Explore the Frontier of Global Academia

01.

medRxiv (Medicine) 2026-06-15 DOI: HASH:522b60704fa9d27125462265c169853b

Routine use of oral iron for people with heart failure and iron deficiency in primary care; retrospective cohort study

Authors:

Maharajan↗Jones↗Bankhead↗Erone↗Haynes↗Katumba↗Li↗Maynard↗Roy↗Shah↗Stanworth↗Smith↗…

Aims: Iron deficiency is common among people with heart failure and associated with morbidity and mortality. While intravenous iron improves clinical outcomes, oral iron continues to be prescribed in routine practice despite limited evidence of benefit. Methods: We completed a retrospective primary care cohort study (2016 to 2021) to investigate the proportion of people with an incident diagnosis of heart failure who had iron deficiency identified (defined as ferritin

Read & Discuss → View Source →

02.

arXiv (quant-ph) 2026-06-24 DOI: arXiv:2606.24643

The Quantum Split-Step Fourier Algorithm for Nonlinear Optical Waveguides

Authors:

Fabio Biancalana↗

arXiv:2606.24643v1 Announce Type: cross Abstract: We introduce the Quantum Split-Step Fourier (QSSF) algorithm for nonlinear optical waveguides, a numerical framework that combines split-step propagation of the nonlinear Schrödinger equation with a commutator-preserving Bogoliubov evolution of Gaussian quantum fluctuations. The method propagates the classical mean field together with the Bogoliubov matrices $U$ and $V$, from which reduced second moments, covariance matrices, symplectic eigenvalues, and entropic measures are constructed for arbitrary spectral windows. Applied to soliton-driven resonant radiation, QSSF shows that the selected radiation band acquires a steadily increasing von Neumann entropy and a corresponding loss of purity, quantifying its entanglement with the rest of the spectrum in the lossless Gaussian setting. The analysis also reveals a surprisingly pronounced low-dimensional structure: although the radiation occupies many Fourier bins, its reduced Gaussian state is dominated by only a few Williamson modes. QSSF therefore provides a practical information-theoretic diagnostic for quantum correlations in nonlinear frequency conversion, supercontinuum generation, and multimode squeezed-light formation in ultrafast waveguide platforms.

Read & Discuss → View Source →

03.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2603.09555

Compiler-First State Space Duality and Portable $O(1)$ Autoregressive Caching for Inference

Authors:

Cosmo Santoni↗Anmol Thapar↗

arXiv:2603.09555v2 Announce Type: replace-cross Abstract: High-throughput Mamba-2 inference is usually tied to fused CUDA and Triton kernels, limiting portability across accelerator backends. We show that the state space duality (SSD) recurrence has a compiler-friendly structure: diagonal per-head dynamics, fixed-size chunking, einsum-dominated compute, and static control flow. Expressing this structure in standard JAX primitives gives a single-source inference path with no custom kernels, a registered JAX PyTree cache, and a compiled on-device autoregressive loop. On a single Google Cloud TPU v6e, batch-1 prefill reaches approximately 140 TFLOPS, or 15% model FLOP utilisation (MFU), the roofline ceiling for this regime, and cached decode reaches up to 64% hardware bandwidth utilisation (HBU). At a 4096-token context, cached decode is 27x–36x faster than full-prefix recomputation across five Mamba-2 checkpoints from 130M to 2.7B parameters. The same source runs unmodified on NVIDIA L40S, where cached decode remains sequence-length independent across all model scales. WikiText-103 validation perplexity matches the Triton reference mamba_ssm v2.2.2 within +/-0.0005 points, and hidden states agree to float32 rounding tolerance. Code is available at https://github.com/CosmoNaught/mamba2-jax.

Read & Discuss → View Source →

04.

arXiv (quant-ph) 2026-06-19 DOI: arXiv:2606.20192

Optimal multi-spectral squeezing via deterministic 2D-phase optimization

Authors:

Bastien Oriot↗Peter Namdar↗Emilie Gillet↗RL Rincon Celis↗Valentina Parigi↗

arXiv:2606.20192v1 Announce Type: new Abstract: Optimization routines are ubiquitous in quantum information technologies and essential to reach the resource levels required by quantum protocols. Specifically, multi-spectral squeezing for use in such protocols requires that losses be kept minimal at every stage, including coherent detection, which is performed by interfering the signal with a classical local-oscillator beam. This in turn requires control over all optical degrees of freedom of the beam in order to optimize the detection. The most general framework for this optimization relies on agnostic, off-the-shelf machine-learning techniques. Here we take the opposite approach: by focusing on a physical description of the specific optical process, we develop a deterministic sequential algorithm that provably reaches the global maximum of the visibility in a pixel basis and scales linearly with the number of pixels, thereby offering an efficient and theoretically grounded alternative to black-box optimization. In our waveguide-based setup, the optimized mask increases the visibility from 76% to 84%, corresponding to a 20% gain in mode-matching efficiency. Multi-spectral squeezing measurements confirm that this improvement translates directly into quantum readout: for the most squeezed spectral mode, the squeezing increases from $-2.08$ dB to $-2.64$ dB, consistent with the inferred efficiency gain. These results establish deterministic spatial phase shaping as an effective, interpretable route to enhanced multimode squeezing in waveguide platforms.

Read & Discuss → View Source →

05.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2510.20454

Capturing Intransitive Dominance in Tennis Forecasting: A Graph Neural Network Approach

Authors:

Lawrence Clegg↗John Cartlidge↗

arXiv:2510.20454v2 Announce Type: replace Abstract: Intransitive player dominance, where player A beats B, B beats C, but C beats A, is common in competitive tennis. Yet, there are few known attempts to incorporate it within forecasting methods. We address this problem with a graph neural network approach that explicitly models these intransitive relationships through temporal directed graphs, with players as nodes and their historical match outcomes as directed edges. Our model (65.7% accuracy, 0.214 Brier score) forecasts competitively with established rating systems such as Weighted Elo. Although it does not improve on the baseline in unconditional accuracy, a forecast-encompassing test shows that it carries complementary information. A combined forecast significantly outperforms Weighted Elo, and there is some indication that the gain grows more strongly on the intransitive matchups our model targets. A graph-based representation of player interactions thus captures a forecasting signal that transitive rating systems discard, even between players who share no common opponents.

Read & Discuss → View Source →

06.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11272

Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data

Authors:

Masoume Gholizade↗Fabrizio Ruffini↗Pietro Ducange↗Francesco Marcelloni↗

arXiv:2606.11272v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative and privacy-preserving model training across distributed clients, but most existing FL systems implicitly assume data stationarity. In real-world settings-such as healthcare, industrial IoT (IIOT), cybersecurity, and smart cities-data streams are inherently non-stationary, leading classical FL methods to suffer from performance degradation, instability, and catastrophic forgetting. Continual Learning (CL) addresses learning under evolving data distributions but has been largely studied in centralized settings, overlooking key constraints of federated systems, including privacy, limited communication, and client heterogeneity. Federated Continual Learning (FCL) emerges at the intersection of FL and CL, aiming to support lifelong, adaptive, and privacy-aware learning over distributed and non-stationary data. This survey provides a comprehensive and systematic overview of FCL. We first present a formal definition of the FCL problem and clarify its distinctive characteristics. We then analyze the limitations of classical FL under non-stationary conditions, highlighting how CL principles support long-term adaptation. To organize the rapidly growing literature, we propose a multi-dimensional taxonomy of FCL approaches. Furthermore, we review representative application domains and data modalities, summarize commonly used evaluation metrics, and discuss experimental perspectives for assessing long-term performance and forgetting. Finally, we highlight key open challenges, including handling extreme heterogeneity under temporal drift, designing scalable and privacy-preserving memory mechanisms, and establishing standardized benchmarks. This survey aims to serve as a reference and a roadmap for advancing FCL toward robust and deployable real-world systems.

Read & Discuss → View Source →

07.

arXiv (math.PR) 2026-06-11 DOI: arXiv:2605.12191

Sure-almost-sure and Sure-limit-sure Window Mean Payoff in Markov Decision Processes

Authors:

Pranshu Gaba↗Shibashis Guha↗

arXiv:2605.12191v2 Announce Type: replace-cross Abstract: Given rationals $\alpha$ and $\beta$, the sure-almost-sure problem for a threshold Boolean objective $\varphi$ in a Markov decision process (MDP) asks if one can simultaneously ensure that all outcomes of the MDP have $\varphi$-value at least $\alpha$ (i.e. sure $\alpha$ satisfaction) and with probability $1$ the outcome has $\varphi$-value at least $\beta$ (i.e. almost-sure $\beta$ satisfaction). The sure-limit-sure problem asks if for all $\varepsilon > 0$ one can simultaneously ensure that all outcomes have $\varphi$-value at least $\alpha$ and with probability at least $1 - \varepsilon$ the outcome has $\varphi$-value at least $\beta$. Moreover, if simultaneous satisfaction of objectives is possible, then one would also like to construct a strategy (for sure-almost-sure) or a family of strategies (for sure-limit-sure) that achieves this. In this paper, we solve the sure-almost-sure and sure-limit-sure problems for window mean-payoff objectives. The window mean-payoff objective strengthens the standard mean-payoff objective by requiring that eventually, from every point in the infinite run, the average payoff becomes greater than a given threshold within a finite window length. We study two variants of window mean payoff: in the fixed variant, the window length $\ell$ is given, while in the bounded variant, the length is not given but is required to be bounded throughout the run. We show that the sure-almost-sure problem and the sure-limit-sure problem are both in P for the fixed variant (if $\ell$ is given in unary) and are both in NP $\cap$ coNP for the bounded variant, matching the computational complexity of sure satisfaction and almost-sure satisfaction when considered separately for these objectives. We also give bounds for the memory requirement of winning strategies for all considered problems.

Read & Discuss → View Source →

08.

arXiv (CS.CV) 2026-06-24 DOI: arXiv:2606.24297

Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching

Authors:

Sujun Sun↗Mingwu Ren↗Haofeng Zhang↗

Cross-domain Few-shot Segmentation (CD-FSS) aims to transfer knowledge learned from source domain to distinct target domains, segmenting unseen target classes with only a few annotated samples. Although existing methods have made significant progress, they still rely on training or fine-tuning processes, which incur high computational costs and risk overfitting. We observe that when powerful and general-purpose vision foundation models are incorporated into these methods, their performance shows only marginal improvement or even degrades due to overfitting. To address this, we eliminate trainable parameters and propose a training-free framework to avoid both training overhead and overfitting. Built upon the self-supervised vision encoder DINOv3, our framework addresses cross-domain challenges through three core modules. First, the Semantic-aware Feature Re-fusion (SAFR) module identifies and re-fuses features that emphasize semantic patterns, generating representations with enhanced semantic discriminability. Additionally, the Adaptive Support Enhancement (ASE) module narrows semantic gaps between support and query through robust query information aggregation. Finally, the Hybrid Prototype Matching (HPM) module integrates matching results from diverse prototypes to adapt to varying semantic complexity across domains. Extensive experiments on four target domain datasets demonstrate that our method achieves state-of-the-art performance in CD-FSS without any training.

Read & Discuss → View Source →

09.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12918

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

Authors:

Chejian Xu↗Zhaorun Chen↗Jingyang Zhang↗Freddy Lecue↗Avni Kothari↗Sarah Tan↗Wenbo Guo↗Bo Li↗

arXiv:2606.12918v1 Announce Type: cross Abstract: Hierarchical multi-agent systems (MAS) are rapidly being deployed in high-stakes workflows across domains such as finance and software engineering. In these systems, safety and security are inherently distributed across role-specialized agents, significantly expanding the attack surface, particularly under coordinated adversarial behaviors such as privilege escalation and cross-agent collusion. Existing red-teaming approaches for MAS remain limited: they rely on heuristic selection of target agents and perturb isolated message streams, leaving critical questions unanswered as which agents are most responsible for system safety, and how compromised agents can coordinate to bypass defenses. We propose MAStrike, a closed-loop framework for collusive red-teaming in hierarchical MAS. We propose the first agent-level Shapley value analysis for MAS, quantifying each agent's marginal contribution to system robustness under task-specific distributions. GGuided by this attribution, MAStrike identifies vulnerable agent coalitions and generates coordinated, role-aware adversarial manipulations. These attacks are iteratively refined through structured causal diagnosis, attributing failure cases to uncompromised agents that block adversarial attempts. We further build a comprehensive MAS red-teaming benchmark and controllable environments spanning diverse hierarchical topologies and domains, including finance, software engineering, and CRM. Extensive experiments across MAS built on multiple frontier models show that MAStrike substantially outperforms heuristic baselines. Our analysis further uncovers non-trivial Shapley value distributions and higher-order interaction structures among agents, revealing critical vulnerabilities and coordination patterns that are overlooked by prior single-agent or template-based methods.

Read & Discuss → View Source →

10.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12816

Graph Reinforcement Learning for Calibration-Aware Quantum Circuit Routing

Authors:

Yash Vardhan Tomar↗Dheeraj Peddireddy↗Vaneet Aggarwal↗

arXiv:2606.12816v1 Announce Type: cross Abstract: Quantum circuit routing is a key step in compiling programs for noisy intermediate-scale quantum processors. Routes that appear efficient by standard overhead metrics can still lose fidelity when they pass through poorly calibrated couplers. We study a calibration-aware graph reinforcement-learning router that uses same-day IBM Heron r2 calibration data to choose hardware-edge SWAPs. We train the policy with proximal policy optimization and evaluate it with exact simulated fidelity across nine Munich Quantum Toolkit (MQT) Bench circuits and three calibration snapshots. Across these evaluations, pooled mean exact fidelity is $0.727$, compared with $0.440$ for SABRE-best20 and $0.481$ for target-aware SABRE. Fidelity gains come with higher routed two-qubit counts and are concentrated in the 5q and 8q circuit families; under the fixed tree action graph, all 10q families favor SABRE-best20. Overall, our results show that calibration-aware learned routing can improve fidelity beyond gate-count-driven compilation.

Read & Discuss → View Source →

11.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2605.14084

CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing

Authors:

Mingzhi Zhu↗Michele Merler↗Raju Pavuluri↗Stacy Patterson↗

Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these capabilities are complementary but misaligned. The Instruct model is concise and tool-disciplined, whereas the Thinking model offers stronger planning and recovery behavior but often over-deliberates and degrades agent performance. We present CRANE (Constrained Reasoning Injection for Code Agents via Nullspace Editing), a training-free parameter-editing method that treats the Thinking-Instruct delta as a directional pool of candidate reasoning edits for the Instruct backbone. CRANE combines magnitude thresholding to denoise the delta, a Conservative Taylor Gate to retain edits that are jointly beneficial for reasoning transfer and tool-use preservation, and Graduated Sigmoidal Projection to suppress format-critical update directions. By merging paired Instruct and Thinking checkpoints, CRANE delivers strong gains over either individual model while preserving Instruct-level efficiency: on Roo-Eval it achieves pass1 of 66.2% (+19.5%) for Qwen3-30B-A3B and 81.5% (+8.7%) for Qwen3-Next-80B-A3B; on SWE-bench-Verified it resolves up to 14 additional instances at both scales (122/500 and 180/500); and on Terminal-Bench v2 it improves pass1/pass5 by up to 2.3%/7.8%, reaching 7.6%/17.9% and 14.8%/30.3%, respectively, consistently outperforming alternative merging strategies across all three benchmarks.

Read & Discuss → View Source →

12.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2510.07750

Calibrating Decision Robustness via Inverse Conformal Risk Control

Authors:

Wenbin Zhou↗Shixiang Zhu↗

arXiv:2510.07750v3 Announce Type: replace-cross Abstract: Robust optimization safeguards decisions against uncertainty by optimizing against worst-case scenarios, yet their effectiveness hinges on a prespecified robustness level that is often chosen ad hoc, leading to either insufficient protection or overly conservative and costly solutions. Recent approaches using conformal prediction construct data-driven uncertainty sets with finite-sample coverage guarantees, but they still fix coverage targets a priori and offer little guidance for selecting robustness levels. We propose a new framework that provides distribution-free, finite-sample guarantees on both miscoverage and regret for any family of robust predict-then-optimize policies. Our method constructs valid estimators that trace out the miscoverage–regret Pareto frontier, enabling decision-makers to reliably evaluate and calibrate robustness levels according to their cost–risk preferences. The framework is simple to implement, broadly applicable across classical optimization formulations, and achieves sharper finite-sample performance. This paper offers a principled data-driven methodology for guiding robustness selection and empowers practitioners to balance robustness and conservativeness in high-stakes decision-making.

Read & Discuss → View Source →

13.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2602.23638

FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA

Authors:

Haoran Zhang↗Dongjun Kim↗Seohyeon Cha↗Haris Vikalo↗

arXiv:2602.23638v3 Announce Type: replace-cross Abstract: Federated LoRA provides a communication-efficient mechanism for fine-tuning large language models on decentralized data. In practice, however, a discrepancy between the factor-wise averaging used to preserve low rank and the mathematically correct aggregation of local updates can cause significant aggregation error and unstable training. We argue that a major source of this problem is rotational misalignment, arising from the rotational invariance of low-rank factorizations – semantically equivalent updates can be represented in different latent subspaces across clients since $(B_i R_i)(R_i^\top A_i) = B_i A_i$. When such misaligned factors are averaged directly, they interfere destructively and degrade the global update. To address this issue, we propose FedRot-LoRA, a federated LoRA framework that aligns client updates via orthogonal transformations prior to aggregation. This alignment preserves the semantic update while reducing cross-client subspace mismatch, without increasing communication cost or restricting model expressivity. We provide a convergence analysis that examines the aggregation error induced by factor-wise averaging and shows how rotational alignment yields a tighter upper bound on this error. Extensive experiments on natural language understanding and generative tasks demonstrate that FedRot-LoRA consistently outperforms existing federated LoRA baselines across a range of heterogeneity levels and LoRA ranks.

Read & Discuss → View Source →

14.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18820

Maturing Markov Decision Processes: Decision Making under Increasing Information and Shrinking Action Sets

Authors:

Jiaxi Liu↗Aiping Yang↗Yuhang Yang↗Shuqi Zhang↗Zewei Dong↗Jiangming Yang↗Xuebin Chen↗

arXiv:2606.18820v1 Announce Type: cross Abstract: Sequential decision problems often exhibit an asymmetric evolution of information and decision flexibility: as a decision cycle unfolds, the agent receives richer information while feasible actions expire due to operational cutoffs, commitments, or resource constraints. Standard MDP formulations typically flatten this structure into stage-dependent state descriptions and action masks, thereby obscuring the nested information–action asymmetry that determines which decisions are urgent and which can be deferred. We introduce Maturing Markov Decision Processes (MMDPs), a formulation built around this information–action asymmetry. We characterize one of its key consequences through an expiring-action priority principle, which identifies the actions that must be resolved before the next stage. Motivated by this structure, we develop a structure-aware reinforcement learning framework with stage-aware policy design, expiring-action abstraction, and search-augmented learning with distillation. Experiments on a controlled multi-supplier replenishment problem, simplified cash-management environments of increasing complexity, and a production-scale simulator show that explicitly modeling this asymmetry improves learning efficiency and becomes increasingly valuable as decision problems scale.

Read & Discuss → View Source →

15.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17437

Spatio-Temporal Fusion Model for Standard View Classification of Echocardiographic Videos

Authors:

Bo Gou↗Jicheng Zhang↗Jianlong Xiong↗Tao He↗Bentian Liu↗Hai Wu↗Yijiao Wang↗Yu Zhang↗Yujia Yang↗Yun Dai↗Jian Liu↗Jie Wang↗…

Automated classification of standard echocardiographic views is crucial for efficient clinical workflow but faces three main challenges. First, publicly available datasets are scarce and limited in scale and view coverage. Second, the performance of some modern video-level architectures for echocardiographic view classification remains underexplored. Third, some view categories exhibit highly similar spatial appearances, making single-frame features insufficient for discrimination, while heterogeneous frame quality complicates robust temporal information fusion. To address these challenges, we release the Echocardiographic Videos of Nine Views (EV9V) dataset, comprising 5,138 videos, 910,579 frames, and 9 standard views, which is, to the best of our knowledge, the largest publicly available echocardiography video dataset. Using EV9V, we systematically benchmark representative video classification architectures, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers. Furthermore, we propose a Spatio-Temporal Fusion Model (STFM), an efficient dual-stream CNN-LSTM (Long Short-Term Memory) framework that jointly captures spatial anatomical structures and temporal cardiac dynamics. The proposed framework leverages uncertainty-aware learning to preferentially sample representative video segments during training and evidence-based fusion during inference, improving robustness to variations in frame quality across echocardiographic videos. Extensive experiments demonstrate that our method achieves competitive performance across diverse video classification models, validating the effectiveness of uncertainty-aware spatio-temporal learning for echocardiographic view classification. The code is available at https://github.com/bgx666/stfm.

Read & Discuss → View Source →

16.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15778

DYNA : Dynamic Episodic Memory Networks for Augmenting Large Language Models with Temporal Knowledge Graphs in Continuous Learning

Authors:

Ali Sarabadani↗Mahtab Tajvidiyan↗

Large Language Models (LLMs) struggle to incorporate new knowledge without forgetting or costly retraining. We propose DYNA, a lightweight framework that augments a frozen LLM with a temporal knowledge graph where events are nodes and temporal relations are directed, timestamped edges. The graph serves as an external, updatable memory. At query time, DYNA retrieves relevant nodes via random walks and centrality measures, then augments the LLM's response. Evaluated on three temporal recall tasks, DYNA reduces catastrophic forgetting by ~7% compared to fine-tuning and improves temporal ordering by ~5% over standard RAG. Higher graph clustering coefficients correlate with better retrieval, showing that graph structure matters. Contributions: (1) episodic memory as temporal KG, (2) retraining-free LLM augmentation, (3) graph properties as predictors of retrieval performance.

Read & Discuss → View Source →

17.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.18080

Edge Flow: A Tractable and Predictive Continuous-Time Model for Gradient Descent at the Edge of Stability

Authors:

Pierre Marion↗

arXiv:2606.18080v1 Announce Type: new Abstract: Gradient descent in deep learning may operate at the edge of stability (EoS), a regime in which the largest eigenvalue of the loss Hessian hovers near the stability threshold $2/\eta$, where $\eta$ is the learning rate. Classical analysis tools such as gradient flow and the descent lemma do not apply here, motivating the search for a continuous-time model valid at EoS. We propose Edge Flow, a system of three coupled ordinary differential equations that provides a tractable, faithful, and predictive model of gradient descent dynamics at EoS. Edge Flow decomposes the dynamics into a center, an oscillation direction, and an oscillation magnitude. The center follows a modified gradient flow on a symmetrized loss; the direction tracks a top eigenvector of the Hessian via Rayleigh quotient dynamics; and the magnitude grows or decays exponentially depending on whether the sharpness exceeds or falls below the threshold $2/\eta$. Crucially, sharpness stabilization emerges from the coupled dynamics via a self-stabilization feedback loop. Discretizing Edge Flow only requires two gradient evaluations and one Hessian–vector product at each iteration. We demonstrate empirically that Edge Flow tracks the dynamics of gradient descent at least as faithfully as previously proposed continuous-time EoS models, while in addition resolving the oscillation of the sharpness at the onset of EoS, and that it provides a principled framework for understanding and mitigating instabilities in this regime.

Read & Discuss → View Source →

18.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2605.03065

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies

Authors:

Sarvesh Patil↗Mitsuhiko Nakamoto↗Manan Agarwal↗Shashwat Saxena↗Jesse Zhang↗Giri Anantharaman↗Cleah Winston↗Chaoyi Pan↗Douglas Chen↗Nai-Chieh Huang↗Zeynep Temel↗Oliver Kroemer↗…

arXiv:2605.03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. This work introduces Off-policy Generative Policy Optimization (OGPO), a sample-efficient algorithm for finetuning GCPs that maintains off-policy critic networks to maximize data reuse and propagate policy gradients through the full generative process of the policy via a modified PPO objective, using critics as the terminal reward. OGPO achieves state-of-the-art performance on manipulation tasks spanning multi-task settings, high-precision insertion, and dexterous control. To our knowledge, it is also the only method that can fine-tune poorly-initialized behavior cloning policies to near full task-success with no expert data in the online replay buffer, and does so with few task-specific hyperparameter tuning. Through extensive empirical investigations, we demonstrate that OGPO drastically outperforms methods alternatives on policy steering and learning residual corrections, and identify the key mechanisms behind its performance. We further introduce practical stabilization tricks, including success-buffer regularization, two-sided conservative advantages, and Q-variance reduction, to mitigate critic over-exploitation across state- and pixel-based settings. Beyond proposing OGPO, we conduct a systematic empirical study of GCP finetuning, identifying the stabilizing mechanisms and failure modes that govern successful off-policy full-policy improvement.

Read & Discuss → View Source →

19.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15455

Understanding Diversity Collapse in RLVR via the Lens of Overtraining

Authors:

Suqin Yuan↗Jinkun Chen↗Jiyang Zheng↗Muyang Li↗Lei Feng↗Dadong Wang↗Tao Xiang↗Tongliang Liu↗Bo An↗

arXiv:2606.15455v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a key approach for enhancing the reasoning abilities of large language models. However, RLVR often suffers from diversity collapse: Pass@$1$ improves while high-$k$ Pass@$k$ degrades, which is viewed as a narrowing of the model's reasoning boundary. We formalize this diversity collapse through the lens of overtraining: once a problem's contribution to the reference metric has effectively saturated, further updates no longer expand what the model can solve but still concentrate probability mass on the trajectories favored by on-policy sampling. Under a standard setup with few rollouts per problem, even a single observed success places a problem in a nearly saturated regime for high-$k$ Pass@$k$, so most updates in standard RLVR are overtraining from the boundary perspective. This perspective also suggests a reading of whether RLVR can expand the model's reasoning abilities beyond the base model: since RLVR is structurally biased against high-$k$ Pass@$k$, its aggregate decline does not by itself mean that no new reasoning gains occurred. Interventionally, restricting updates to problems with zero observed success lifts Pass@$256$ above the base model on difficult benchmarks; observationally, a non-trivial fraction of initially unsolvable problems become solvable during standard RLVR training. Building on these findings, we propose Bayesian Boundary Gating (BBG), which redirects optimization away from overtraining by estimating each problem's marginal contribution to the reasoning boundary. Across multiple reasoning benchmarks, BBG improves average Pass@$k$ across a wide range of $k$.

Read & Discuss → View Source →

20.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15770

ttda704 at SemEval-2026 Task 6: Structured Chain-of-Thought Prompting for Political Evasion Detection

Authors:

Tai Tran Tan↗An Dinh Thien↗

This paper describes our system for SemEval-2026 Task 6, which addresses the classification of political evasion strategies in English question-answer pairs extracted from U.S. presidential interviews. We systematically compare two distinct paradigms: (1) Parameter-Efficient Fine-Tuning of Qwen3 models (4B-32B) using QLoRA, enhanced with tiered upsampling and weighted cross-entropy loss to address severe class imbalance, and (2) structured Chain-of-Thought (CoT) prompting of reasoning-capable API models, namely DeepSeek-V3.2 and Grok-4-Fast. Our evaluation demonstrates that structured CoT prompting of reasoning-enabled models substantially outperforms our baseline parameter-efficient fine-tuning implementation in absolute Macro F1. Our best system, Grok-4-Fast with extended reasoning and few-shot hierarchical CoT prompting, achieves a Macro F1 of 0.5147 on Subtask 2 (9-class evasion) and 0.7979 on Subtask 1 (3-class clarity), ranking 8th out of 33 teams on Subtask 2 and 13th out of 41 teams on Subtask 1 on the official leaderboard. Furthermore, our ablation studies reveal key insights into effective prompt design for evasion detection: presenting labels within a hierarchical taxonomy helps structure model reasoning, while few-shot exemplars provide task calibration. However, the strongest prompt variants are not statistically distinguishable in Macro F1, and explicitly enabling extended reasoning modes yields substantial performance gains by facilitating the multi-step pragmatic analysis required to detect evasive intent.

Read & Discuss → View Source →

21.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15146

Contextual Bandits for Maximizing Stimulated Word-of-Mouth Rewards

Authors:

Ahmed Sayeed Faruk↗Elena Zheleva↗

arXiv:2606.15146v1 Announce Type: new Abstract: Stimulated word-of-mouth is a strategy that promotes information sharing through prompts or incentives. Optimizing stimulated word-of-mouth through social networks requires identifying and targeting connected users who are most susceptible to spillover, a phenomenon where the influence of recommendations extends beyond the immediate audience to impact their connected users. The probability of spillover varies across individuals, and their connections, leading to heterogeneity. Understanding and accurately estimating the spillover probabilities among users in social networks is crucial for improving the effectiveness of stimulated word-of-mouth. To address this, we present a novel contextual multi-armed bandit framework that learns individual spillover probabilities and ranks connected users to maximize rewards from stimulated word-of-mouth. Experiments on real-world network datasets demonstrate that accounting for spillover heterogeneity enhances the targeting precision of top-$k$ connected users, boosting rewards and outperforming baseline methods that do not learn individual spillover effects.

Read & Discuss → View Source →

22.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12616

PersonaDrive: Human-Style Retrieval-Augmented VLA Agents for Closed-Loop Driving Simulation

Authors:

Mahmoud Srewa↗Praneetsai Iddamsetty↗Mohammad Abdullah Al Faruque↗Salma Elmalaki↗

Closed-loop driving simulators typically populate their environments with non-ego traffic agents that behave largely the same way, produced either by rule-based traffic managers or by learned models trained toward a single behavioral mode. Recent work introduces style variation through post-hoc labels on observational data or LLM-inferred reward weights, but these signals act as proxies for what a style should reward rather than demonstrations of humans explicitly asked to drive in that style. We introduce PersonaDrive, a pipeline that conditions a vision-language-action (VLA) driving agent on retrieved demonstrations from a style-instructed human driving dataset, in which participants drive CARLA leaderboard routes under aggressive, neutral, and conservative instructions on a driver-in-the-loop rig. The pipeline has three stages: (i) offline triplet mining over per-style human driving data using a combined image-text similarity score; (ii) training a lightweight retrieval head that fuses frozen visual features with a small control encoder over per-style databases; and (iii) fine-tuning a single VLA backbone to treat retrieved context points as in-context behavioral demonstrations during waypoint prediction. At inference, the same backbone is conditioned on any style by swapping which per-style database the retrieval head queries, so selecting a style requires no per-style retraining while enabling human-style, style-diverse non-ego agents for closed-loop simulation. On Bench2Drive, PersonaDrive (no style) improves the driving score by 4.6% over SimLingo and 2.5% over HiP-AD, and under style conditioning attains the highest driving score in every style within a roughly 2% band (its weakest style surpassing the strongest baseline, DMW, by 5.4%), while average speed and acceleration rise by 18% and 25% from the conservative to the aggressive instruction.

Read & Discuss → View Source →

23.

medRxiv (Medicine) 2026-06-22 DOI: HASH:5bcc53f1f11c04b5dbcbb1bb322bfb48

Substantia Nigra and Subthalamic Nucleus Deep Brain Stimulation Exert Opposing Effects on Novelty Recognition in Parkinson's Disease

Authors:

Li↗Jiang↗Liu↗Yang↗Yao↗Zhang↗Xie↗Hollunder↗Strange↗Meng↗Wang↗Shi↗…

Episodic memory plays a critical role in supporting adaptive behavior; however, whether it can be causally regulated in humans via deep subcortical stimulation remains unclear. In the present study, we investigated the differential effects of substantia nigra (SN) and subthalamic nucleus (STN) stimulation on episodic memory, as well as the underlying mechanisms of its associated brain networks, using a recognition memory task combined with concurrent functional magnetic resonance imaging in patients with Parkinson's disease. SN-DBS increased recognition sensitivity and reduced false alarms at both frequencies, whereas 10 Hz STN-DBS reduced sensitivity and increased false alarms. Functional connectivity analyses in the absence of DBS stimulation identified a false recognition-related network linking nigral, pallidal, subthalamic, medial temporal, frontal, and occipital regions. SN-DBS-related false alarm reduction tracked modulation of this circuit and was marked by its baseline vulnerability state. These behavioral effects mapped onto target-dependent parieto-occipital and SN-visual retrieval pathways, supporting a model in which DBS bidirectionally regulates recognition memory through target- and frequency-dependent subcortical-cortical circuits.

Read & Discuss → View Source →

24.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15783

ttda704 at SemEval-2026 Task 4: Modeling Narrative Structures via Pseudonymization and Multi-View Sentence Alignment

Authors:

Tai Tran Tan↗An Dinh Thien↗

We present our approach to SemEval 2026 Task 4: Narrative Story Similarity and Narrative Representation Learning. Our solution uses contrastive learning with fine-tuned sentence transformers to capture narrative similarity across abstract themes, course of action, and outcomes. We develop two pipelines: (Track A) a single-view method that encodes full narratives with smart layer freezing to reduce overfitting, and (Track B) a multi-view method that models theme, plot, and outcome with view-specific projection heads and self-supervised alignment. Both pipelines build on sentence-transformers models and are trained with contrastive loss on synthetic data. The code is available at the following GitHub repository: https://github.com/dinhthienan33/SemEval2026-Task4-ttda704.

Read & Discuss → View Source →

25.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2510.11228

Mean-field BSDEs with non-Lipschitz coefficients and double mean reflections

Authors:

Hanwu Li↗Jin Shi↗

arXiv:2510.11228v2 Announce Type: replace Abstract: The present paper is devoted to the study of mean-field backward stochastic differential equations (MFBSDEs) with double mean reflections whose generators are not Lipschitz continuous. With the help of the Skorokhod problem and some a priori estimates for MFBSDEs, we establish the existence and uniqueness results for doubly mean reflected MFBSDEs.

Read & Discuss → View Source →