Yang Lu

The paper introduces SHADOWMERGE, a novel poisoning attack that successfully compromises graph-based agent memory by exploiting relation-channel conflicts, achieving a high attack success rate across multiple real-world benchmarks.

This paper addresses the threat of coordinated misinformation in LLM-based Multi-Agent Systems by proposing a defense framework, STAR, that effectively identifies and rectifies misleading information at the sentence level.

The paper proposes DareU, a novel LLM unlearning framework that optimizes unlearning by zeroing out data attribution scores instead of maximizing prediction loss, achieving effective unlearning while maintaining model utility.

DiffCrossGait proposes a novel trajectory-level alignment method using latent diffusion to overcome domain discrepancies in 2D-3D gait recognition, achieving state-of-the-art performance.

ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance across diverse tasks.

ElasticMem introduces a novel framework that treats memory as an elastic latent resource, allowing LLM agents to adaptively manage and inject variable-budget memories for improved performance in long-term reasoning tasks.

ExpWeaver introduces a novel framework for LLM agents to learn from past experiences using latent retrieval-augmented generation, achieving state-of-the-art performance while significantly improving token efficiency.

This paper proposes a multi-user PA-enabled EDMA framework to maximize total information rate in the presence of probabilistic LoS blockages, random NLoS scattering, and practical inwaveguide attenuation, deriving closed-form expressions and algorithms for a two-user scenario and extending it to the general multi-user scenario.