Pengtao Xie

OraclePRM: Unlocking the Potential of Each Instance for Multimodal Process Reward Model Training

S-Chain: Structured Visual Chain-of-Thought for Medicine

DreamPRM: Domain-reweighted Process Reward Model for Multimodal Reasoning

ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models

TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining

LoGra-Med: Long-Context Multi-Graph Alignment for Medical Visual-Language Models

BiDoRA: Bi-level Optimization-based Weight-Decomposed Low-Rank Adaptation

Downstream Task Guided Masking Learning in Masked Autoencoders Using Multi-Level Optimization

Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning