Ge Liu

7

Papers

71

Total Citations

Papers (7)

Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning

SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding

Learning Molecular Representation in a Cell

A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals

Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective

Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning

NeurIPS 2025arXiv

Riemannian Consistency Model

NeurIPS 2025arXiv