Dafeng Wei

Researcher · Finch, Embodied Research Center, AgiBot (智元机器人)

I work on Vision-Language Models (VLM) and Vision-Language-Action models (VLA) for embodied AI — teaching robots to reason about the world and act in it.

Previously, I was a senior algorithm engineer on the autonomous driving team at Li Auto, where I built multimodal large models for driving scenarios (on-vehicle VLM deployment related to DriveVLM, and multimodal retrieval systems for the data loop), and before that an algorithm engineer at ByteDance. I received my M.S. from Shanghai Jiao Tong University, advised by Prof. Hongtao Lu.

News

Dec 2025 GenieReasoner is released — unified embodied VLM reasoning with robotic action.
Oct 2025 AgiBot World Colosseo was selected as a Best Paper Award Finalist at IROS 2025 🏆.
Mar 2025 We released AgiBot World — 1M+ robot manipulation trajectories, fully open-sourced.
Dec 2024 BEV-TSR was accepted to AAAI 2025.
Dec 2024 I joined Finch (Embodied Research Center) at AgiBot, working on VLM & VLA.

Publications

* denotes equal contribution. Also see my Google Scholar profile.

2025

Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training

Yi Liu, Sukai Wang, Dafeng Wei, Xiaowei Cai, Linqing Zhong, Jiange Yang, Guanghui Ren, Jinyu Zhang, Maoqing Yao, Chuankang Li, Xindong He, Liliang Chen, Jianlan Luo

arXiv preprint, 2025

GenieReasoner jointly optimizes embodied reasoning and action execution, with the ERIQ reasoning benchmark (6k+ QA pairs) and FACT, a flow-matching action tokenizer.

Paper Project Code

AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

AgiBot-World-Contributors (incl. Dafeng Wei)

IROS 2025 🏆 Best Paper Award Finalist · IEEE T-RO 2026

An open platform with 1M+ real-robot trajectories across 217 tasks, and GO-1, a generalist policy built on latent action representations.

Paper Project Code Dataset

BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving

Tao Tang*, Dafeng Wei*, Zhengyu Jia, Tian Gao, Changwei Cai, Chengkai Hou, Peng Jia, Kun Zhan, Haiyang Sun, Jingchen Fan, Yixing Zhao, Fu Liu, Xiaodan Liang, Xianpeng Lang, Yang Wang

AAAI 2025

Retrieving complex driving scenes with free-form text queries directly in BEV feature space.

Paper arXiv

2022

Efficient Dual Attention SlowFast Networks for Video Action Recognition

Dafeng Wei, Ye Tian, Liqing Wei, Hong Zhong, Siqian Chen, Shiliang Pu, Hongtao Lu

Computer Vision and Image Understanding (CVIU), 2022

Lightweight two-stream video networks with a cross-modality dual attention fusion module (CMDA).

Paper Code

2021

Towards Dynamic and Scalable Active Learning with Neural Architecture Adaption for Object Detection

Fuhui Tang*, Dafeng Wei*, Chenhan Jiang, Hang Xu, Andi Zhang, Wei Zhang, Hongtao Lu, Chunjing Xu

BMVC 2021

Active learning for object detection that adapts network architecture as the labeled pool grows; deployed on large-scale autonomous-driving data at Huawei.

Paper

2020

TableCell dataset overview from the ICPR poster

Image-based Table Cell Detection: a Novel Table Structure Decomposition Method with New Dataset

Dafeng Wei, Hongtao Lu, Yi Zhou, Kai Chen

ICPR 2020

Detecting table cells as objects to recover table structure, with TableCell — an open dataset of 170K cell-level annotations.

Paper Poster Code & Dataset

Experience

2024.12 – Present
AgiBot (智元机器人) — Researcher, Finch · Embodied Research Center
Vision-Language Models & Vision-Language-Action models for embodied AI.
2023.04 – 2024.12
Li Auto (理想汽车) — Senior Algorithm Engineer, Autonomous Driving
Multimodal LLMs for driving (on-vehicle VLM deployment); multimodal image/video retrieval for the data loop.
2021.04 – 2023.04
ByteDance (字节跳动) — Algorithm Engineer, TikTok Data & EDU
Multimodal video quality modeling for TikTok; document layout analysis for education products.

Internships

2020.10 – 2021.03
Huawei Noah's Ark Lab (华为诺亚研究院) — Research Intern, Computer Vision
Active learning for object detection on large-scale autonomous-driving data (BMVC 2021).
2020.04 – 2020.09
Hikvision Research Institute (海康威视研究院) — Algorithm Intern, Deep Learning
Efficient video action recognition for driver behavior analysis (CVIU 2022).

Education

2018.09 – 2021.03
Shanghai Jiao Tong University — M.S. in Computer Technology
Advisor: Prof. Hongtao Lu. Thesis: efficient deep learning for video action recognition.
2014.09 – 2018.06
Hangzhou Dianzi University — B.S. in Automation
Advisor: Assoc. Prof. Botao Zhang.

Miscellaneous

🧩 I built ArxivPilot, a Chrome extension that adds reading aids to arXiv papers — give it a try if you read a lot of papers.
🔌 I built StepFunMCP, an MCP server for StepFun (阶跃星辰) chat / vision / image-generation / speech models — on PyPI as stepfun-mcp.
🤖 In my spare time I closely follow progress on AGI and autonomous agents.
❤️ Certified in CPR & First Aid by the American Heart Association (AHA) — always ready to help.