Hello 🎊

I am Jinxi He (何锦熙), an MS in Robotics (MSR) student at Carnegie Mellon UniversityCMU, supervised by Prof. Katia Sycara.

My research focused on Multi-modal Large Language Model (MLLM) hallucination and all kinds of interesting generation tasks. I am also deeply interested in Robot Learning, particularly long horizon visual task planning and execution.

News 🐝

VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity has been accepted to COLM 2026! Paper Website Benchmark

New paper LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos has been accepted to ECCV 2026! Paper Website Code

Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation. Paper Website

Read more →
Jinxi He
Click to see more!