Ling Shao

Fidelity-Aware Data Composition for Robust Robot Generalization

$1+1<1$? Breaking the Standalone Barrier in Federated Fine-Tuning of Multimodal Large Language Models under Non-IID Data

Contrastive Self-Rewarding MLLM

Multi-Grained Policy Optimization for Multimodal Reasoning: From An Uncertainty Perspective

Selective Seeing: Context-Aware Attention Interventions for Mitigating Hallucinations in Large Vision-Language Models

DDP: Dual-Decoupled Prompting for Multi-Label Class-Incremental Learning

Variational Task Vector Composition

LongHalQA: Long-Context Hallucination Evaluation for MultiModal Large Language Models

M$^2$M: LEARNING CONTROLLABLE MULTI OF EXPERTS AND MULTI-SCALE OPERATORS ARE THE PARTIAL DIFFERENTIAL EQUATIONS NEED