Yuqing Ma

AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing

Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning

SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning

Conflict-Aware Knowledge Editing in the Wild: Semantic-Augmented Graph Representation for Unstructured Text

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning

Token-Aware Inference-Time Intervention for Large Language Model Alignment

Lexical Diversity-aware Relevance Assessment for Retrieval-Augmented Generation

Hierarchical Prompts with Context-aware Calibration for Open-Vocabulary Object Detection