Hello! I’m Jiantong Chen, currently a researcher at the Embodied Intelligence Center of Shanghai Artificial Intelligence Laboratory. My research focuses on robotic learning and embodied artificial intelligence, investigating how intelligent systems perceive, interact with, and learn from environments. I earned my Master’s degree in Pattern Recognition and Intelligent Systems (2020) from Xidian University, where I was advised by Prof. Jie Feng.

Recent News

• [2025-11] I’ve launched a new project, InternManip-Eval(v1.0.0), a cleanly separated evaluation module extracted from the InternManip framework.

  This version includes a fully refactored codebase, numerous bug fixes, and upgraded functionality. It currently supports Calvin, SimplerEnv, GenManip, as well as ARX LIFT2 real-world robot control used in the IROS offline challenge.

  InternManip-Eval adopts a unified client–server (C-S) evaluation paradigm, enabling a consistent workflow across embodied-manipulation benchmarks—even when running on different simulators. As a result, the framework is general, easy to use, and highly efficient (with built-in parallel evaluation support).

  I warmly welcome everyone to try it out!

• [2025-08] We are hosting the IROS 2025 Challenge with two tracks: Manipulation and Navigation. The Vision-Language Manipulation in Open Tabletop Environments challenge, featured at the IROS 2025 Workshop, has a submission deadline of September 30th. We warmly welcome all participants!
• [2025-07] InternManip open-sourced! An All-in-one robot manipulation learning suite for policy models training and evaluation on various datasets and benchmarks.
• [2025-07] InternUtopia v2.2.0 released! The project was renamed from GRUtopia and is a simulation platform for versatile Embodied AI research and developments.
• [2025-02] GRUtopia v2.0.0 released!
• [2024-06] June 21st marks Global ALS Awareness Day. We have launched a technology-driven ALS care initiative. NEWS!