探索全球前沿学术脉络

01.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2606.14812

Joint convergence in Wiener chaos via transport hierarchy and Malliavin covariances

作者:

Ciprian A Tudor↗

arXiv:2606.14812v1 Announce Type: new Abstract: We study the joint convergence in distribution of a sequence $X_N = I_p(f_N)$ of multiple Wiener–Itô integrals of order $p\geq 2$ that converges to a Gaussian limit $Z\sim N(0,\sigma^2)$, together with another sequence $Y_N = I_q(g_N)$ converging in law. The central finding is that the joint convergence of $(X_N, Y_N)$ is completely governed by the asymptotic behavior of the iterated Malliavin covariances $Y_{r+1,N} = \langle DX_N, DY_{r,N}\rangle_H$, $r\geq 0$: joint convergence holds as soon as these covariances converge jointly with $Y_N$, and the structure of the limiting distribution is then explicitly determined by their limits. Moreover, the convergence of the Malliavin covariances is necessary for joint convergence, as shown by a counterexample. When $q

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2605.13217

GAGPO: Generalized Advantage Grouped Policy Optimization

作者:

Siyuan Zhu↗Chao Yu↗Rongxin Yang↗Zongkai Liu↗Jinjun Hu↗Qiwen Chen↗Yibo Zhang↗

arXiv:2605.13217v1 Announce Type: cross Abstract: Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents often receive sparse, trajectory-level rewards only at the end of an episode, making it difficult to determine which intermediate actions contributed to success or failure. As a result, propagating delayed outcomes back to individual decision steps without relying on costly auxiliary value models remains an open problem. We propose Generalized Advantage Grouped Policy Optimization (GAGPO), a critic-free reinforcement learning method for precise, step-aligned temporal credit assignment. GAGPO constructs a non-parametric grouped value proxy from sampled rollouts and uses it to compute TD/GAE-style temporal advantages, recursively propagating outcome supervision backward through time. Combined with group-wise advantage normalization and an action-level importance ratio, GAGPO extracts stable, localized optimization signals directly from multi-turn trajectories. Experiments on ALFWorld and WebShop show that GAGPO outperforms strong reinforcement learning baselines. Further analyses demonstrate faster early-stage learning, improved interaction efficiency, and smoother optimization dynamics, suggesting that GAGPO offers a simple yet effective framework for multi-turn agentic reinforcement learning.

阅读与讨论 → 访问原文 →

03.

bioRxiv (Bioinfo) 2026-06-21 DOI: HASH:1503ecc04840a6c2280666cc51cc7b31

OracleScreen-LILRB4: Machine Learning-Guided Discovery of Myeloid Immune Checkpoint Binders Validated in Patient-Derived Cells

作者:

Abdel-Rahman↗Gabr↗

The identification of small molecule modulators of immune checkpoint proteins remains a significant challenge in drug discovery due to the flat, featureless nature of protein-protein interaction interfaces and the characteristically low hit rates observed in conventional high-throughput screening campaigns. Here we report OracleScreen-LILRB4, an ensemble machine learning framework trained on quantitative biophysical screening data from two structurally diverse compound libraries (19,800 compounds total) screened against the myeloid immune checkpoint leukocyte immunoglobulin-like receptor B4 (LILRB4/ILT3). By formulating binding prediction as a regression task targeting continuous {Delta}Fnorm values rather than binary hit classifications, OracleScreen-LILRB4 achieved a mean Spearman R of 0.61 and ROC-AUC of 0.86 under scaffold-aware cross-validation. Prospective virtual screening of a 45,760-member compound library and experimental validation of the top 200 predictions yielded a 28.5% hit rate, representing a 15.0-fold enrichment over baseline, with 16 compounds demonstrating nanomolar-affinity LILRB4 (ILT3) engagement. Lead compounds ORS-22 and ORS-14 restored anti-tumor immune activity across patient-derived colorectal cancer and acute myeloid leukemia co-culture systems, reversing SCG2-mediated immunosuppression and recovering cytotoxic T-cell function. These findings establish OracleScreen-LILRB4 as an effective computational framework for accelerating small molecule discovery against non-enzymatic immune checkpoint targets.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2601.08010

CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation

作者:

Chaoyu Li↗Deeparghya Dutta Barua↗Fei Tao↗Pooyan Fazli↗

Vision-language models achieve strong performance across a wide range of multimodal understanding and reasoning tasks, yet their multi-step reasoning remains unstable. Repeated sampling over the same input often produces divergent reasoning trajectories and inconsistent final predictions. To address this, we introduce two complementary approaches inspired by test-time scaling: (1) CASHEW, an inference-time framework that stabilizes reasoning by iteratively aggregating multiple candidate trajectories into higher-quality reasoning traces, with explicit visual verification filtering hallucinated steps and grounding reasoning in visual evidence, and (2) CASHEW-RL, a learned variant that internalizes this aggregation behavior within a single model. CASHEW-RL is trained using Group Sequence Policy Optimization (GSPO) with a composite reward that encourages correct answers grounded in minimal yet sufficient visual evidence, while adaptively allocating reasoning effort based on task difficulty. This training objective enables robust self-aggregation at inference. Extensive experiments on 13 image understanding, video understanding, and video reasoning benchmarks show significant performance improvements, including gains of up to +26.2 percentage points on ScienceQA and +9.1 percentage points on EgoSchema.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19368

Neural Architectures as Functional Priors in Physics-Informed Control Problems

作者:

Sonia Rubio Herranz↗Fernando Carlos L\'opez Hern\'andez↗Antonio L\'opez Montes↗

arXiv:2606.19368v1 Announce Type: cross Abstract: In this work we investigate the role of neural architectures as implicit functional priors in control problems governed by ordinary differential equations. Rather than focusing on highly complex problems, our objective is to investigate architecture-dependent effects in controlled dynamical systems within the simplest physically interpretable settings possible. In particular, we study a controlled linear RLC electrical circuit and a nonlinear Duffing-type dynamical system. Both systems are analyzed first through classical optimal-control formulations and later through PINN-based approaches. We compare different combinations of multilayer perceptrons (MLPs) and Fourier-based KAN-like architectures, and analyze their influence on the resulting controls. The numerical experiments suggest that different architectural choices systematically generate qualitatively distinct controls, even under identical governing equations, loss functionals, initial and target states, training parameters and physical constraints. Significant differences appear in the spectral structure, smoothness, energy distribution, and phase-space behavior of the learned solutions. A central observation of this work is the emergence of a functional specialization phenomenon when the neural architectures are allowed sufficient freedom to shape the structure of the learned controls. More specifically, in the systems considered here, Fourier-based architectures tend to produce trajectories with richer oscillatory content, whereas smoother low-frequency-biased architectures tend to generate more regular and energetically efficient controls. This suggests that different functional components of the control problem may be handled more efficiently by different neural architectures, leading to an implicit specialization between state representation and control generation.

阅读与讨论 → 访问原文 →

06.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2606.14897

An Analytical Methodology for Quantifying Airspace Conflict Rate and Complexity

作者:

Andrew P. Kendall↗John-Paul Clarke↗

arXiv:2606.14897v1 Announce Type: cross Abstract: Air traffic growth, advanced air mobility, and increasingly autonomous operations are driving the need for scalable and adaptive airspace design methodologies. Central to this challenge is quantifying how traffic flow structure and demand, governed in part by airspace geometry, influence conflict generation and operational complexity. This paper presents an analytical framework for computing conflict rate and conflict probability in structured airspace using stochastic flow models. Traffic streams are modeled as renewal processes with prescribed inter-arrival time distributions, while interactions between flows are captured through geometry-dependent minimum spacing constraints at merges and crossings. Within this formulation, closed-form upper bounds on the expected conflict rate and conflict probability per aircraft are derived as functions of flow configuration and demand. These metrics are interpreted as complementary measures of airspace complexity, reflecting controller workload and per-aircraft operational risk. The methodology is applied to representative hexagonal cell geometries with varying routing structures and flow distributions. Results reveal non-monotonic tradeoffs between routing flexibility, capacity, and conflict generation, with intermediate flow configurations outperforming both highly constrained and highly distributed cases. The proposed framework provides a tractable tool for evaluating airspace design alternatives and complexity-informed traffic management strategies.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.10968

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

作者:

Renjie Mao↗Xiangxin Zhou↗Lvfang Tao↗Yixin Ding↗Yu Shi↗Yongguang Lin↗Yuheng Wu↗Honglin Zhu↗Qian Qiu↗Wenxi Zhu↗

arXiv:2606.10968v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, existing PPO-style trust-region mechanisms remain position-agnostic by enforcing uniform thresholds across all tokens independently. This pointwise treatment conflicts with autoregressive generation in two critical ways. First, uniform thresholds ignore autoregressive asymmetry. Early-stage deviations produce compounding sequence-level drift, causing static thresholds to under-regulate early divergence and excessively constrain late-stage exploration. Second, evaluating token-level divergence in isolation overlooks cumulative prefix drift, granting the same divergence allowance regardless of how far the conditioning history has already deviated from the rollout policy. To address this limitation, we propose CPPO (Cumulative Prefix-divergence Policy Optimization), a token-level masking rule that aligns updates with a finite-horizon policy-improvement bound via two coupled mechanisms. First, a position-weighted threshold imposes stricter limits at early positions whose effects persist longer, relaxing constraints for late-stage tokens. Second, a cumulative prefix budget tracks historical deviations, dynamically restricting further token-level deviation to prevent compounding errors along the prefix. Empirically, CPPO enhances training stability and significantly improves reasoning accuracy across various model scales.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.19279

NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learning

作者:

Daniel Romero Schellhorn↗Till Mossakowski↗Bj\"orn Gehrke↗

arXiv:2606.19279v1 Announce Type: new Abstract: Neurosymbolic semantics is fragmented: classical, fuzzy, probabilistic and neural systems each define truth by their own inductive rules. NeSyCat, extending ULLER, subsumes them under a single inductive definition of truth, parametric in a strong monad and an aggregation structure on truth-values. NeSyCat has so far lacked an account of predicates and functions learned by neural networks. We provide NeSyCat Torch as the missing link and interpret computational symbols via neural networks, implementing the framework in probabilistic programming and tensor-based backends. We use the distribution monad for reference semantics and metric evaluation, and complement it by a monad for numerically stable, differentiable training: the lazy log-tensor monad over the log-semiring. For efficient training in batches, we furthermore employ a batch monad. The axioms are the source code: written once in monad-based do-notation, monadic bind performs marginalisation, lazily pruning unneeded branches. On MNIST addition, our HaskTorch, JAX, and PyTorch implementations outperform LTN and DeepProbLog in speed and accuracy, while achieving nearly the accuracy of DeepStochLog. However, unlike DeepStochLog, we stay in a uniform framework that applies to many first-order NeSy approaches. Namely, the construction is parametric in the monad; instantiating it with, e.g., the Giry monad extends the approach to continuous probability (working out a neural representation here is left for future work).

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17122

TrustErase: Auditable Instant Machine Unlearning with Passport-Embedded Representations

作者:

Rutger Hendrix↗Leonardo G. Russo↗Concetto Spampinato↗Matteo Pennisi↗Giovanni Bellitto↗

arXiv:2606.17122v1 Announce Type: cross Abstract: The demand for privacy-compliant AI has amplified the need for machine unlearning; yet, existing retraining or distillation-based methods remain unverifiable and computationally costly. We introduce TrustErase, a verifiable, data-free unlearning framework leveraging passport-embedded representations for instant, modular, and auditable forgetting. By treating passports as cryptographic keys within parameter-efficient adaptation layers, TrustErase enables the removal of specific classes or datasets through simple deactivation, without retraining, fine-tuning, or access to the original data. A singular value based decomposition conceals passports within model weights, ensuring that unlearning actions remain transparent and provably compliant. Evaluations on MNIST, CIFAR10 and CIFAR100 show that TrustErase matches or exceeds state-of-the-art benchmarks such as DELETE, L2UL, and Boundary Shrink, while operating in a strictly data-free regime. Ultimately, TrustErase establishes a new paradigm for trustworthy, accountable, and instantly forgettable AI systems.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16023

IBAD: Interpretable Behavioral Anomaly Detection on Human Mobility Data

作者:

Bita Azarijoo↗John Krumm↗Cyrus Shahabi↗

arXiv:2606.16023v1 Announce Type: new Abstract: Human mobility appears highly diverse, yet much of a person's daily mobility can be explained by a small set of recurring behavioral templates, such as commuting, school-centered activities, caregiving, nightlife, or errand patterns. We present \texttt{IBAD} (\underline{I}nterpretable \underline{B}ehavioral \underline{A}nomaly \underline{D}etection), a framework that learns interpretable daily mobility templates and represents each individual as a distribution over mixtures of these templates. Rather than focusing on specific locations, IBAD characterizes activities that individuals perform across locations. This approach first discovers global behavioral templates using Latent Dirichlet Allocation (LDA), then employs a hierarchical self-supervised model to learn normal behavior of individuals from their soft behavioral templates. We also introduce a splicing benchmark that creates controlled behavioral mismatches between an individual's historical profile and injected mobility patterns. Experiments on real-world and synthetic datasets show that daily behavior can be effectively decomposed into a small number of interpretable templates. Crucially, we show that the learned behavioral archetypes transfer across distinct geographic and demographic contexts. Furthermore, IBAD maintains a robust competitive performance across all settings. For reproducibility purposes, the code is accessible at ~\href{https://github.com/USC-InfoLab/IBAD}{https://github.com/USC-InfoLab/IBAD}.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2602.21160

Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions

作者:

Mame Diarra Toure↗David A. Stephens↗

arXiv:2602.21160v3 Announce Type: replace-cross Abstract: In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), that cannot distinguish whether a model's ignorance involves a benign or safety-critical class. We decompose MI into a per-class vector $C_k(x)=\sigma_k^{2}/(2\mu_k)$, with $\mu_k{=}\mathbb{E}[p_k]$ and $\sigma_k^2{=}\mathrm{Var}[p_k]$ across posterior samples. The decomposition follows from a second-order Taylor expansion of the entropy; the $1/\mu_k$ weighting corrects boundary suppression and makes $C_k$ comparable across rare and common classes. By construction $\sum_k C_k \approx \mathrm{MI}$, and a companion skewness diagnostic flags inputs where the approximation degrades. After characterising the axiomatic properties of $C_k$, we validate it on three tasks: (i) selective prediction for diabetic retinopathy, where critical-class $C_k$ reduces selective risk by 34.7\% over MI and 56.2\% over variance baselines; (ii) out-of-distribution detection on clinical and image benchmarks, where $\sum_k C_k$ achieves the highest AUROC and the per-class view exposes asymmetric shifts invisible to MI; and (iii) a controlled label-noise study in which $\sum_k C_k$ shows less sensitivity to injected aleatoric noise than MI under end-to-end Bayesian training, while both metrics degrade under transfer learning. Across all tasks, the quality of the posterior approximation shapes uncertainty at least as strongly as the choice of metric, suggesting that how uncertainty is propagated through the network matters as much as how it is measured.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2604.13326

Right Regions, Wrong Labels: Semantic Label Flips in Segmentation under Correlation Shift

作者:

Akshit Achara↗Yovin Yahathugoda↗Nick Byrne↗Michela Antonelli↗Esther Puyol Anton↗Alexander Hammers↗Andrew P. King↗

The robustness of machine learning models can be compromised by spurious correlations between non-causal features in the input data and target labels. A common way to test for such correlations is to train on data where the label is strongly tied to some non-causal cue, then evaluate on examples where that tie no longer holds. This idea is well established for classification tasks, but for semantic segmentation the specific failure modes are not well understood. We show that a model may achieve reasonable overlap while assigning the wrong semantic label, swapping one plausible foreground class for another, even when object boundaries are largely correct. We focus on this semantic label-flip behaviour and quantify it with a simple diagnostic (Flip) that counts how often ground truth foreground pixels are assigned the wrong foreground identity while remaining predicted as foreground. In a setting where category and scene are correlated during training, increasing the correlation consistently widens the gap between common and rare test conditions and increases these within-object label swaps on counterfactual groups. Overall, our results motivate assessing segmentation robustness under distribution shift beyond overlap by decomposing foreground errors into correct pixels, flipped-identity pixels, and missed-to-background pixels. We also propose an entropy-based, ground truth label-free `flip-risk' score, which is computed from foreground identity uncertainty, and show that it can flag flip-prone cases at inference time. Code is available at https://github.com/acharaakshit/label-flips.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12382

SPEA2$^+$: Improved Density Estimation in SPEA2 with Provable Runtime Guarantees

作者:

Duc-Cuong Dang↗Andre Opris↗Dirk Sudholt↗

arXiv:2606.12382v1 Announce Type: cross Abstract: The Strength Pareto Evolutionary Algorithm 2 (SPEA2) is a popular and prominent evolutionary algorithm for solving multi-objective optimisation problems. Despite its popularity, theoretical analyses of SPEA2 have only appeared recently. Moreover, these analyses focus exclusively on how SPEA2 handles non-dominated solutions and disregard the algorithmic components responsible for handling dominated solutions. We conduct a first runtime analysis of SPEA2 for which these components are analysed. We prove that, unlike other prominent algorithms, including NSGA-II, NSGA-III and SMS-EMOA under the same setting of constant population size and duplicate elimination, SPEA2 is unable to cover the Pareto front of the OneTrapZeroTrap benchmark efficiently. Our results indicate that using k-th nearest-neighbour distance in the fitness assignment provides an insufficient signal to maintain diversity among dominated individuals. To address this issue, we propose an improved variant, SPEA2$^+$, that considers all pairwise distances. The new algorithm achieves the same performance guarantees as the other prominent algorithms on OneTrapZeroTrap, while matching the performance of the original SPEA2 on simpler problems. Experimental results complement our theoretical findings.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2602.00122

VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents

作者:

Hongzhu Yi↗Yujia Yang↗Yuanxiang Wang↗Tong Li↗Zhenyu Guan↗Tianyu Zong↗Jiahuan Chen↗Chenxi Bao↗Tiankun Yang↗Haopeng Jin↗Yixuan Yuan↗Xinming Wang↗…

In recent years, image editing models have made significant progress, enabling users to manipulate visual content in a flexible and interactive manner through natural language instructions. However, an important yet underexplored research direction remains dense visual document image editing, which involves modifying textual content within images while faithfully preserving the original text style and background context. Existing methods primarily focus on English scenarios and images with relatively sparse text, and thus cannot adequately address dense, structurally complex documents or non-Latin scripts such as Chinese. To bridge this gap, we propose VDE Bench (Visual Doc Edit Bench), a rigorously human annotated and evaluated benchmark specifically designed to assess the performance of image editing models on bilingual Chinese-English and complex visual document editing tasks. The benchmark comprises a high quality dataset of 942 instruction based image editing samples, whose seed images encompass dense Chinese and English text documents including academic papers, posters, presentation slides, examination materials, and newspapers. Furthermore, we introduce a novel evaluation framework that systematically quantifies editing performance at the OCR parsing level, thereby enabling fine grained assessment of text modification accuracy. Based on this benchmark, we conduct a comprehensive evaluation of representative image editing models. Human verification demonstrates a high degree of consistency between human judgments and automated evaluation metrics. VDE Bench constitutes the first systematic benchmark for evaluating the performance of image editing models on bilingual dense text visual documents.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18833

Seed-Guided Semi-Supervised Clustering by A-Contrario Anomaly Detection

作者:

Nassir Mohammad↗

arXiv:2606.18833v1 Announce Type: new Abstract: This paper introduces a semi-supervised clustering framework grounded in the statistical duality between grouping principles and anomaly detection. We address the challenge of robust cluster definition in noisy environments – a task where partitioning algorithms often over-assign outliers and density-based methods remain sensitive to heuristic global parameters. Drawing on a-contrario statistical reasoning and Gestalt proximity principles, we define a cluster as a maximal subset of data points containing no anomalies relative to a null hypothesis of uniform randomness. Central to this approach is the Perception algorithm, which utilises a principled expectation-based threshold ($\mathbb{E} < 1$) to identify outliers without manual parameter tuning. By treating clustering as the dual of anomaly detection, we employ an iterative ``clustering-by-exclusion'' mechanism. The algorithm is seed-guided, leveraging minimal user-provided labels to initialise robust cluster medians and form initial groups, which are subsequently expanded by admitting non-anomalous points. This approach naturally isolates fringe points, isolated noise, and emerging unknown clusters. We evaluate the method on synthetic and real-world benchmarks, including image and text datasets represented through raw, linear-reduced, and neighbourhood-preserving embeddings. Results demonstrate that with as few as 10–30 seeds per cluster, the proposed method achieves competitive and often very strong performance under a practical low-tuning benchmarking protocol, while maintaining linear scalability with respect to both observations and dimensionality for a fixed number of seeded clusters and iterations.

阅读与讨论 → 访问原文 →

16.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2410.18635

Path integral control of open quantum systems

作者:

Aar\'on Villanueva↗Hilbert Kappen↗

arXiv:2410.18635v4 Announce Type: replace Abstract: We investigate open-loop quantum state preparation for a class of open quantum systems whose dynamics follow a Gorini-Kossakowski-Lindblad-Sudarshan (GKLS) master equation that admits a trajectory-based stochastic representation. The deterministic control objective is reformulated as a stochastic optimal control problem – interpreting stochasticity as a methodological tool akin to stochastic Schrödinger equation unravelings – which situates the problem within the path integral control framework. For the class of GKLS generators under consideration, this reformulation leads to an explicit expression for the optimal control as a weighted average over stochastic quantum trajectories, thereby eliminating the need for gradient evaluations. Building on this theoretical result, we derive a control update rule for piecewise-constant control pulses and demonstrate that adaptive importance sampling progressively enhances the control estimator during optimization, culminating in the algorithm we term Path integral Quantum Control (PiQC). We further introduce an annealed variant of PiQC, wherein a synthetic noise schedule gradually steers open-system trajectories toward closed-system dynamics, enabling high-fidelity unitary state preparation. Numerical studies on a dissipative single-qubit system and a multi-qubit Nuclear Magnetic Resonance model verify that PiQC yields precise open-loop controls and displays robustness to Hamiltonian perturbations. We propose PiQC as a trajectory-based alternative to gradient-based approaches, which might offer a viable solution in quantum control problems where gradient computation is infeasible or computationally demanding.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2602.06014

Optimism Stabilizes Thompson Sampling for Adaptive Inference

作者:

Shunxing Yan↗Han Zhong↗

arXiv:2602.06014v2 Announce Type: replace-cross Abstract: Thompson sampling (TS) is widely used for stochastic multi-armed bandits, yet its inferential properties under adaptive data collection are subtle. Classical asymptotic theory for sample means can fail because arm-specific sample sizes are random and coupled with the rewards through the action-selection rule. We study adaptive inference for Thompson sampling with Gaussian randomized indices in $K$-armed stochastic bandits with independent sub-Gaussian reward noises, and identify optimism as a key mechanism for restoring stability, meaning that each arm's pull count concentrates around a deterministic scale. This stability yields asymptotically valid Wald inference despite adaptive sampling. First, we prove that variance-inflated TS is stable for any $K \ge 2$, including the challenging regime where multiple arms are optimal, with asymptotically uniform allocation over optimal arms and sharp logarithmic pull-count asymptotics for suboptimal arms. This resolves the $K$-armed extension question raised by \citet{halder2025stable}, using new winner-map and Lyapunov-drift techniques to control allocation among multiple optimal arms. Second, we analyze an alternative optimistic modification that keeps the Gaussian index variance unchanged but adds an explicit mean bonus to the index center, and establish a similar stability conclusion. In summary, suitably implemented optimism stabilizes Thompson sampling and enables asymptotically valid Wald inference in multi-armed bandits, while incurring only a mild additional regret cost.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2602.10635

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization

作者:

Keane Ong↗Sabri Boughorbel↗Luwei Xiao↗Chanakya Ekbote↗Wei Dai↗Ao Qu↗Jingyao Wu↗Rui Mao↗Ehsan Hoque↗Erik Cambria↗Gianmarco Mengaldo↗Paul Pu Liang↗…

arXiv:2602.10635v3 Announce Type: replace Abstract: Socially intelligent AI systems must reason across diverse human behavioral tasks and generalize to new social contexts. However, behavioral data is inherently heterogeneous, comprising diverse modalities and prediction targets that produce uneven training signals across samples, creating imbalanced learning dynamics that challenge existing AI models. To address this, we develop Omnisapiens-7B 2.0, a foundation model for social behavior processing that explicitly addresses learning from heterogeneous behavioral data. This is enabled through Heterogeneity-Aware Relative Policy Optimization, a new RL method that rebalances learning signals across samples by approximating each sample's contribution to the policy update and using these estimates to drive geometrically centered, inertially smoothed advantage modulation for stable training. Omnisapiens-7B 2.0 achieves the best and most consistent performance across 10 behavioral tasks, while also attaining the best performance on all five held-out benchmarks, with gains of up to +12.02% and +9.37% respectively. Furthermore, it demonstrates more consistent and interpretable reasoning traces, supporting reliable real-world behavioral applications. Our model is available at https://github.com/MIT-MI/human_behavior_atlas.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.18111

Learning Fair Pareto-Optimal Policies in Multi-Objective Reinforcement Learning

作者:

Umer Siddique↗Peilang Li↗Yongcan Cao↗

arXiv:2606.18111v1 Announce Type: cross Abstract: Fairness is an important aspect of decision-making in multi-objective reinforcement learning (MORL), where policies must ensure both optimality and equity across multiple, potentially conflicting objectives. While single-policy MORL methods can learn fair policies for fixed user preferences using welfare functions such as the generalized Gini welfare function (GGF), they fail to provide the diverse set of policies necessary for dynamic or unknown user preferences. To address this limitation, we formalize the fair optimization problem in multi-policy MORL, where the goal is to learn a set of Pareto-optimal policies that ensure fairness across all possible user preferences. Our key technical contributions are threefold: (1) We show that for concave, piecewise-linear welfare functions (e.g., GGF), fair policies remain in the convex coverage set (CCS), which is an approximated Pareto front for linear scalarization. (2) We demonstrate that non-stationary policies, augmented with accrued reward histories, and stochastic policies improve fairness by dynamically adapting to historical inequities. (3) We propose three novel algorithms, which include integrating GGF with multi-policy multi-objective Q-Learning (MOQL), state-augmented multi-policy MOQL for learning non-statoinary policies, and its novel extension for learning stochastic policies. We evaluate our algorithms across various domains and compare our methods against the state-of-the-art MORL baselines. The empirical results show that our methods learn a set of fair policies that accommodate different user preferences.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2601.21714

E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory

作者:

Kaixiang Wang↗Yidan Lin↗Jiong Lou↗Zhaojiacheng Zhou↗Bunyod Suvonov↗Jie Li↗

arXiv:2601.21714v5 Announce Type: replace Abstract: The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical integrity over extended horizons. However, prevalent memory preprocessing paradigms suffer from destructive de-contextualization. By compressing complex sequential dependencies into pre-defined structures (e.g., embeddings or graphs), these methods sever the contextual integrity essential for deep reasoning. To address this, we propose E-mem, a framework shifting from Memory Preprocessing to Episodic Context Reconstruction. Inspired by biological engrams, E-mem employs a heterogeneous hierarchical architecture where multiple assistant agents maintain uncompressed memory contexts, while a central master agent orchestrates global planning. Unlike passive retrieval, our mechanism empowers assistants to locally reason within activated segments, extracting context-aware evidence before aggregation. Evaluations on the LoCoMo benchmark demonstrate that E-mem achieves over 54\% F1, surpassing the state-of-the-art GAM by 7.75\%, while reducing token cost by over 70\%.

阅读与讨论 → 访问原文 →

21.

medRxiv (Medicine) 2026-06-18 DOI: HASH:fb11076d96d21564ba39a31feeb60958

A Brain-Aging Transcriptomic Signature Reclassifies WHO Glioma Grade and Predicts Survival Independently of IDH Status: A Multi-Cohort Study

作者:

Saadawy↗Khatan↗

Background Despite WHO grade and IDH status, significant survival differences remain in diffuse gliomas. We hypothesized that a brain-aging transcriptomic signature, reflecting neuroinflammation, myeloid infiltration, and synaptic loss, would independently predict survival and allow for molecular reclassification. Methods A neurodegeneration score was derived via PCA of brain MRI volumes from 1,057 OASIS-3 subjects and projected onto 888 TCGA-LGG/GBM (discovery) and 693 CGGA gliomas (validation). A 14-gene signature of glial/myeloid (GFAP, AQP4, TYROBP, TREM2, C1QA, CD68, ITGAM) and neuronal (SYP, DLG4, GRIN1, GRIA1, SNAP25, SYN1, RBFOX3) genes were computed. Elastic-net Cox regression identified a 3-gene panel (C1QA, CD68, GRIA1). Kaplan-Meier, multivariate Cox, decision curve, and single-cell RNA-seq analyses were performed. Results High brain-aging scores predicted poorer overall survival (p < 0.0001) and remained an independent prognostic factor after adjusting for WHO grade and IDH status (z = 4.72, p < 0.001); chronological age was non-significant (p = 0.231). In IDH-mutant gliomas, significance was confirmed in both cohorts (TCGA p = 0.027; CGGA p < 0.0001). Bidirectional reclassification showed high-risk Grade 2 tumors with Grade 3-like survival (p = 0.00089), and indolent Grade 3 tumors resembling Grade 2 by Ki-67. Single-cell RNA-seq confirmed macrophage localization of signature genes; DCA demonstrated net benefit over grade alone at 5-30% probability thresholds. Conclusions A brain-aging transcriptomic signature independently predicts glioma survival beyond WHO grade and IDH status, validated in an independent Chinese cohort, with clinical utility for identifying high-risk Grade 2 and sparing over-treatment of indolent Grade 3 tumors.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12251

Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization

作者:

Xinhai Zou↗Chang Zhao↗Alireza Aghabagherloo↗Dave Singel\'ee↗Robin Degraeve↗Bart Preneel↗

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.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14351

ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models

作者:

Dong Han↗Yong Li↗

With the advance of generative AI, the text-to-image (T2I) model has the ability to generate various contents. However, T2I models still can generate unsafe contents. To alleviate this issue, various concept erasing methods are proposed. However, existing methods tend to excessively erase unsafe concepts and suppress benign concepts contained in harmful prompts, which can negatively affect model utility. In this paper, we focus on eliminating unsafe content while maintaining model capability in safe semantic meaning interpretation by optimizing the concept erasing reward (CER) with reinforcement learning. To avoid overly content erasure, we introduce the Safe Adapter to project partial text embedding for efficient concept regulation in cross-attention layers. Extensive experiments conducted on different datasets demonstrate the effectiveness of the proposed method in alleviating unsafe content generation while preserving the high fidelity of benign images compared with existing state-of-the-art (SOTA) concept erasing methods. In terms of robustness, our method outperforms counterparts against red-teaming tools. Moreover, we showcase the proposed approach is more effective in emerging image-to-image (I2I) scenarios compared with others. Lastly, we extend our method to erase general concepts, such as artistic styles and objects. Disclaimer: This paper includes discussions of sexually explicit content that may be offensive to certain readers. All images used in this work are synthesized or from public datasets.

阅读与讨论 → 访问原文 →

24.

medRxiv (Medicine) 2026-06-16 DOI: HASH:ab56471947fac0fa36a1befa94423010

A MULTICENTER SWEDISH HISTOPATHOLOGY IMAGE DATASET OF PEDIATRIC CENTRAL NERVOUS SYSTEM TUMORS

作者:

NYMAN↗Tampu↗I. E↗Shamikh↗Prochazka↗Blystad↗Basmaci↗Diaz de Stahl↗Augustsson↗Zielinska-Chomej↗Cao↗von Salome↗…

Refined detection methods, more detailed tumor characterization, and adequate distinction between different pediatric tumor subtypes are necessary to improve diagnosis and treatment, enable precision medicine, and advance patient prognosis. However, the application of computational approaches to pediatric brain tumors remains limited, largely due to the lack of accessible datasets. To address part of this gap, we provide whole slide images (WSIs) of hematoxylin and eosin (H&E)-stained tissue sections from all pediatric central nervous system (CNS) samples collected in Sweden between 2013 and 2023. These data represent a population-based national cohort encompassing all six pediatric oncology centers in Sweden and are available through the Swedish Childhood Tumor Biobank (BTB). The dataset includes 1,446 WSIs of sufficient image quality with confirmed CNS tumor diagnoses, derived from 537 unique subjects (562 cases). In addition, diagnosticrelevant clinical information is included. Corresponding whole-genome sequencing (WGS), wholetranscriptome sequencing (WTS), and methylation array data are available for most tumor samples through separate resources. This H&E dataset has been specifically curated to support artificial intelligence-based analyses, while also serving broader applications in medical research and education. When combined with matched molecular data, it provides a valuable resource for advancing multimodal and precision diagnostic approaches in the pediatric population. Refined detection methods, more detailed tumor mapping and adequate distinction between different subtypes of pediatric tumors are necessary to improve treatment, enable precision medicine and improve patient prognosis. Application of computational algorithms for pediatric brain tumors is very limited mainly due to the unavailability of pediatric histology brain tumor data sets. To enable the development of AI models comprehensive datasets covering a wide range of pediatric brain tumors are needed.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2509.24894

Improved Stochastic Optimization of LogSumExp

作者:

Egor Gladin↗Alexey Kroshnin↗Jia-Jie Zhu↗Pavel Dvurechensky↗

arXiv:2509.24894v4 Announce Type: replace-cross Abstract: The LogSumExp function, dual to the Kullback-Leibler (KL) divergence, plays a central role in many important optimization problems, including entropy-regularized optimal transport (OT) and distributionally robust optimization (DRO). In practice, when the number of exponential terms inside the logarithm is large or infinite, optimization becomes challenging since computing the gradient requires differentiating every term. We propose a novel convexity- and smoothness-preserving approximation to LogSumExp that can be efficiently optimized using stochastic gradient methods. This approximation is rooted in a sound modification of the KL divergence in the dual, resulting in a new $f$-divergence called the Safe KL divergence. Our experiments and theoretical analysis of the LogSumExp-based stochastic optimization, arising in DRO and continuous OT, demonstrate the advantages of our approach over existing baselines.

阅读与讨论 → 访问原文 →