Miao Yu

OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment

SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models

UniErase: Towards Balanced and Precise Unlearning in Language Models

BACKDOOR COLLAPSE: ELIMINATING UNKNOWN THREATS VIA KNOWN BACKDOOR AGGREGATION IN LANGUAGE MODELS

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks

MIND SCRAMBLE: UNVEILING LARGE LANGUAGE MODEL PSYCHOLOGY VIA TYPOGLYCEMIA