Mohan Zhang

TRUST: A Decentralized Framework for Auditing Large Language Model Reasoning

PPBOOST: PROGRESSIVE PROMPT BOOSTING FOR TEXT-DRIVEN MEDICAL IMAGE SEGMENTATION

DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation

Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs

Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model