Academic Intelligence · Curated Daily

探索全球前沿学术脉络

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

01.
arXiv (CS.CV) 2026-06-11

Plan-and-Verify Video Reward Reasoning with Spatio-Temporal Scene Graph Grounding

Reward models for text-to-video (T2V) generation guide post-training but often fail at fine-grained semantic alignment. We trace this to two structural weaknesses in existing reasoning-based reward models: they do not systematically verify every condition described in the prompt, and the visual evidence supporting each judgment remains implicit in their free-form reasoning. We propose SG-PVR, a video reward model that addresses these limitations through plan-and-verify reasoning grounded in spatio-temporal scene graphs. The verification plan decomposes the prompt into atomic claims, ensuring every requirement is checked. The spatio-temporal scene graph, encoding entities, attributes, and temporally-grounded relations, is extracted from the video and maintained as a persistent structured visual reference throughout reasoning. Each claim is verified against both the video and the scene graph, anchoring judgments in explicit visual evidence. SG-PVR achieves strong performance on semantic alignment, including fine-grained temporal semantics. As a test-time reranker, it further enhances compositional alignment in T2V generation.

02.
arXiv (CS.CV) 2026-06-15

Spectrum Aware Illumination Estimation Using Multispectral Image

Multispectral (MS) imaging extends beyond conventional RGB imaging by capturing more spectral bands, thereby improving illuminant spectrum estimation (ISE). However, existing methods often fail to fully exploit spectral information, resulting in suboptimal performance under diverse lighting conditions and across different sensor domains. Hence, we propose a deep learning framework with a spatio-spectral feature extraction block, which incorporates spectral attention mechanisms to enhance spectral correlation and preserve illuminant-relevant spatial features. Through the inclusion of an illuminant prior (IP), our approach prioritizes specific channels that provide more meaningful information in an MS image. We also propose a spectral-domain transform across different MS sensor spaces. The results demonstrate that illuminant spectra learned in high-dimensional sensor spaces can be effectively transformed to various lower-dimensional camera sensor spaces without any additional training. To facilitate evaluation, we introduce a real-world MS dataset containing high-dimensional ground-truth illumination spectra captured under diverse lighting conditions. Through extensive experiments, we demonstrate that our method achieves superior accuracy compared to existing models, thus providing a practical solution for real-world ISE. The code and dataset are available at https://github.com/hyejin5/Spectrum-Aware-Illumination-Estimation-Using-Multispectral-Image.

03.
arXiv (CS.CV) 2026-06-24

SER: Learning to Ground Video Reasoning with Semantic Evidence Rewards

Video MLLMs often struggle with fine-grained spatio-temporal reasoning, sometimes generating correct answers based on irrelevant frames or objects. Although outputting spatio-temporal evidence during reasoning is a promising direction, existing RL frameworks typically rely on geometry-only (IoU) rewards, which can be sensitive to boundary perturbations and overlook semantic alignment. To address this, we propose Semantic Evidence Reward (SER), which reformulates spatio-temporal evidence grounding as a constrained verification task. Instead of computing pixel-level overlap, SER uses a referee VLM as a local checker to evaluate model-generated evidence claims across two dimensions: relevance and localization quality, combined with a temporal penalty. This design reduces the reliance on dense box annotations and enables training directly on standard video QA data. On the V-STAR benchmark, SER achieves 49.6% mLGM, improving by 3.0 points over the strong evidence-grounded baseline Open-o3-Video, demonstrating its potential in enhancing both answer accuracy and evidence grounding.

04.
arXiv (CS.AI) 2026-06-25

Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound

arXiv:2606.25978v1 Announce Type: cross Abstract: Multi-agent goal recognition asks an observer to jointly infer which agents act together and what each team is trying to achieve, so the hypothesis space grows combinatorially with the number of team partitions and goals per team. Real applications such as drone surveillance and collaborative robotics expose only the agents' trajectory, which forces the observer to rank team-goal hypotheses from behavior alone. Multi-Agent Goal Recognition with Branch-and-Bound (MAGR-BB) addresses this setting with a shared team- and goal-conditioned policy used as the scoring model inside a factorized branch-and-bound search. On a controlled multi-agent Blocksworld benchmark, MAGR-BB returns the same top-ranked hypothesis as exhaustive search throughout the trajectory while cutting hypothesis materialization by orders of magnitude and reducing cumulative recognition runtime substantially.

05.
arXiv (CS.LG) 2026-06-16

When to use what Schatten-$p$ norm in deep learning?

arXiv:2606.15268v1 Announce Type: new Abstract: Schatten-$\infty$ based optimizers such as Muon have shown promising empirical performance, but there remains seemingly conflicting observations regarding whether they are beneficial. We resolve this conflict by showing that the conclusion is regime dependent. Even when the objective is smooth in the Schatten-$\infty$ geometry, smaller Schatten-$p$ geometries can be optimal, specifically in the low-dimensional regime, which we show includes Chinchilla scaling. This conclusion follows from a new noise-robust acceleration result for the SODA framework for $p>2$. The same analysis explains why Muon-like methods do not require warmup, why they naturally favor large batches, and yields a batch size scaling rule for arbitrary $p$.

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

Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization

arXiv:2606.12251v1 Announce Type: cross Abstract: Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently optimize adversarial perturbations. To address this, we investigate whether reinforcement learning (RL) training can disrupt the gradient structure used by attackers by training image classifiers with policy-gradient objectives and epsilon-greedy exploration. Through systematic experiments across CIFAR-10, CIFAR-100, and ImageNet-100 with multiple architectures, we find that RL-trained classifiers significantly disrupt gradient-based adversarial optimization. To explain this, we conduct a comprehensive mechanism analysis using loss landscape visualization, static and dynamic gradient indicators, and predictive entropy. Our analysis reveals that RL acts as an implicit regularizer, producing models with highly unstable gradient directions and smaller gradient magnitudes. This combination makes each PGD step both unreliable in direction and limited in magnitude, causing gradient-based attacks to fail within practical iteration budgets. We further show that combining RL with adversarial training (RL-adv) provides a dual-layer defense operating at two complementary levels: RL degrades gradient information available to attackers (gradient-level defense), while adversarial training strengthens decision boundaries (boundary-level defense). RL-adv achieves the highest robustness across all major attack types evaluated, including gradient-based (PGD, AutoAttack), transfer-based, and query-based attacks, outperforming SL-adv by a significant margin. These findings identify RL-induced gradient disruption as a complementary robustness mechanism and motivate future research on hybrid SL-RL training schedules that combine SL's efficiency with RL's gradient-regularization properties.

07.
medRxiv (Medicine) 2026-06-22

MinderCare: protocol for a mixed-methods evaluation of a digitally enabled dementia care service.

Introduction and aims Dementia is a growing public health challenge affecting millions of people worldwide. It is a progressive condition that increases the risk of infections, falls, hospital admissions, dependence in activities of daily living, safety issues such as wandering, care home transfers, and death. New ways of supporting people living with dementia (PLWD) at home are urgently needed. We describe the MinderCare study which evaluates a digitally enabled care model that integrates low-burden sensor-based remote monitoring within a nurse-led clinical service. Methods and analysis In this mixed-methods study, we will recruit 100 people with confirmed or suspected dementia living at home and deploy the Minder remote monitoring system for at least 12 months. A detailed characterisation of the cohort will be obtained, including cognition, frailty, participant and carer wellbeing, functioning, and quality of life. The feasibility, acceptability, sustainability, and resource requirements of the service will also be assessed. Low-cost sensors provide information about behaviour, environment and physiology from the home. Machine-learning algorithms have been used to develop digital biomarkers of infection, sleep, night-time behaviours, daily activities and routines, and the effects of clinical events and treatment. These will be assessed through clinical reports of sensor-derived data that include anomaly alerts provided to the clinical teams. Algorithms will be assessed for their clinical utility and acceptability. The comparative-effectiveness component will be designed as a target trial emulation using linked electronic health-record data to construct a time-indexed external usual-care control cohort. The primary comparative outcome will be Days Alive and Out of Hospital (DAOH) over 12 months from the activation-index date, with healthcare utilisation, costs, institutionalisation and mortality assessed as secondary outcomes. DAOH and estimated MinderCare effects will also be examined across prespecified strata of baseline inpatient utilisation. Ethics and dissemination Ethical approval has been granted by the North East Newcastle and North Tyneside 2 Research Ethics Committee, and the study has received confirmation of capacity and capability by the Imperial College Healthcare NHS Trust. Study findings will be disseminated to patients, health and social care professionals, and policymakers through peer-reviewed publications and conference presentations. Study registration number: ISRCTN14997677 and NIHR portfolio CPMSID 63023.

08.
arXiv (quant-ph) 2026-06-25

The Cost of Removing Tunability in Quantum Data Re-Uploading

arXiv:2606.25598v1 Announce Type: new Abstract: Fixed encoding data re-uploading quantum circuits provide a striking example of universality emerging from a highly constrained architecture. However, universality alone is insufficient for assessing the theoretical and practical value of fixed and tunable upload circuits. The resource cost of removing tunability remains poorly understood. In this work, we establish quantitative depth-error scaling for approximating tunable upload circuits with fixed upload circuits. We show that a tunable upload circuit can be approximated by a fixed upload circuit using depth \( D = O_\sigma\!\left[(\log(1/\varepsilon))^\sigma\right] \) for every \(\sigma>1\), with a target dependent constant overhead, thereby improving the previously known polynomial dependence on \(1/\varepsilon\) with the same overhead. Our proof is based on an auxiliary extension approximation mechanism that combines Gevrey class construction, Jackson's theorem and generalized quantum signal processing theorem. Thus, the expressive power lost by removing tunability can be recovered using only polylogarithmic growth in circuit depth with a target dependent constant overhead. We further identify a periodic mismatch obstruction intrinsic to fixed upload approximations and use Turán-Nazarov inequalities to prove logarithmic lower bounds \( D = \Omega(\log(1/\varepsilon)) \) for the approximation of mismatch class target tunable upload circuits. Conceptually, our analysis reveals two structural mechanisms underlying approximation in fixed upload architectures: auxiliary extensions and mismatch obstructions. These results provide a quantitative understanding of how expressivity is transferred from tunable frequencies into circuit depth, and suggest a broader framework for studying approximation complexity in quantum signal processing and related quantum learning models.

09.
arXiv (CS.AI) 2026-06-16

Optimizing Health Coverage in Ethiopia: A Learning-augmented Approach and Persistent Proportionality Under an Online Budget

arXiv:2509.00135v2 Announce Type: replace Abstract: As part of nationwide efforts aligned with the United Nations' Sustainable Development Goal 3 on Universal Health Coverage, Ethiopia's Ministry of Health is strengthening health posts to expand access to essential healthcare services. However, only a fraction of this health system strengthening effort can be implemented each year due to limited budgets and other competing priorities, thus the need for an optimization framework to guide prioritization across the regions of Ethiopia. In this paper, we develop a tool, Health Access Resource Planner (HARP), based on a principled decision-support optimization framework for sequential facility planning that aims to maximize population coverage under budget uncertainty while satisfying region-specific proportionality targets at every time step. We then propose two algorithms: (i) a learning-augmented approach that improves upon expert recommendations at any single-step; and (ii) a greedy algorithm for multi-step planning, both with strong worst-case approximation estimation. In collaboration with the Ethiopian Public Health Institute and Ministry of Health, we demonstrated the empirical efficacy of our method on three regions across various planning scenarios.

10.
arXiv (CS.LG) 2026-06-15

Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success

arXiv:2606.14560v1 Announce Type: cross Abstract: Non-Euclidean optimisation methods with matrix-valued updates, such as Muon and Scion, have recently shown strong empirical performance for training Transformer models, yet their theoretical advantages over Euclidean methods remain poorly understood. We address this gap in the heavy-tailed non-convex regime, where stochastic gradients have bounded $p$-th central moments, $p \in (1,2]$. We show that certain non-Euclidean methods achieve optimal sample complexity under stronger stationarity measures, while Euclidean methods incur additional dimension-dependent costs. As a consequence, for $m \times n$ matrices, Muon finds an $\varepsilon$-stationary point in nuclear norm within $\mathcal{O}\left(\min\{m, n\} \frac{\Delta_1 L}{\varepsilon^2} \left(\frac \sigma \varepsilon \right)^{\frac p {p-1}}\right)$ samples, absorbing heavy-tailed noise without extra dimension dependence, unlike Euclidean methods. We further prove this sample complexity, including its dimension dependence, is optimal for all first-order methods under nuclear-norm stationarity. Experiments on large language models support our theory. Surprisingly, our results suggest that other Schatten geometries beyond the spectral geometry of Muon can perform competitively in certain settings.

12.
arXiv (CS.CL) 2026-06-16

LLM Judges Have Dark Current: A Psychometric Datasheet for LLM-as-a-Judge Evaluation

LLM-as-a-judge systems are now routinely used for open-ended model evaluation, where human preference annotation is costly, slow, and difficult to reproduce. Yet these judges are often reported as scalar accuracy, win-rate, or agreement devices. We argue that a judge should instead be reported as a measurement instrument. We introduce a Judge Datasheet protocol that measures dark current under true-vacuum inputs, stable cross-sensitivity to same-quality surface variation, positional false preference, target sensitivity on a controlled quality ladder, and the criterion or operating point induced by tie instructions. The direction-stability decomposition reveals that apparent Delta0 preference can be stable surface response or disguised position bias. In a three-judge open-weight case study, Llama-3.1-8B shows high dark current and presentation-conflicted Delta0 behavior, Qwen2.5-14B is vacuum-clean and target-sensitive but mixes stable and positional over-discrimination, and Qwen2.5-32B is vacuum-clean with low stable cross-sensitivity and low positional false preference. A strict tie criterion eliminates Qwen32B Delta0 false preference but absorbs marginal Delta1 target signals into ties while preserving Delta5 sensitivity. The results show that prompting moves the criterion, not the resolution. We do not claim that the downstream mechanism hypothesis that motivated this work is confirmed; the contribution is a metrological protocol for measuring the measuring device before downstream claims are made.

13.
arXiv (quant-ph) 2026-06-11

Quantum thermodynamics, quantum correlations and quantum coherence in accelerating Unruh-DeWitt detectors in both steady and dynamical state

arXiv:2512.18123v2 Announce Type: replace Abstract: We investigate the interplay between quantum thermodynamics, quantum correlations, and quantum coherence within the framework of the Unruh-DeWitt (UdW) detector model. By analyzing both the steady and dynamical states of various quantum resources (including steerability, entanglement, quantum discord, and coherence), we study how these resources evolve under Markovian and non-Markovian environments. Furthermore, we investigate the impact of both the Unruh temperature and the energy levels on three key quantum phenomena: thermodynamic evolution, quantum correlations, and quantum coherence, considering different initial state preparations. The hierarchical structure relating quantum correlations and quantum coherence is determined. We further examine the thermodynamic performance of a quantum heat engine, highlighting the influence of memory effects and classical correlations on heat exchange, work extraction, and efficiency. Our results reveal that non-Markovian dynamics can enhance the preservation of quantum correlations and improve the engine's efficiency compared to purely Markovian regime. These findings provide insights into the role of quantum correlations and quantum coherence in quantum thermodynamic processes and open avenues for optimizing quantum devices operating in relativistic or open-system settings.

14.
arXiv (CS.LG) 2026-06-24

Asymptotic Signal Subspace Recovery in Softmax Attention Models

arXiv:2606.22406v2 Announce Type: replace Abstract: Attention mechanisms have demonstrated remarkable empirical success in identifying relevant information from large collections of tokens, yet the theoretical principles underlying this behavior remain poorly understood. We study a stylized softmax-attention model in which a query vector is learned by stochastic gradient ascent from a collection of informative and nuisance tokens. Exploiting the symmetry of the model, we derive a population objective and characterize the limiting ordinary differential equation governing the learning dynamics. Using tools from stochastic approximation and dynamical systems theory, we establish a rigorous connection between the stochastic learning algorithm and its deterministic limit. Our main result shows that, under suitable high-dimensional scaling assumptions and standard step-size conditions, the learned query converges almost surely to the one-dimensional signal subspace spanned by the latent informative direction. Equivalently, the query asymptotically recovers the latent signal up to the intrinsic sign ambiguity. These results provide a rigorous theoretical foundation for understanding attention mechanisms as signal extraction procedures in high-dimensional noisy environments and offer a dynamical-systems perspective on how attention discovers relevant information in the presence of substantial noise.

15.
arXiv (CS.CL) 2026-06-18

Towards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise Applications

Large language model (LLM)-based multi-agent systems demonstrate strong performance on complex reasoning and task execution, enabling broad enterprise applications. However, production deployment remains challenging due to domain-specific customization requirements and high latency and inference costs in agentic workflows. We propose a unified framework for customization and efficient deployment of multi-agent systems in real-world settings. The first stage, Agentic Model Customization, combines continual pretraining, supervised fine-tuning, and preference optimization to adapt a compact model to specialized domains while retaining strong agentic capabilities. The second stage, Inference Optimization, integrates speculative decoding and FP8 quantization with targeted calibration to enable cost-efficient serving with minimal quality loss. Across enterprise workloads, our framework enables rapid domain adaptation and achieves a 4.48x speedup in throughput while maintaining performance and improving robustness on long-tail scenarios.

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

Stochastic trace estimation with tensor train random vectors

arXiv:2606.15679v1 Announce Type: cross Abstract: Stochastic trace estimation is a standard tool for approximating the trace of a large-scale matrix available only through matrix-vector products. However, in tensor-structured settings, unstructured Gaussian or Rademacher test vectors may be prohibitively expensive to store and compute with, while cheaper rank-one tensor-product vectors can require sample complexities that grow exponentially with the tensor order. This work studies Gaussian random tensor train vectors as a structured alternative for stochastic trace estimation. We show that, with a suitable choice of the tensor train rank, random tensor train vectors recover dimension-independent guarantees for the Girard–Hutchinson estimator. In particular, a median-of-means variant with tensor train rank $r \geq d-1$ achieves the same dependence on the accuracy $\varepsilon$ and failure probability $\delta$ as the classical estimator based on unstructured Gaussian vectors. We further prove an oblivious subspace injection result for sketches formed from independent Gaussian random tensor train vectors: tensor train rank $r\geq d-1$ and $\mathcal{O}(\varepsilon^{-2}(k+\log(1/\delta)))$ samples suffice for a $k$-dimensional target subspace. Finally, we investigate the use of such sketches within the Nystr\"{o}m++ framework. We show that the resulting estimator can achieve the desired $\mathcal{O}(\varepsilon^{-1})$ sample complexity under an additional spectral-tail condition. These results provide clarififcation on both the potential and the limitations of random tensor train vectors in stochastic trace estimation.

17.
arXiv (CS.AI) 2026-06-11

Forecasting Future Behavior as a Learning Task

arXiv:2606.11445v1 Announce Type: new Abstract: Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs. For large reasoning models (LRMs), this conventional route is particularly difficult to follow: explanation methods for single token generations do not naturally generalize to long trajectories, and the trajectories themselves are often not faithful when read as natural language. We propose an alternative that bypasses the explanation step: treat behavior forecasting as a learnable task and train Behavior Forecasters that operates on a single reasoning trajectory to make the same forecasts one would typically seek from an explanation. The forecaster's training data is obtained by querying the LRM with no human annotation, and its inference is done in a single forward pass. We instantiate this approach on two tasks: how likely the LRM is to repeat its answer on re-runs, and how removing parts of the input changes its answer. We evaluate this approach on both tasks across three diverse reasoning datasets and find that trained Behavior Forecasters are more accurate than GPT-5.4 and Claude Opus-4.6 reading the same trajectories as naive readers, at a small fraction of their inference cost. We find that fine-tuning the backbone end-to-end and initializing it from the target LRM are each necessary for strong performance. These results show that the reasoning trajectory carries information about the LRM's future behavior that goes beyond what naive reading conveys.

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

GLARE: A Natural Language Interface for Querying Global Explanations

arXiv:2606.19735v1 Announce Type: new Abstract: While global explanations are crucial for understanding vision models across datasets, classes, and decision contexts, their complex and monolithic nature often hinders practical exploration. Because users typically seek targeted answers to specific questions rather than static artifacts, we present an LLM-based interactive interface that provides natural language access to global explanations for black-box image classifiers. The system's core LLM acts as a mediator, translating natural language questions into structured SQL queries over local explanation data. This enables flexible aggregation without exposing users to low-level representations. For each query, the interface outputs statistics-augmented natural language responses, supporting local explanations, and intent-aligned visualizations. We evaluate the system on intent interpretation, query mapping accuracy, generalization to novel queries and datasets, and robustness to linguistic errors. Our results demonstrate that LLM-mediated querying substantially improves the accessibility and usability of global explanations for human-centered XAI.

19.
arXiv (CS.CL) 2026-06-16

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving

Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas. However, their effectiveness in complex mathematical reasoning involving multi-step FOL deductions is still under-researched. While LLMs perform competitively on established mathematical reasoning benchmarks, they struggle with multi-step FOL tasks, as demonstrated by Deepseek-Prover-V2-7B's low accuracy (4.2%) on our proposed theorem proving dataset. This issue arises from the limited exploration of diverse proof strategies and the potential for early reasoning mistakes to undermine entire proofs. To address these issues, we propose DREAM, a self-adaptive solution that enhances the Diversity and REAsonability of LLMs' generation strategies. DREAM incorporates an Axiom-Driven Strategy Diversification mechanism to promote varied strategic outcomes and a Sub-Proposition Error Feedback to help LLMs reflect on and correct their proofs. Our contributions include pioneering advancements in LLMs' mathematical reasoning through FOL theorem proving, introducing a novel inference stage solution that improves performance by 0.6% to 6.4%, and providing a curated dataset of 447 mathematical theorems in Lean 4 format for evaluation.

20.
arXiv (CS.LG) 2026-06-17

From Drift to Coherence: Stabilizing Beliefs in LLMs

arXiv:2606.17832v1 Announce Type: new Abstract: Large language models (LLMs) are often hypothesized to perform implicit Bayesian inference, yet a key coherence condition, the martingale property of predictive beliefs, has been shown to fail in controlled synthetic in-context learning settings. We revisit this question in a more typical usage regime: generic multiple-choice question answering. Exploiting the discrete answer space, we compute exact predictive distributions and study belief dynamics induced by autoregressive answer resampling. We introduce prompted predictive resampling (PPR), where an LLM generates a sequence of answers to the same question. Empirically, PPR reveals early-stage belief drift, indicating martingale violations. However, after sufficient resampling steps, the belief process self-stabilizes and converges to a coherent predictive distribution. Based on this observation, we further propose (i) a seed-answer prompting strategy to accelerate stabilization, and (ii) a self-consistency loss that amortizes early-stage drift into the model via fine-tuning. Experiments on multiple-choice QA benchmarks show that our methods substantially reduce belief drift and improve predictive coherence without sacrificing accuracy.

21.
arXiv (CS.LG) 2026-06-16

Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data

arXiv:2502.19544v3 Announce Type: replace Abstract: Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online RL by leveraging abundant non-curated data that is reward-free, of mixed quality, and collected across multiple embodiments. Although learning a world model appears promising for utilizing such data, we find that naive fine-tuning fails to accelerate RL training on many tasks. Through careful investigation, we attribute this failure to the distributional shift between offline and online data during fine-tuning. To address this issue and effectively use the offline data, we propose two techniques: i) experience rehearsal and ii) execution guidance. With these modifications, the non-curated offline data substantially improves RL's sample efficiency. Under limited sample budgets, our method achieves nearly twice the aggregate score of learning-from-scratch baselines across 72 visuomotor tasks spanning 6 embodiments. On challenging tasks such as locomotion and robotic manipulation, it outperforms prior methods that utilize offline data by a decent margin.

22.
arXiv (CS.LG) 2026-06-16

A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization

arXiv:2606.16154v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning, but GRPO-style optimization remains prone to collapse. We analyse this instability through token-level gradient dynamics, deriving a taxonomy that predicts how updates affect next-token probabilities and entropy. The taxonomy shows that stability depends jointly on the advantage sign and token distribution under the current policy. Motivated by this finding, we propose Winner Advantage Policy Optimization (WAPO), a simple online clipped policy-gradient objective that updates only on positive-advantage completions. Across mathematical reasoning and multi-hop QA benchmarks, WAPO improves training stability and matches or outperforms baselines across multiple model families. Full code can be found at https://github.com/layer6ai-labs/wapo.

23.
Nature Medicine 2026-06-15

Activity-dependent adaptive deep brain stimulation improves gait in Parkinson’s disease

Parkinson’s disease leads to a spectrum of locomotor deficits that vary in severity with the nature of daily activities and the fluctuating physiology of patients. Many of these deficits remain inadequately addressed by existing deep brain stimulation therapies that rely on activity-agnostic parameters optimized for cardinal motor symptoms. By contrast, therapies embedding activity-specific parameters have the potential to better address the entire range of symptoms. Here we expose physiological principles that enable real-time decoding of ongoing locomotor activities across motor fluctuations from the neural dynamics of the subthalamic nucleus. This decoding steered activity-dependent adaptations of deep brain stimulation therapies that improved locomotor deficits while preserving efficacy for cardinal motor symptoms across activities of daily living. Our activity-dependent framework provides a blueprint for next-generation neuromodulation therapies that continuously select parameters optimized to the behavioral context and fluctuating physiology of each patient. ClinicalTrials.gov registration NCT06791902 . Neural decoding algorithms that leverage physiological principles of locomotor encoding support activity-dependent deep brain stimulation therapies that improve locomotor deficits in people with Parkinson’s disease.

24.
bioRxiv (Bioinfo) 2026-06-13

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

作者:

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.

25.
arXiv (CS.CV) 2026-06-12

MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models

World Action Models (WAMs) present a promising paradigm for robotic control via video prediction. However, current WAMs suffer from fundamental spatial bottlenecks: standard text inputs introduce referential ambiguity in cluttered scenes, while unstructured RGB predictions lack semantic grounding and remain biased by task-irrelevant backgrounds. To overcome these limitations, we introduce MaskWAM, an object-centric world-action model. By jointly integrating masks as both explicit inputs and predictions via a unified Mixture of Transformers (MoT), MaskWAM unlocks robust policy generalization. This design provides two key benefits: (1) predicting future masks yields object-centric semantic supervision that suppresses visual noise, significantly enhancing even standard text-conditioned WAMs; and (2) coupling this predictive supervision with first-frame visual prompts, such as target object masks, establishes a precise spatial anchor that substantially reduces language ambiguity. Crucially, as WAMs are inherently vision-driven architectures, direct mask conditioning yields substantially stronger guidance than text alone, establishing a precise and robust paradigm for manipulating unseen objects. Evaluations on LIBERO, RoboTwin, and real-world tasks demonstrate that MaskWAM significantly outperforms baselines in both language-clear and language-ambiguous tasks.