Recent advances have significantly improved our understanding of the generalization performance of gradient descent (GD) methods in deep neural networks. A natural and fundamental question is whether GD can achieve generalization rates comparable to the minimax optimal rates established in the kernel setting. Existing results either yield suboptimal rates of O(1/ n), or focus on networks with smooth activation functions, incurring exponential dependence on network depth L. In this work, we establish optimal generalization rates for GD with deep ReLU networks by carefully trading off optimization and generalization errors, achieving only polynomial dependence on depth. Specifically, under the assumption that the data are NTK separable from the margin γ, we prove an excess risk rate of eO(L6/(nγ2)), which aligns with the optimal SVM-type rate eO(1/(nγ2)) up to depth-dependent factors. A key technical contribution is our novel control of activation patterns near a reference model, enabling a sharper Rademacher complexity bound for deep ReLU networks trained with gradient descent.

Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation via external guard models--designed to monitor LLM inputs and outputs and block potentially harmful content--has emerged as a prevalent mitigation strategy. Existing approaches of training guard models rely heavily on extensive human curated datasets and struggle with out-of-distribution threats, such as emerging harmful categories or jailbreak attacks. To address these limitations, we propose RSafe, an adaptive reasoning-based safeguard that conducts guided safety reasoning to provide robust protection within the scope of specified safety policies. RSafe operates in two stages: (1) guided reasoning, where it analyzes safety risks of input content through policy-guided step-by-step reasoning, and (2) reinforced alignment, where rule-based RL optimizes its reasoning paths to align with accurate safety prediction.

W paradigm e introduce that enhances Autoregressi image ve Retrie generation val Augmentation by autoregressi ( v A ely R-R incorporating AG), a novel knearest neighbor retrievals at the patch level. Unlike prior methods that perform a fix single, ed reference static retrie images, val before AR-RA generation G performs and conte condition xt-aware the retrie entire vals generation at each genon eration step, using prior-generated patches as queries to retrieve and incorporate the evolving most rele generation vant patch-le needs vel while visual avoiding references, limitations enabling (e.g., the o model ver-cop to ying, respond stylisto tic bias, etc.) prevalent in existing methods. To realize AR-RAG, we propose two parallel frameworks: (1) Distribution-Augmentation in Decoding (DAiD), a tion training-free of model-predicted plug-and-use patches decoding with the strate distrib gy that ution directly of retrie mer v ges ed patches, the distrib and u(2) Feature-Augmentation in Decoding (FAiD), a parameter-efficient fine-tuning method convolution that progressi operations vely and smooths leverages the them features to augment of retriev the ed patches image generation via multi-scale process.

Large language models (LLMs), despite their impressive performance across a wide range of tasks, often struggle to balance two competing objectives in openended text generation: fostering diversity and creativity while preserving logical coherence. Existing truncated sampling techniques, including temperature scaling, top-p (nucleus) sampling, and min-p sampling, aim to manage this trade-off.

Designing protein sequences that fold into a target 3D structure--known as protein inverse folding--is a fundamental challenge in protein engineering. While recent deep learning methods have achieved impressive performance by recovering native sequences, they often overlook the one-to-many nature of the problem: multiple diverse sequences can fold into the same structure.

USER: Please segment .

Learning a compact representation of history is critical for planning and generalization in partially observable environments. While meta-reinforcement learning (RL) agents can attain near Bayes-optimal policies, they often fail to learn the compact, interpretable Bayes-optimal belief states. This representational inefficiency potentially limits the agent's adaptability and generalization capacity. Inspired by predictive coding in neuroscience--which suggests that the brain predicts sensory inputs as a neural implementation of Bayesian inference--and by auxiliary predictive objectives in deep RL, we investigate whether integrating self-supervised predictive coding modules into meta-RL can facilitate learning of Bayes-optimal representations. Through state machine simulation, we show that meta-RL with predictive modules consistently generates more interpretable representations that better approximate Bayes-optimal belief states compared to conventional meta-RL across a wide variety of tasks, even when both achieve optimal policies. In challenging tasks requiring active information seeking, only meta-RL with predictive modules successfully learns optimal representations and policies, whereas conventional meta-RL struggles with inadequate representation learning. Finally, we demonstrate that better representation learning leads to improved generalization. Our results strongly suggest the role of predictive learning as a guiding principle for effective representation learning in agents navigating partial observability.

Watermarking is widely regarded as a promising defense against the misuse of large language models (LLMs); however, existing methods are fundamentally constrained by their vulnerability to scrubbing and spoofing attacks. This vulnerability stems from an inherent trade-off governed by watermark window size: smaller windows resist scrubbing better but are easier to reverse-engineer, enabling lowcost statistics-based spoofing attacks. This work expands the trade-off boundary by introducing a novel mechanism, equivalent texture keys, where multiple tokens within a watermark window can independently support the detection. Based on the redundancy, we propose a watermark scheme with Sub-vocabulary decomposed Equivalent tExture Key (SEEK). SEEK achieves a Pareto improvement, enhancing robustness to scrubbing attacks without sacrificing resistance to spoofing.

Recent advancements in Vision-Language-Action (VLA) models have shown promise for end-to-end autonomous driving by leveraging world knowledge and reasoning capabilities.

While energy-based models have recently proven to be a powerful framework for learning to reason with neural networks, their practical application is still limited by computational cost. That is, existing methods for energy-based iterative reasoning suffer from computational bottlenecks by relying on expensive optimization routines during training and especially during inference.