Jiaxin Ge

Constantly Improving Image Models Need Constantly Improving Benchmarks

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

EmpathyRobot: A Dataset and Benchmark for Empathetic Task Planning of Robotic Agent

Self-Corrected Multimodal Large Language Model for Robot Manipulation and Reflection

Training Task Experts through Retrieval Based Distillation