Yuan

The paper proposes Skill-RM, a unified framework that treats reward modeling as an agentic task to consistently integrate diverse evaluation criteria, achieving superior performance over traditional methods.

VLESA is a novel framework that monitors human activities from egocentric video to predict and intervene in dangerous actions by incorporating goal-conditioned safety checks based on inferred intent.

The paper introduces a Contextual Integrity (CI) framework and a new benchmark (DelegateCI-Bench) to rewrite user queries sent to cloud LLMs, ensuring only task-essential information is retained while preserving utility and maximizing privacy.

NeuroArmor is a white-box runtime defense that uses prompt-specific safe variants to selectively detect and mitigate jailbreak attacks, significantly reducing attack success rates while maintaining a low false positive rate.

The paper introduces HERALD, a token-level cryptographic redaction framework that encrypts only sensitive tokens in clinical text, enabling privacy-preserving LLM deployment without significant loss of utility.

ImageAuditor introduces a novel Membership Inference Attack (MIA) specifically designed for Image-based Retrieval-Augmented Generation (IRAG) systems, achieving high accuracy by addressing cross-modal retrieval and discriminative signal extraction challenges.

This paper introduces CHERRL, a controllable hacking environment for rubric-based reinforcement learning to study and mitigate reward hacking.

This paper presents GRAIL, a digital generation pipeline that synthesizes human-object interactions for humanoid robots.

The paper proposes a novel method using fully homomorphic encryption (FHE) to learn causal structures while preserving data privacy, achieving high consistency and practical efficiency.

The paper introduces and analyzes cross-session stored prompt injection, demonstrating that persistent system state transforms prompt injection from a temporary model-level threat into a long-lived, system-level vulnerability in agentic systems.

Pepper is a novel, high-bandwidth anonymous broadcast protocol that achieves cryptographic sender anonymity and significantly improves messaging throughput compared to existing state-of-the-art systems.

The paper proposes DPDL, a novel differential privacy algorithm for decentralized stochastic learning on non-IID data, which uses similarity-based calibration of perturbed cross-gradients to achieve privacy preservation and maintain training efficiency.

MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.

The paper proposes Shallow-RHS, an asymmetric graph-completion model, to solve the cold-start problem for both new content and new devices in large-scale recommendation systems.

The paper proposes an iCEM+TL framework that combines the Sample-efficient Cross-Entropy Method with Transfer Learning and Reward Redesign to improve robotic motion planning for complex tasks like stacking and shelf placement.

The paper proposes a simulation-trained variable impedance control framework for wearable exoskeletons that safely and effectively augments human physical capabilities across multiple tasks.

This paper proposes a training-free framework called ReasonAlloc to mitigate inference bottlenecks in large language models by recasting decoding-time key-value compression as a hierarchical budget allocation problem.

This paper presents a comprehensive survey on reconfigurable antennas for next-generation mobile networks, focusing on their potential and applications.

肖代替了视觉令牌的永久删除，通过可恢复的路由来改进视觉语言模型的性能