BO ZHANG

Short Bio

I am a Computer Vision expert at RobotEra, where I lead a team forging Embodied Intelligence for humanoid robots.

Previously I was on the LongCat Team at Meituan. I worked on projects covering MLLMs, self-driving, and MLOps. I also built the conversational systems of digital avatars for online sales.

Prior to Meituan, I was on the AutoML team at Xiaomi, where we built the NAS framework searching hardware-efficient architectures for mobile applications.

I was generously invited by Glenn Jocher (Ultralytics CEO) as a representative for our most popular open-source project YOLOv6 to the YOLO Vision conference in 2022, 2023, and 2025 (Shenzhen).

I received a BSc from Jilin University (2010) and an MSc (Laurea Magistrale) from University of Trento (2013).

I also authored a tour guide book (2018) on Italy.

You may reach me at zhangboyd@gmail.com.

Selected Publications

• LongCat-Flash-Omni Technical Report
  Meituan LongCat Team
  [arXiv]
• Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput
  Bo Zhang, Shuo Li, Runhe Tian, Yang Yang, Jixin Tang, Jinhao Zhou, Lin Ma
  [arXiv]
• Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference
  Qingyuan Li, Bo Zhang, Liang Ye, Yifan Zhang, Wei Wu, Yerui Sun, Lin Ma, Yuchen Xie
  [arXiv]
• A Speed Odyssey for Deployable Quantization of LLMs
  Qingyuan Li, Ran Meng, Yiduo Li, Bo Zhang, Liang Li, Yifan Lu, Xiangxiang Chu, Yerui Sun, Yuchen Xie
  [arXiv]
• VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks
  Xiangxiang Chu, Jianlin Su, Bo Zhang, Chunhua Shen
  ECCV 2024
• Norm Tweaking: High-performance Low-bit Quantization of Large Language Models
  Liang Li, Qingyuan Li, Bo Zhang, Xiangxiang Chu
  AAAI 2024
• MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
  MobileVLM Team
  [arXiv]
• YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
  YOLOv6 Team
  [arXiv] | [Github]
• Twins: Revisiting the Design of Spatial Attention in Vision Transformers
  Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, Chunhua Shen
  NeurIPS 2021
• Conditional Positional Encodings for Vision Transformers
  Xiangxiang Chu, Zhi Tian, Bo Zhang, Xinlong Wang, Chunhua Shen
  ICLR 2023
• Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search
  Xiangxiang Chu, Tianbao Zhou, Bo Zhang, Jixiang Li
  ECCV 2022
• FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
  Xiangxiang Chu, Bo Zhang, Ruijun Xu
  ICCV 2021
• AutoKWS: Keyword Spotting with Differentiable Architecture Search
  Bo Zhang, Wenfeng Li, Qingyuan Li, Weiji Zhuang, Xiangxiang Chu, Yujun Wang
  ICASSP 2021