consisting of successive random steps in a mathematical space. A fundamental quantity of interest is the probability that a simple symmetric random walk returns to the origin after 2n steps. In this paper, we develop a unified probabilistic approach that connects the return probabilities in arbitrary dimensions with moment representations. Using this framework, we provide probabilistic proofs of several combinatorial identities involving beta and gamma functions, and derive new combinatorial identities in general dimensions.

Read & Discuss → View Source →

09.

bioRxiv (Bioinfo) 2026-06-22 DOI: HASH:26699b7854fdc6ba1b7307f28d8c44e6

Drug-Prot: A query system for statistical inference of drug effects and interactions in dynamic proteomic networks

Authors:

Ulmer↗Sun↗Qian↗Aebersold↗Guo↗Buehlmann↗

Understanding drug effects and drug-drug interactions is essential for developing combination therapies. We present Drug-Prot, a computational framework that leverages large-scale perturbation proteomics to quantify causal drug effects, drug-drug interactions, and dynamic protein relationships. Using data from 63 single drugs and 59 drug combinations applied to 18 breast cancer cell lines at 6, 24, and 48 hours, Drug-Prot estimates drug effects on protein expression and reconstructs directed temporal protein dependency networks. The publicly available software enables targeted analyses of user-defined protein sets, substantially reducing the multiple-testing burden. Through an interactive web application, users obtain corrected p-values for single-drug and combination effects, directed temporal dependency networks, and downloadable results without requiring access to the underlying proteomic dataset. As a use case, we apply invariance-regularized Random Forests to triple-negative breast cancer cell lines to identify proteins associated with drug response. Querying these proteins in Drug-Prot reveals drug-specific and interaction effects at the protein-network level, illustrating how the framework links candidate causal protein features to actionable drug combinations.

Read & Discuss → View Source →

10.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2509.11548

How Auxiliary Reasoning Unleashes GUI Grounding in VLMs

Authors:

Weiming Li↗Yan Shao↗Jing Yang↗Yujing Lu↗Ling Zhong↗Yuhan Wang↗Min Yu↗Tongxiao Ruan↗Manni Duan↗

Graphical user interface (GUI) grounding is a fundamental task for building GUI agents. However, general vision-language models (VLMs) struggle with this task due to a lack of specific optimization. We identify a key gap in this paper: while VLMs exhibit significant latent grounding potential, as demonstrated by their performance measured by Pointing Game, they underperform when tasked with outputting explicit coordinates. To address this discrepancy and bypass the high data and annotation costs of current fine-tuning approaches, we propose three zero-shot auxiliary reasoning methods. By providing explicit spatial cues such as axes, grids and labeled intersections as part of the input image, these methods enable VLMs to better articulate their implicit spatial understanding capabilities. We evaluate these methods on four GUI grounding benchmarks across seven open-source and proprietary VLMs. Experimental results show substantial gains from auxiliary reasoning. Mark-Grid Scaffold boosts Gemini-3.1-Pro from 11.72\% under direct inference to 95.20\% on ScreenSpot-v2, achieves state-of-the-art performance on ScreenSpot, and approaches the strongest fine-tuned methods on ScreenSpot-v2 and UI-I2E-Bench. Our code is available at https://github.com/liweim/AuxiliaryReasoning.

Read & Discuss → View Source →

11.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2506.13196

KEPLA: A Knowledge-Enhanced Deep Learning Framework for Accurate Protein-Ligand Binding Affinity Prediction

Authors:

Han Liu↗Keyan Ding↗Peilin Chen↗Yinwei Wei↗Liqiang Nie↗Dapeng Wu↗Shiqi Wang↗

arXiv:2506.13196v5 Announce Type: replace Abstract: Accurate prediction of protein-ligand binding affinity is critical for drug discovery. While recent deep learning approaches have demonstrated promising results, they often rely solely on structural features of proteins and ligands, overlooking their valuable biochemical knowledge associated with binding affinity. To address this limitation, we propose KEPLA, a novel deep learning framework that explicitly integrates prior knowledge from Gene Ontology and ligand properties to enhance prediction performance. KEPLA takes protein sequences and ligand molecular graphs as input and optimizes two complementary objectives: (1) aligning global representations with knowledge graph relations to capture domain-specific biochemical insights, and (2) leveraging cross attention between local representations to construct fine-grained joint embeddings for prediction. Experiments on two benchmark datasets across both in-domain and cross-domain scenarios demonstrate that KEPLA consistently outperforms state-of-the-art baselines. Furthermore, interpretability analyses based on knowledge graph relations and cross attention maps provide valuable insights into the underlying predictive mechanisms.

Read & Discuss → View Source →

12.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2505.22829

Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies

Authors:

Chenruo Liu↗Kenan Tang↗Yao Qin↗Qi Lei↗

arXiv:2505.22829v2 Announce Type: replace-cross Abstract: This paper bridges distribution shift and AI safety through a comprehensive analysis of their conceptual and methodological synergies. While prior discussions often focus on narrow cases or informal analogies, we establish two types connections between specific causes of distribution shift and fine-grained AI safety issues: (1) methods addressing a specific shift type can help achieve corresponding safety goals, or (2) certain shifts and safety issues can be formally reduced to each other, enabling mutual adaptation of their methods. Our findings provide a unified perspective that encourages deeper integration between distribution shift and AI safety research.

Read & Discuss → View Source →

13.

arXiv (math.PR) 2026-06-11 DOI: arXiv:2512.24807

Heat kernel estimates for Markov processes with blowing-up jump kernels

Authors:

Soobin Cho↗Panki Kim↗Renming Song↗Zoran Vondra\v{c}ek↗

arXiv:2512.24807v2 Announce Type: replace Abstract: In this paper, we establish sharp two-sided heat kernel estimates for a large class of purely discontinuous symmetric Markov processes on closed subsets $F$ of $\mathbb{R}^d$, whose jump kernels blow up on a Borel subset $\Sigma$ of $F$. We assume that $F\setminus \Sigma$ is a $\kappa$-fat set and is dense in $F$. To the best of our knowledge, this is the first work establishing sharp heat kernel estimates for jump processes whose jump kernels blow up on part of the state space. The jump kernels under consideration take the form $J(x,y)=|x-y|^{-d-\alpha}{\mathcal B}(x,y)$, where $\alpha\in (0,2)$ and the function ${\mathcal B}(x,y)$ blows up at a subset $\Sigma$ of $F$. A fundamental obstacle is that the tails of the jump measures are not uniformly bounded, and hence standard techniques in heat kernel analysis do not provide a priori off-diagonal estimates. To overcome this difficulty, we develop a new approach based on weighted integral estimates for the heat kernel that are sensitive to both the blow-up behavior of the jump kernel and the geometry of $F\setminus \Sigma$. Examples of processes falling within our general framework include traces of isotropic $\alpha$-stable processes in $C^{1,\rm Dini}$ sets, processes in Lipschitz sets arising in connection with the nonlocal Neumann problem, and a large class of resurrected self-similar processes in the closed upper half-space.

Read & Discuss → View Source →

14.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19827

When, Where, and How: Adaptive Binning for Tabular Self-Supervised Learning

Authors:

Daehwan Kim↗Haejun Chung↗Ikbeom Jang↗

arXiv:2606.19827v1 Announce Type: cross Abstract: Medical tabular data are ubiquitous in clinical research, but deep learning for tables remains underexplored because reliable labels often require costly expert adjudication, even though structured clinical variables are routinely available in tabular form. Self-supervised learning can leverage these unlabeled tables, and recent binning-based pretexts offer a promising inductive bias, but existing objectives fix a single global quantile discretization and apply feature-agnostic supervision. We propose Adaptive Binning, a training-adaptive discretization pretext for tabular SSL that couples discretization to learning through a feature-wise coarse-to-fine curriculum. Motivated by the spectral bias of neural networks and the principles of curriculum learning, our method progressively refines discretization per feature upon plateau detection and selects representation-aware splits to jointly improve value-space concentration and representation-space coherence. A heterogeneity-aware objective unifies categorical reconstruction with ordinal supervision for numerical features, and experiments on public medical tabular datasets under unified evaluation protocols show consistent gains for linear probing and fine-tuning without dataset-specific discretization tuning. We further introduce a medical tabular SSL benchmark with standardized protocols to support reproducible progress in this underexplored domain. Our code is available at https://github.com/labhai/Adaptive-Binning.

Read & Discuss → View Source →

15.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16652

Optimising Temporary Accommodation Placement Across London with AI-Powered SaaS in E-Governance Systems

Authors:

Hankun He↗Jordan Richards↗Gopalakrishnan Netuveli↗Kumar Aniket↗Ramya Pachatcharam↗Binta Ade-olusile↗Nathan Nagaiah↗Matthew I Bellgard↗

arXiv:2606.16652v1 Announce Type: cross Abstract: Temporary accommodation has become a major fiscal and administrative pressure for English local authorities, particularly in London, where demand and costs have risen sharply. This paper documents the creation and use of DOMUS, a cloud-based, AI-enabled decision-support system built from scratch at the University of East London and customised for the needs of London Borough of Newham to support statutory Temporary accommodation placement. DOMUS integrates household case records, policy-constrained affordability and suitability rules, and live private-rental listings within a single governance-aligned workflow. The system combines transparent, rule-based filtering with large language model-assisted search to standardise the application of bedroom need, affordability thresholds, geographic preferences, and accessibility requirements, while preserving officer discretion and audibility. Household and property attributes are encoded into policy-consistent representations prior to AI-assisted ranking and explanation. A pilot deployment in Newham's secure environment evaluated operational performance relative to manual workflows. Results indicate substantial reductions in search time, improved adherence to key placement constraints, and high staff satisfaction, while maintaining statutory compliance and role-based accountability. Beyond TA, the paper frames DOMUS as replicable digital public infrastructure: a modular, cloud-native Software-as-a-Service architecture that can be deployed across other UK boroughs and adapted to other public administration tasks characterised by scarcity, rule-bound eligibility, and high stakes. The findings demonstrate the feasibility of scalable, ethically governed AI deployment in local government and contribute to debates on AI-enabled public value creation in e-governance.

Read & Discuss → View Source →

16.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13211

Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints

Authors:

Omar Alshahrani↗Muzammil Behzad↗

arXiv:2606.13211v1 Announce Type: new Abstract: AI systems are being deployed across medical imaging faster than their failure modes are understood. At this point in time, the failure of greatest clinical concern is hallucination: clinically plausible but factually incorrect outputs, including fabricated anatomical structures, missed findings, incorrect laterality, and invented measurements in generated reports, with direct consequences, for example, for biopsy decisions, staging, and treatment planning. This structured narrative synthesizes peer-reviewed studies, benchmark datasets, and FDA regulatory guidance across five imaging modalities to produce a cross-modality analysis of hallucination taxonomy, etiology, detection, and mitigation. Specifically, we address three questions in this study: (1) how can existing taxonomies be unified across modalities?, (2) how do medical-specialized foundation models hallucinate less than general-purpose ones?, and (3) which mitigation strategies are effective and compatible with FDA lifecycle oversight? We note that three taxonomic frameworks together cover the imaging pipeline in a way no single framework does alone. We also highlight that general-purpose foundation models outperform medical-specialized models on hallucination-specific benchmarks, indicating that narrow domain fine-tuning can introduce overfitting-induced confabulation. At the same time, the oversight of radiologists remains essential; for instance, a very high percentage of of AI-generated flags required expert correction before clinical use. Physics-informed architectural constraints, Chain-of-Thought prompting, and human-in-the-loop safeguards each address different failure modes and is effective when combined. All findings are mapped to the FDA's Total Product Lifecycle and Predetermined Change Control Plan frameworks, which treat hallucination management as a lifecycle obligation rather than a pre-deployment checklist.

Read & Discuss → View Source →

17.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.05551

Conformal Risk-Averse Decision Making with Action Conditional Guarantee

Authors:

Zihan Zhu↗Shayan Kiyani↗George Pappas↗Hamed Hassani↗

arXiv:2606.05551v2 Announce Type: replace-cross Abstract: Reliable decision making pipelines powered by machine learning models require uncertainty quantification (UQ) methods that come with explicit safety guarantees. Conformal prediction provides such UQ by wrapping ML predictions into prediction sets, and recent work by Kiyani et al. (2025b) established that these sets can be translated into optimal risk-averse decision policies – yet only inheriting marginal safety guarantees. We generalize and strengthen their results by (i) introducing action-conditional conformal prediction, which yields safety guarantees conditioned explicitly on each action taken by the decision maker, (ii) showing that action-conditional prediction sets serve as a proxy for the feasible decision space for risk-averse decision makers aiming to optimize action-conditional value-at-risk, and (iii) proposing a principled finite-sample algorithm based on pinball-loss minimization, connecting the framework of Gibbs et al. (2025) to action-conditional guarantees. Experiments on two real-world datasets confirm that our approach significantly improves action-conditional performance over conformal baselines.

Read & Discuss → View Source →

18.

arXiv (CS.LG) 2026-06-24 DOI: arXiv:2602.02899

Decentralized SGD with Controlled Disagreement Finds Flatter Minima

Authors:

Zesen Wang↗Mikael Johansson↗

arXiv:2602.02899v2 Announce Type: replace Abstract: Decentralized training is often regarded as inferior to centralized training because the consensus errors between workers are thought to undermine convergence and generalization. This work challenges this view by introducing decentralized SGD with Adaptive Consensus (DSGD-AC), which uses a time-dependent scaling mechanism to maintain consensus errors throughout the training. We show that adaptive consensus changes the stationary variance of disagreement modes by balancing two effects: it preserves consensus-error magnitude through weaker graph damping while still allowing curvature-dependent damping to shape the disagreement directions. This balance can produce a stronger Hessian-weighted loss-envelope penalty around the deployed model, even when normalized Hessian alignment is weaker than in standard DSGD. Empirical results on image classification show that DSGD-AC reaches flatter solutions and higher test accuracy than standard DSGD and even centralized SGD. Together, these results support consensus errors as a useful implicit regularizer and open a new perspective on the design of decentralized learning algorithms.

Read & Discuss → View Source →

19.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20400

The Significance of Style Diversity in Annotation-Free Synthetic Data Generation

Authors:

Zahra Abbasiantaeb↗Zeno Belligoli↗Omar Essam↗Mohammad Aliannejadi↗

arXiv:2606.20400v1 Announce Type: new Abstract: Generating high-utility synthetic data for intent classification typically requires human-annotated seed data, which is often unavailable in fast-paced industrial settings. In this paper, we propose a framework for synthetic dialogue generation that works entirely without human-annotated data, relying solely on intent definitions. Our proposed dialogue generation framework utilizes two different types of topic and style attributes to improve data diversity. Also, we propose two novel post-hoc stylization models called Univ and Exam to transform synthetic LLM-generated utterances into more varied, human-like linguistic styles. To enhance data quality, we utilize an LLM-as-a-judge filtering process. Experimental results on both industrial and public datasets demonstrate that the proposed approach achieves up to 93.3% of the performance obtained using human-annotated training data. Crucially, the findings reveal that style diversity is more critical than topic diversity for synthetic data utility, as it prevents models from learning spurious stylistic correlations. Furthermore, the study shows that incorporating style attributes during the generation process is more effective than post-hoc style adaptation.

Read & Discuss → View Source →

20.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2605.09163

FORTIS: Benchmarking Over-Privilege in Agent Skills

Authors:

Shawn Li↗Chenxiao Yu↗Han Wang↗Wei Yang↗Ryan Rossi↗Franck Dernoncourt↗Xiyang Hu↗Philip Yu↗Chaowei Xiao↗Huan Zhang↗Yue Zhao↗

arXiv:2605.09163v3 Announce Type: replace Abstract: Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution. This layer is widely treated as an organizational abstraction, but we argue it is also a privilege boundary that current models routinely exceed. We present FORTIS, a benchmark that evaluates over-privilege in agent skills across two stages: whether a model selects the minimally sufficient skill from a large overlapping library, and whether it executes that skill without expanding into broader tools or actions than the skill permits. Across ten frontier models and three domains, we find that over-privileged behavior is the norm rather than the exception. Models consistently reach for higher-privilege skills and tools than the task requires, failing at both stages at rates that remain high even for the strongest available models. Failure is especially severe under the ordinary conditions of real user interaction: incomplete specification, convenience framing, and proximity to skill boundaries. None of these requires adversarial construction. The results indicate that the skill layer, far from containing agent behavior, is itself a primary source of privilege escalation in current systems.

Read & Discuss → View Source →

21.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13443

How Much Memory Do We Need? Adaptive Memory Gate for Neural Operators

Authors:

Jihyeon Hur↗Yongseok Kwon↗Min-Gi Jo↗Jeongwhan Choi↗Noseong Park↗

arXiv:2606.13443v1 Announce Type: new Abstract: Neural operators have emerged as a powerful data-driven approach for solving time-dependent PDEs. Among recent advances, memory-augmented neural operators explicitly incorporate past states and have achieved remarkable performance under low-resolution observation settings. However, existing approaches apply a fixed memory weight regardless of observation conditions, such as resolution or physical parameters, limiting their adaptability. Our preliminary experiments reveal that optimal memory weight varies with resolution and viscosity, implying that a fixed memory weight cannot simultaneously optimize performance across diverse settings. We propose AMGFNO, which dynamically modulates memory weight through a learnable gate. On the Kuramoto-Sivashinsky and Burgers' equations, AMGFNO achieves 55-79% nRMSE reduction over at low resolution, with the learned gate value automatically decreasing from $\bar{g} \approx 0.7$ to near-zero as resolution increases.

Read & Discuss → View Source →

22.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2509.26476

Regression Language Models for Code

Authors:

Yash Akhauri↗Xingyou Song↗Arissa Wongpanich↗Bryan Lewandowski↗Mohamed S. Abdelfattah↗

We study code-to-metric regression: predicting numeric outcomes of code executions, a challenging task due to the open-ended nature of programming languages. While prior methods have resorted to heavy and domain-specific feature engineering, we show that a single unified Regression Language Model (RLM) using a frozen LLM encoder can simultaneously predict directly from text, (i) the memory footprint of code across multiple high-level languages such as Python and C++, (ii) the latency of Triton GPU kernels, and (iii) the accuracy and speed of trained neural networks represented in ONNX. In particular, a relatively small 300M parameter RLM based on T5Gemma, obtains >0.9 Spearman-rank on competitive programming submissions from APPS, and a single unified model achieves >0.5 average Spearman-rank across 24 different programming languages from CodeNet. Furthermore, the RLM can obtain the highest average Kendall-Tau of 0.46 on five classic NAS design spaces previously dominated by graph neural networks, and simultaneously predict architecture latencies on numerous hardware platforms.

Read & Discuss → View Source →

23.

arXiv (CS.LG) 2026-06-24 DOI: arXiv:2606.24143

AsyncOPD: How Stale Can On-Policy Distillation Be?

Authors:

Wonjun Kang↗Kevin Galim↗Seunghyuk Oh↗Minjun Kang↗Sanghyun Park↗Donghoon Kim↗Minjae Lee↗Minseo Kim↗Rishabh Tiwari↗Yuchen Zeng↗Hyung Il Koo↗Kangwook Lee↗…

arXiv:2606.24143v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Like reinforcement learning (RL), however, OPD faces an on-policy systems bottleneck, as rollouts can dominate training time for reasoning workloads. Asynchronous training pipelines can alleviate this bottleneck by decoupling rollout generation from learner updates, but doing so introduces stale-policy data. While prior work has studied stale data in asynchronous RL, its effects in OPD remain underexplored. We present the first systematic study of staleness in asynchronous OPD, focusing on a practical setting where teacher feedback is implemented through local KL losses and full-vocabulary teacher logits are too expensive to store or transfer, necessitating finite teacher-score caches. We first show that KL direction changes the stale-data problem: teacher-weighted forward KL is more robust to stale rollouts, whereas student-weighted reverse KL is vulnerable. Second, for this vulnerable reverse-KL case, we study whether methods designed to stabilize asynchronous RL can mitigate OPD staleness. In our experiments, they do not improve over a simpler OPD-specific surrogate: recomputing the reverse-KL signal under the current student at learner time. Third, we analyze how finite teacher-score caches create a bias-variance tradeoff for sparse and sampled reverse-KL OPD estimators. This motivates multi-sample Monte Carlo (MC), which preserves MC correctability while reducing one-sample variance. Finally, we present and open-source AsyncOPD, a fully asynchronous OPD training pipeline built from these estimator choices. Experiments show that AsyncOPD improves training throughput by $1.6\times$ to $3.8\times$ over strict synchronous training while reaching comparable accuracy.

Read & Discuss → View Source →

24.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15753

RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thought

Authors:

Yaoting Huang↗Yifu Yuan↗Linqi Han↗Chengwen Li↗Shuoheng Zhang↗Xianze Yao↗Hongyao Tang↗Yan Zheng↗Jianye Hao↗

arXiv:2606.15753v1 Announce Type: new Abstract: Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments and maintain consistent visual grounding throughout multi-step reasoning. However, current vision-language models rely on text-only or coordinate-augmented chain-of-thought, where entity references remain implicit and ambiguous. This may cause the reasoning process to decouple from visual evidence, entity references to drift across steps, and a causal disconnection between the reasoning trajectory and the final answer, with these problems further amplified in multi-view scenarios due to cross-view appearance changes. To address these issues, we propose Pinned Chain-of-Thought (\pincot{}), a structured reasoning paradigm that pins every reasoning step to visual evidence. \pincot{} introduces the concept of \reasoninganchor{}, which binds each task-relevant entity to a structured visual anchor with entity name, unique identity, view index, and spatial grounding, enabling consistent entity tracking across reasoning steps and views. We build a fully automated data generation pipeline to construct \dataset{}, a high-quality \pincot{}-formatted reasoning dataset. We then train \method{} through three-stage post-training that progressively injects embodied knowledge, structured reasoning ability, and process-supervised alignment, with rewards that directly constrain both anchor localization and identity consistency during reasoning. On 14 benchmarks covering embodied spatial reasoning, multi-view reasoning, and pointing, \method{} with only 4B parameters consistently outperforms 7B level open-source embodied models, achieving a 12\% average improvement over the strongest 7B baseline, Mimo-Embodied. Further analysis shows that \pincot{} improves grounding accuracy and cross-step identity consistency, validating the effectiveness of process supervision.

Read & Discuss → View Source →

25.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2512.20014

Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive Prompting

Authors:

Sangoh Lee↗Sangwoo Mo↗Wook-Shin Han↗

arXiv:2512.20014v3 Announce Type: replace-cross Abstract: While Vision-Language-Action (VLA) models generalize well to generic instructions, they struggle with personalized commands such as "bring my cup," where the robot must act on one specific instance among visually similar objects. We study this setting of manipulating personal objects, in which a VLA must identify and control a user-specific object unseen during training using only a few reference images. To address this challenge, we propose Visual Attentive Prompting (VAP), a simple-yet-effective training-free perceptual adapter that equips frozen VLAs with top-down selective attention. VAP treats the reference images as a non-parametric visual memory, grounds the personal object in the scene through open-vocabulary detection and embedding-based matching, and then injects this grounding as a visual prompt by highlighting the object and rewriting the instruction. We construct two simulation benchmarks, Personalized-SIMPLER and Personalized-VLABench, and a real-world tabletop benchmark to evaluate personalized manipulation across multiple robots and tasks. Experiments show that VAP consistently outperforms generic policies and token-learning baselines in both success rate and correct-object manipulation, helping to bridge the gap between semantic understanding and instance-level control.

Read & Discuss → View Source →