中 EN
登录 注册账户

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。

登录 注册账户
01.
medRxiv (Medicine) 2026-06-23

Changes in hierarchical brain dynamics of rumination following mindfulness-based cognitive therapy for depression

作者:
Dagnino↗P. C↗van der Velden↗A. M↗Ruhe↗H. G↗Kuyken↗Kringelbach↗M. L↗Vohryzek↗Deco↗

Major depressive disorder (MDD) is a leading cause of disability worldwide with risk of onset and recurrence linked to depressive ruminative thought patterns. Mindfulness-based cognitive therapy (MBCT) is an evidence-based treatment for depression that targets the ability to recognise, decenter, and disengage from ruminative thought patterns. Elucidating how MBCT impacts hierarchical brain organisation may be key to understanding the processes by which MBCT can modulate ruminative tendencies. In a randomised controlled functional magnetic resonance imaging (fMRI) trial on individuals with MDD (N=80) before and after MBCT in addition to treatment as usual (TAU), we investigated changes in hierarchical brain organisation during resting-state and rumination. We built whole-brain models to obtain generative connectivity (GEC) matrices per patient and quantified brain hierarchy by measuring the global directedness and regional trophic levels in each GEC, in which greater directedness reflects more directional information flow and less recurrence. Global directedness in MBCT+TAU compared to TAU increased during rumination, with no changes during resting-state. Furthermore, increased regional breadth of hierarchy during rumination was related to improvements in clinical and behavioural outcomes following MBCT+TAU. Increased brain hierarchy during rumination following mindfulness training may be consistent with a shift away from self-reinforcing negative mental loops towards more differentiated and less coupled cognitive and bodily cycles, supporting MBCT's ability to interrupt ruminative processes. Hierarchical brain dynamics may hold promise as a treatment-sensitive marker and a potential mechanism of therapeutic change in MBCT for depression.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.LG) 2026-06-19

On the Variance of Temporal Difference Learning and its Reduction Using Control Variates

作者:
Hsiao-Ru Pan↗Bernhard Sch\"olkopf↗

arXiv:2606.20357v1 Announce Type: new Abstract: We analyze the variance of temporal difference (TD) learning using the phased setting with tabular representation, and show that one of the mechanisms behind its ability to reduce variance is by effectively aggregating over a larger number of independent trajectories. Based on this insight, we demonstrate that (1) the variance of TD is asymptotically bounded from above by Monte Carlo (MC) estimators, and (2) shorter horizon updates incurs less variance for a fixed number of samples. Beyond TD, we show that Direct Advantage Estimation (DAE), a method for estimating the advantage function, can be seen as a type of regression-adjusted control variate, which achieves a tighter bound on the variance compared to TD in the large-sample limit. Finally, we numerically illustrate the behaviors of these estimators with carefully designed environments.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CV) 2026-06-24

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

作者:
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.

阅读与讨论 → 访问原文 →
04.
arXiv (math.PR) 2026-06-25

Pointwise Hurst Estimation via Scale Accumulation: A Noise-Robust Approach for Rough Volatility

作者:
Jokubas Petkevicius↗

arXiv:2606.25771v1 Announce Type: cross Abstract: We introduce an estimator for the pointwise, time-varying Hölder exponent (Hurst parameter) of a stochastic process, based on the geometry accumulation integral G_Lambda(t) = integral from Lambda to 1 of |eth_s X(t)| s^{-1} ds, where eth_s X(t) = (X(t+s)-X(t))/s is the scale derivative at resolution s. We prove consistency, noise robustness with explicit threshold Lambda* = sigma^{1/H}, and a CLT at rate (log Lambda)^{-1/2}. The estimator is pointwise in time, defined at finite resolution, and eliminates microstructure noise by scale separation. Existing estimators give a global H from integrated variance; this gives a time-varying H(t) directly from the price path.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.LG) 2026-06-15

Neural ARFIMA model for forecasting BRIC exchange rates with long memory

作者:
Donia Besher↗Madhurima Panja↗Shovon Sengupta↗Tanujit Chakraborty↗

arXiv:2509.06697v3 Announce Type: replace-cross Abstract: Exchange rate forecasting remains a challenging problem, particularly for emerging economies, where the observed time series exhibit pronounced long-memory dependence, nonlinear dynamics, and sensitivity to macro-financial drivers. Classical models such as ARFIMA capture long-range persistence but fail to adequately represent nonlinear relationships, while modern machine learning approaches often neglect the underlying long-memory structure in macroeconomic series. To address this gap, we propose a Neural AutoRegressive Fractionally Integrated Moving Average (NARFIMA) model that integrates ARFIMA-based long-memory modeling with neural networks for nonlinear function approximation, while incorporating exogenous macroeconomic and uncertainty indicators. The framework provides a unified approach for capturing persistence, nonlinear dynamics, and external shocks. We establish asymptotic stationarity of the NARFIMA process and develop conformal prediction intervals for distribution-free uncertainty quantification. Empirical results for BRIC exchange rates show that NARFIMA consistently outperforms a broad range of forecasting benchmarks across multiple horizons, underscoring the importance of explicitly modeling long-memory dependence in exchange rate dynamics. The `narfima' R package provides an implementation of our approach.

阅读与讨论 → 访问原文 →
06.
bioRxiv (Bioinfo) 2026-06-13

MoE-Bind: Guiding De Novo Protein Binder Generation with Sparse Experts

作者:
Sarkar↗

De novo protein binder design has been dominated by structure-based pipelines that require known three-dimensional target conformations and consume substantial compute and generation time per design, limiting their throughput and accessibility for routine large-scale binder exploration. Sequence-only generative models promise a faster and lighter alternative, yet existing systems remain uniformly dense and frequently reintroduce structural computation at inference, undermining the core advantages they were intended to deliver. Across the broader language modelling community, transformers have meanwhile transitioned from fully dense designs to sparse Mixture-of-Experts architectures that decouple capacity from per-token compute, a shift that has yet to reach sequence-only protein binder generation. We present MoE-Bind, an autoregressive protein binder generator that, for the first time in this domain, combines Multi-head Latent Attention with a sparse Mixture-of-Experts feed-forward network and is evaluated under two independent structure predictors, Boltz-2 and AlphaFold2-Multimer. Despite activating less than half the per-token parameters of compute-matched dense baselines, MoE-Bind matches or exceeds them on full-length receptor-conditioned binder generation on a leakage-free Docking Benchmark 5.0 evaluation, transfers without peptide-specific training to short-peptide design, and reduces training and inference compute by a large margin. Routing analysis on generated binders reveals interpretable expert specialization at both the individual amino acid and biochemical group level, a structured expert-token alignment not previously reported for natural-language MoE models. These results show that sparse architectural design, rather than scale, can deliver fast, structure-free, and interpretable protein binder generation.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.CV) 2026-06-25

GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization

作者:
Pengyue Jia↗Seongheon Park↗Song Gao↗Xiangyu Zhao↗Sharon Li↗

Worldwide image geolocalization-the task of predicting GPS coordinates from images taken anywhere on Earth-poses a fundamental challenge due to the vast diversity in visual content across regions. While recent approaches adopt a two-stage pipeline of retrieving candidates and selecting the best match, they typically rely on simplistic similarity heuristics and point-wise supervision, failing to model spatial relationships among candidates. In this paper, we propose GeoRanker, a distance-aware ranking framework that leverages large vision-language models to jointly encode query-candidate interactions and predict geographic proximity. In addition, we introduce a multi-order distance loss that ranks both absolute and relative distances, enabling the model to reason over structured spatial relationships. To support this, we curate GeoRanking, the first dataset explicitly designed for geographic ranking tasks with multimodal candidate information. GeoRanker achieves state-of-the-art results on two well-established benchmarks (IM2GPS3K and YFCC4K), significantly outperforming current best methods.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.AI) 2026-06-19

Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods

作者:
Jeong Woon Lee↗Kyoleen Kwak↗Daeho Kim↗Hyoseok Hwang↗

arXiv:2601.22970v2 Announce Type: replace-cross Abstract: Policies learned via continuous actor-critic methods often exhibit erratic, high-frequency oscillations, making them unsuitable for physical deployment. Current approaches attempt to enforce smoothness by directly regularizing the policy's output. We argue that this approach treats the symptom rather than the cause. In this work, we theoretically establish that policy non-smoothness is fundamentally governed by the differential geometry of the critic. By applying implicit differentiation to the actor-critic objective, we prove that the sensitivity of the optimal policy is bounded by the ratio of the Q-function's mixed-partial derivative (noise sensitivity) to its action-space curvature (signal distinctness). To empirically validate this theoretical insight, we introduce PAVE (Policy-Aware Value-field Equalization), a critic-centric regularization framework that treats the critic as a scalar field and stabilizes its induced action-gradient field. PAVE rectifies the learning signal by minimizing the Q-gradient volatility while preserving local curvature. Experimental results demonstrate that PAVE achieves smoothness comparable to policy-side smoothness regularization methods, while maintaining competitive task performance, without modifying the actor.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.CV) 2026-06-25

RubricRL: Simple Generalizable Rewards for Text-to-Image Generation

作者:
Xuelu Feng↗Yunsheng Li↗Ziyu Wan↗Zixuan Gao↗Junsong Yuan↗Dongdong Chen↗Chunming Qiao↗

Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key challenge, however, lies in designing effective and interpretable rewards. Existing methods often rely on either composite metrics (e.g., CLIP, OCR, and realism scores) with fixed weights or a single scalar reward distilled from human preference models, which can limit interpretability and flexibility. We propose RubricRL, a simple and general framework for rubric-based reward design that offers greater interpretability, composability, and user control. Instead of using a black-box scalar signal, RubricRL dynamically constructs a structured rubric for each prompt–a decomposable checklist of fine-grained visual criteria such as object correctness, attribute accuracy, OCR fidelity, and realism–tailored to the input text. Each criterion is independently evaluated by a multimodal judge (e.g., o4-mini), and a prompt-adaptive weighting mechanism emphasizes the most relevant dimensions. This design not only produces interpretable and modular supervision signals for policy optimization (e.g., GRPO or PPO), but also enables users to directly adjust which aspects to reward or penalize. Experiments with an autoregressive text-to-image model demonstrate that RubricRL improves prompt faithfulness, visual detail, and generalizability, while offering a flexible and extensible foundation for interpretable RL alignment across text-to-image architectures.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.LG) 2026-06-16

Physics-conforming Latent Twins

作者:
Matthias Chung↗Yutong Bu↗Deepanshu Verma↗

arXiv:2606.15053v1 Announce Type: new Abstract: Surrogate models are central to scientific machine learning, where they enable fast prediction, simulation, inference, and control for complex physical systems. For time-dependent problems, however, accurate interpolation of training trajectories is not sufficient: reliable surrogates should also respect the conservation laws, invariants, admissibility conditions, and dissipative structures that give those trajectories physical meaning. We introduce Physics-conforming Latent Twins, a framework for learning latent surrogate solution operators whose dynamics satisfy selected physical principles by design. The method builds on the Latent Twin formulation by jointly learning an encoder, a decoder, and a latent flow map between arbitrary time-indexed states, while constraining the latent dynamics to preserve or dissipate prescribed structural quantities. We develop a constraint-transfer viewpoint that connects physical structure in the original state space with compatible constraints in latent space, and prove structure-preservation bounds showing how latent enforcement improves control of physical defects after decoding. We also derive algebraic conditions for latent flow maps that preserve linear and quadratic invariants or enforce dissipative inequalities. Numerical experiments on representative ODE and PDE benchmarks demonstrate improved constraint satisfaction, structural fidelity, and qualitative long-time behavior while maintaining accurate surrogate prediction.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CL) 2026-06-15

Can Post-Training Turn LLMs into Good Medical Coders? An Empirical Study of Generative ICD Coding

作者:
Ziqing Wang↗Weihao Li↗Shijie Chen↗Yuan Luo↗Kaize Ding↗

Automated International Classification of Diseases (ICD) coding is a core medical-coding task for billing, epidemiology, and clinical decision support. Generative large language models (LLMs) are often reported as weak medical coders, but this finding mainly comes from inference-time settings such as prompting, retrieval, reranking, or tool use, leaving the role of task-specific post-training underexplored. We present a controlled empirical study of post-training for generative ICD coding, comparing discriminative baselines with LLM coders across prompting, supervised fine-tuning, and reinforcement learning under a common protocol and metric set. To our knowledge, this is the first study to evaluate RL-based post-training for generative LLM coders in ICD coding. We further introduce PHI, a diagnostic curriculum that extends GRPO to refine missed-code cases. Our results show that prompting-only evaluation substantially underestimates the potential of LLMs for ICD coding. SFT provides the main capability jump, GRPO further improves code-set prediction beyond SFT, and PHI provides targeted gains on macro-level performance. These findings suggest that the main bottleneck is not the generative formulation alone, but how the model is adapted and optimized for full-taxonomy recall. We release our code, data splits, and checkpoints at https://github.com/AlexandreWANG915/LLM4ICD.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.AI) 2026-06-11

\texttt{Range-Arithmetic}: Verifiable Deep Learning Inference on an Untrusted Party

作者:
Ali Rahimi↗Babak H. Khalaj↗Mohammad Ali Maddah-Ali↗

arXiv:2505.17623v2 Announce Type: replace-cross Abstract: Verifiable computing (VC) has gained prominence in decentralized machine learning systems, where resource-intensive tasks like deep neural network (DNN) inference are offloaded to external participants due to blockchain limitations. This creates a need to verify the correctness of outsourced computations without re-execution. We propose \texttt{Range-Arithmetic}, a novel framework for efficient and verifiable DNN inference that transforms non-arithmetic operations, such as rounding after fixed-point matrix multiplication and ReLU, into arithmetic steps verifiable using sum-check protocols and concatenated range proofs. Our approach avoids the complexity of Boolean encoding, high-degree polynomials, and large lookup tables while remaining compatible with finite-field-based proof systems. Experimental results show that our method not only matches the performance of existing approaches, but also reduces the computational cost of verifying the results, the computational effort required from the untrusted party performing the DNN inference, and the communication overhead between the two sides.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CV) 2026-06-16

OneFocus: Enabling Real-World X-ray Security Screening with a Unified Vision-Language Model

作者:
Jiali Wen↗Hongxia Gao↗Litao Li↗Yixin Chen↗Kaijie Zhang↗Qianyun Liu↗Xiaoqin Wen↗

X-ray contraband detection is critical for security in large-scale logistics and transportation, yet conventional detectors struggle to adapt to emerging contraband types and lack fundamental visual understanding. Vision-language models (VLMs) offer strong generalization but are hindered by the scarcity of high-quality X-ray image-caption data. To bridge this critical gap, we present MMXray, a meticulously curated benchmark of 52,124 image-caption pairs spanning 28 fine-grained classes of X-ray contraband. To enrich MMXray with realistic occlusion patterns, we further introduce CleanDET, a dedicated synthesis dataset containing clean foreground contraband images from 28 categories and background images with diverse density levels, together with AnyContraSyn, a controllable synthesis method designed to operate on CleanDET. We also develop OnePipe, an extensible pipeline for systematic data curation. Built on MMXray, we propose OneFocus, a unified VLM that supports four core tasks: visual question answering, contraband localization, classification, and image understanding. OneFocus achieves state-of-the-art performance in X-ray contraband understanding and demonstrates robust cross-domain generalization, establishing a strong vision-language baseline for security screening.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.LG) 2026-06-19

Entropy Estimation in Multi-Qutrit Systems via Variational and Classical Neural Networks

作者:
Sai Sakunthala Guddanti↗Anil Prabhakar↗Ria Rushin Joseph↗

arXiv:2606.20504v1 Announce Type: cross Abstract: We present a systematic study of von Neumann entropy estimation in multi-qutrit quantum systems using two complementary approaches: variational quantum algorithms (VQAs) and classical convolutional neural networks (CNNs), evaluated using an ideal (noise-free) quantum simulator. For systems up to three qutrits, we construct and evaluate 11 hardware-efficient SU(3)-inspired ansatzes. A parameter sweep shows that estimation accuracy is primarily determined by the number of trainable parameters, provided sufficient entanglement is present. Based on this study, we fix the parameter count to approximately 120 for subsequent experiments, observing that increasing entangling-gate counts beyond a threshold yields only marginal improvements. For larger systems (two to five qutrits), we use a CNN trained on measurement outcomes from tensor-product mutually unbiased bases. The model achieves accurate and stable predictions and exhibits a systematic improvement in performance with system size, with the highest errors for two-qutrit systems and the lowest for five-qutrit systems. Notably, using only 12.5% of the measurements required for full state tomography is sufficient to reach 90th-percentile absolute errors of approximately 0.13-0.16 nats for both four- and five-qutrit systems. The CNN model is also robust to shot noise and generalizes well to out-of-distribution states. Overall, within the simulated settings studied here, our results indicate a transition in practical methods: VQAs are effective for small systems, while CNN-based estimators offer improved scalability and robustness for larger qutrit systems.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.AI) 2026-06-16

Honeypot Protocol

作者:
Najmul Hasan↗

arXiv:2604.13301v1 Announce Type: cross Abstract: Trusted monitoring, the standard defense in AI control, is vulnerable to adaptive attacks, collusion, and strategic attack selection. All of these exploit the fact that monitoring is passive: it observes model behavior but never probes whether the model would behave differently under different perceived conditions. We introduce the honeypot protocol, which tests for context-dependent behavior by varying only the system prompt across three conditions (evaluation, synthetic deployment, explicit no-monitoring) while holding the task, environment, and scoring identical. We evaluate Claude Opus 4.6 in BashArena across all three conditions in both honest and attack modes. The model achieved 100% main task success and triggered zero side tasks uniformly across conditions, providing a baseline for future comparisons with stronger attack policies and additional models.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.CV) 2026-06-16

Stepwise Token Selection for Efficient Multimodal Large Language Models

作者:
Landi He↗Shawn Young↗Lijian Xu↗

In multimodal large language models (MLLMs), inference cost is largely dominated by the visual token prefix rather than the language backbone, making token reduction a key factor for improving efficiency. Existing approaches typically assign independent importance scores to visual tokens and retain a fixed number of top-ranked tokens, implicitly assuming token independence and a uniform compression ratio across inputs. In this work, we reformulate visual token pruning as a sequential decision-making process. Specifically, we introduce a pointer-style selection mechanism that iteratively chooses informative tokens, conditioning each decision on previously selected ones, and dynamically determines when to stop via a learned termination action. This enables joint optimization of both the selected subset and its size. To enable end-to-end training under standard language modeling objectives, we design a differentiable relaxation based on a variance-preserving noise interpolation scheme, allowing gradients to propagate through the discrete selection process. Extensive experiments on LLaVA-v1.5-7B and Qwen2.5-VL-7B demonstrate that our approach consistently outperforms fixed-ratio baselines across different compression levels. Under aggressive pruning that removes 88.9% of visual tokens, our method preserves 94.6% of the original accuracy while achieving a 1.88x speed-up in prefill latency.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.CV) 2026-06-15

Rethinking One-Step Image Editing through ChordEdit: Reproduction, Simplification, and New Insights

作者:
Minghan Li↗Jeremy Moebel↗Mengyu Wang↗

One-step image editing is important for making text-guided editing fast, practical, and easy to deploy, but its underlying mechanism is still not fully understood. We revisit ChordEdit through reproduction, ablation, and simplification. Our analysis shows that a) the chord window $\delta$ largely acts as an effective timestep shift from $t$ to $t - \delta$; b) chord transport acts on high-noise images and mainly performs low-frequency semantic editing; and c) proximal alignment acts on low-noise images and complements it by adding high-frequency target details. In this view, ChordEdit naturally decomposes editing into a coarse low-frequency transport stage and a fine high-frequency alignment stage. These findings suggest a path toward prompt-conditioned dynamic timestep selection for adaptive image editing. All code and results can be found at \href{https://github.com/Harvard-AI-and-Robotics-Lab/ChordEdit-Reproduction}{link}.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.CV) 2026-06-19

Hierarchical mutual distillation for multi-view fusion: Learning from all possible view combinations

作者:
Jiwoong Yang↗Haejun Chung↗Ikbeom Jang↗

Multi-view learning often struggles to effectively leverage images captured from diverse angles and locations. Learning methods for unstructured multi-view images remain largely underexplored. We propose a novel Hierarchical Mutual Distillation for Multi-View Fusion (HMDMV) method, which can handle both structured and unstructured multi-view scenarios. It makes predictions utilizing all possible view combinations: single view, partial multi-view, and full multi-view. The method generates predictions for each view combination and then applies hierarchical mutual distillation to enhance inter-view consistency. An uncertainty-based weighting mechanism further refines the fusion process by adjusting the influence of each view combination according to its prediction confidence, reducing the impact of low-confidence views. Extensive experiments on large-scale structured and unstructured datasets demonstrate that HMDMV consistently achieves state-of-the-art classification accuracy. Another unique advantage of HMDMV is that it provides improved flexibility in inference, allowing for more or fewer view counts in inference than those used in training without additional processing. We also provide a light version with reduced training cost by designing an efficient strategy that randomly samples subsets of view combinations during each training iteration. These results highlight HMDMV's robustness in real-world settings where view availability is variable or incomplete. The code is available at https://github.com/labhai/HMDMV.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.AI) 2026-06-11

Vision-Language-Action Jump-Starting for Reinforcement Learning Robotic Agents

作者:
Angelo Moroncelli↗Roberto Zanetti↗Marco Maccarini↗Loris Roveda↗

arXiv:2604.13733v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imperfect rewards remains difficult due to inefficient exploration and poor credit assignment. Vision-Language-Action (VLA) models leverage large-scale multimodal pretraining to provide generalist, task-level reasoning, but current limitations hinder their direct use in fast and precise manipulation. In this paper, we propose Vision-Language-Action Jump-Starting (VLAJS), a method that bridges sparse VLA guidance with on-policy RL to improve exploration and learning efficiency. VLAJS treats VLAs as transient sources of high-level action suggestions that bias early exploration and improve credit assignment, while preserving the high-frequency, state-based control of RL. Our approach augments Proximal Policy Optimization (PPO) with a directional action-consistency regularization that softly aligns the RL agent's actions with VLA guidance during early training, without enforcing strict imitation, requiring demonstrations, or relying on continuous teacher queries. VLA guidance is applied sparsely and annealed over time, allowing the agent to adapt online and ultimately surpass the guiding policy. We evaluate VLAJS on six challenging manipulation tasks: lifting, pick-and-place, peg reorientation, peg insertion, poking, and pushing in simulation, and validate a subset on a real Franka Panda robot. VLAJS consistently outperforms PPO and distillation-style baselines in sample efficiency, reducing required environment interactions by over 50% in several tasks. Real-world experiments demonstrate zero-shot sim-to-real transfer and robust execution under clutter, object variation, and external perturbations.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.AI) 2026-06-17

Offline Preference-Based Trajectory Evaluation

作者:
Fernando Diaz↗

arXiv:2606.17541v1 Announce Type: cross Abstract: Offline evaluation of agentic systems often collapses trajectories to terminal success, discarding information about partial progress and inducing widespread ties, creating substantial statistical inefficiency by reducing effective sample size and weakening the ability to distinguish systems. We propose preference-based trajectory evaluation, which compares trajectories directly through temporal preferences over progress and time-to-return profiles. We find that, across diverse agentic and interactive benchmarks, standard success-based metrics produce tied comparisons on roughly 75% of instances, whereas trajectory-aware preferences reduce ties to roughly 35%, improving discriminative power, ranking stability, and data efficiency. Our results suggest that benchmark saturation, often attributed to poor data collection or problem difficulty, may also be explained by the choice of evaluation measure.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.AI) 2026-06-19

Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots

作者:
Khurram Javed↗Joseph Modayil↗Gloria Kennickell↗Richard S. Sutton↗John Carmack↗

arXiv:2606.19357v1 Announce Type: cross Abstract: We built a robot called the Robotroller that actuates an Atari CX40+ controller and a device called the Atari Devbox that renders the game frame and the reward signal from the Arcade Learning Environment on a screen. The Robotroller and the Atari Devbox, together with an off-the-shelf camera and a desktop computer, constitute a system that can be used to study reinforcement learning algorithms in the physical world. We call the full system Physical Atari. In this paper, we detail the key decisions that make Physical Atari a robust and accessible platform. To make the system robust, we designed the Robotroller so that all movement is done through bearings, which reduces wear. Additionally, we wrote software that monitors the state of the servos at a high frequency and intervenes to limit stress. To make the system accessible, we used affordable off-the-shelf components and parts that can be manufactured using consumer 3D printers. Physical Atari can be built for under $1,000 and has been used for weeks of non-stop reinforcement learning experiments without any mechanical failures. We used it to validate that reinforcement learning algorithms can learn directly on robots and show that even small distribution shifts between learning and deployment can significantly degrade the performance of policies. Our results underscore the importance of on-device adaptation for strong performance on robots.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.AI) 2026-06-12

LoRA-Muon: Spectral Steepest Descent on the Low-Rank Manifold

作者:
Franz Louis Cesista↗Katherine Crowson↗C\'edric Simal↗Stella Biderman↗

arXiv:2606.12921v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) significantly reduces compute and memory costs for finetuning Deep Learning models but is often harder to tune than dense training: when using factor-wise optimizers such as AdamW, it is sensitive to initialization choices, its optimal learning rates transfer poorly across ranks, and it often fails to beat dense baselines. We derive LoRA-Muon by applying the Muon optimizer's spectral steepest-descent rule to the low-rank setting. Along with our split weight-decay rule, our main claim is that LoRA-Muon is a good low-rank proxy for full-rank Muon and Shampoo-family optimizers. Its optimal learning rates transfer across rank, width, depth, and factor-rescaling. In our compute-matched TinyShakespeare study, a rank-$2$ proxy recovers the dense best tested learning rate, and a rank-$32$ LoRA-Muon run attains lower mean validation loss than the dense baseline in the seed-averaged sweep. We further show that the Spectron optimizer depends on arbitrary factor scaling, so it would likely be a poor fit when finetuning starts from badly imbalanced factors, and that LoRA-RITE's simplified QR-coordinate core implements the same spectral update. LoRA-Muon computes that update without QR-decomposition and avoids storing second moments, making it more accelerator-friendly and memory-efficient.

阅读与讨论 → 访问原文 →
23.
medRxiv (Medicine) 2026-06-11

Electrical signatures of divergent connectivity in the human subgenual cingulate cortex

作者:
Qianq↗Kerezoudis↗Gregg↗Hermes↗Klassen↗B. T↗Chari↗Tisdall↗M. M↗Baker↗M. R↗Miller↗…

Background: Major depressive disorder remains a leading cause of disability. While subgenual cingulate cortex (sgCC) deep brain stimulation (DBS) shows promise for medically refractory depression, clinical outcomes have been heterogeneous, suggesting that individual differences in neural circuitry engagement may critically influence therapeutic efficacy. We aimed to define the electrophysiological signatures of sgCC efferent connectivity using single-pulse electrical stimulation (SPES) with intracranial stereo-EEG (sEEG) to inform rational targeting and physiological biomarkers for sgCC-DBS. Methods: In four patients undergoing clinically indicated sEEG for seizure mapping, SPES was delivered through sgCC pairs, while distributed brain stimulation-evoked potentials (BSEPs) were recorded across cortical and subcortical sites. Responses were characterized using Canonical Response Parameterization to extract reproducible waveforms and per-trial reliability. Results: sgCC stimulation elicited reproducible, spatially organized BSEPs across frontal, limbic, and paralimbic networks, aligning with known anatomical pathways. Frontal recruitment featured robust, lateralized orbitofrontal activation favoring the ipsilateral central, medial OFC and bilateral ventromedial prefrontal responses. Limbic effects demonstrated bilateral cingulate activation with stronger ipsilateral recruitment and lateralized amygdala and hippocampal responses. Paralimbic engagement included insular responses with subject-specific anterior predominance and bi-hemispheric temporal-polar slow-wave deflections. Conclusion: These findings provide direct electrophysiological evidence of distributed, lateralized sgCC divergent network connectivity in the human brain, offering physiologic confirmation of its role in affective circuitry. The observed topography and laterality have direct applications for sgCC-DBS targeting and implicate BSEP signatures as candidate biomarkers to guide patient-specific therapy.

阅读与讨论 → 访问原文 →
24.
arXiv (math.PR) 2026-06-16

The distribution of the de Moivre experiment

作者:
Hac\`ene Belbachir↗Hamza Zeggada↗

arXiv:2606.15178v1 Announce Type: new Abstract: In this paper, we focus on de Moivre random experience which allows us to introduce the $ s- $Bernoulli distribution and the bi$ ^s $nomial distribution. We present some probabilistic properties such as the expectation, the variance, the skewness and kurtosis coefficients, the moments and the generating functions. Then we establish that for $ s\in\mathbb{N} $, the bi$ ^s $nomial distribution converges to a limiting Poisson and normal distributions when $ n\rightarrow\infty. $

阅读与讨论 → 访问原文 →
25.
arXiv (CS.CL) 2026-06-12

S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP

作者:
Mohammed Bouri↗Mohammed Erradi↗Adnane Saoud↗

Despite recent progress in Natural Language Processing (NLP), models remain vulnerable to word substitution attacks. Most existing defenses focus on first order sensitivity and measure how much the output changes when the input is slightly perturbed. However, they ignore how this sensitivity evolves, which is described by curvature. When gradients vary sharply, models can still fail. This paper introduces the Smooth Growth Bound Tensor (S-GBT), a second order method that bounds the Hessian element-wise, for which we provide formal theoretical proofs on the resulting robustness bounds. A regularization term is added during training to minimize these bounds. This yields tighter certified robustness against word substitution attacks. The change in the output under word substitution is bounded by both a linear term and a quadratic term. S-GBT is derived for two architectures: Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN). The method is integrated directly into the training objective. Its effectiveness is evaluated on multiple benchmark datasets. The results show that combining first and second order regularization improves certified robust accuracy by up to 23.4% compared to prior methods, while clean accuracy remains competitive. These findings indicate that controlling both the gradient and its variation is a promising direction for building more robust models.

阅读与讨论 → 访问原文 →