Xiangtai Li

Xiangtai Li

PhD in PKU

I am Xiangtai Li. I work on computer vision, multi-modal learning, and related problems.

I am working as a Senior Staff Research Scientist at ByteDance (Tiktok), Singapore.

Our team works on applications development and research for TikTok Live. Our products and models are used by TT-Live directly and have impact on billions of users.

Topics cover large language models, diffusion models, and LLM agents.

Previously, I worked as a Research Fellow at MMLab@NTU, S-Lab, advised by Prof. Chen Change Loy.

I obtained my PhD degree from Peking University (PKU) under the supervision of Prof. Yunhai Tong, and my bachelorโ€™s degree from Beijing University of Posts and Telecommunications (BUPT).

My current research topics focus on two main aspects, LLMs and AIGC:

  • LLMs: unified modeling, benchmarking, dataset pipeline building, RL-based post-training, diffusion language models, agentic learning.

  • AIGC: Image/Video Editing, Controllable image/video generation, Streaming video generation.

Moreover, the code and models for my work (about 98%), including the projects I have deeply contributed to, are open-sourced on GitHub.

I serve as a regular reviewer for many conferences and journals, including CVPR, ICCV, ECCV, ICLR, AAAI, NeurIPS, ICML, IJCAI, IEEE-TIP, IEEE-TPAMI, IJCV, IEEE-TSCVT, IEEE-TMM, and IEEE-TGRS.

I also serve as an Area Chair for ICLR-2025/2026, CVPR-2026, ICML-2025/2026, ICCV-2025, NeurIPS-2025/2026, AAAI-2026/2027, WACV-2026/2027, and ECCV-2026.

In addition, I also serve as an Associate Editor for T-PAMI and Pattern Recognition Letters.

I am looking for strong interns with LLM/Diffusion infra and/or AIGC background, location: Beijing and Singapore. Candidates with strong infra ability first. (ByteIntern/็ญ‹ๆ–—ไบ‘ๅฎžไน ็”Ÿ)

My email addresses are xiangtai94@gmail.com and xiangtai.li@bytedance.com. Feel free to contact me directly.

๐Ÿ“ News

  • 2026.07.20: Sa2VA on PAMI-2026! Pixel-SAIL on COLM-2026! Checkout new visual RL work, UniVR.

  • 2026.06.20: Three works on Video Caption Dataset, Grounding RL and Visual Spatial Understanding were accepted to ECCV 2026!

  • 2026.05.01: Two works on Temporal Grounding and Highlight Detection were accepted to ICML 2026!

  • 2026.04.10: SAMTok was accepted to CVPR 2026 as a Highlight paper!

  • 2026.03.10: Eight works were accepted by CVPR 2026!

๐Ÿ“ Publications

* means equal contribution.

Recent Works

  • SAMTok: Representing Any Mask with Two Words, Yikang Zhou*, Tao Zhang*, Dengxian Gong, Yuanzheng Wu, Ye Tian, Haochen Wang, Haobo Yuan, Jiacong Wang, Lu Qi, Hao Fei, Anran Wang, Zhuochen Wang, Yujing Wang, Cheng Chen, Shunping Ji, Xiangtai Li [CVPR-2026, Highlight] Use two words to represent any mask to facilitate use of VLM infra for pixel-LLM. | Code
  • Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence, Jiahao Meng, Xiangtai Li, Haochen Wang, Yue Tan, Tao Zhang, Lingdong Kong, Yunhai Tong, Anran Wang, Zhiyang Teng, Yujing Wang, Zhuochen Wang [ICML-2026] The first non-agentic spatial-temporal RL post-training framework. | Code
  • Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs, Haochen Wang*, Yuhao Wang*, Tao Zhang, Yikang Zhou, Yanwei Li, Jiacong Wang, Jiani Zheng, Ye Tian, Jiahao Meng, Zilong Huang, Guangcan Mai, Anran Wang, Yunhai Tong, Zhuochen Wang, Xiangtai Li, Zhaoxiang Zhang [ICLR-2026] SOTA region caption models | Code Model and Data
  • MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation, Ye Tian, Ling Yang, Jiongfan Yang, Anran Wang, Yu Tian, Jiani Zheng, Haochen Wang, Zhiyang Teng, Zhuochen Wang, Yinjie Wang, Yunhai Tong, Mengdi Wang, Xiangtai Li [ICLR-2026] The first unified parallel generation model | Code Model and Data
  • Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos, Haobo Yuan*, Xiangtai Li*, Tao Zhang*, Zilong Huang, Shilin Xu, Shunping Ji, Yunhai Tong, Lu Qi, Jiashi Feng, Ming-Hsuan Yang [TPAMI-2026] Marrying SAM2 with LLaVA-like MLLM for open-ended spatial temporal understanding. | Project Page

    • Several Other Previous Works

  • RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything, Shilin Xu, Haobo Yuan, Qingyu Shi, Lu Qi, Jingbo Wang, Yibo Yang, Yining Li, Kai Chen, Yunhai Tong, Bernard Ghanem, Xiangtai Li, Ming-Hsuan Yang [ICLR-2025, Oral] A new real-time multi-task segmentation setting, benchmark, and a simple efficient baseline. | Code
  • OMG-Seg: Is One Model Good Enough For All Segmentation?, Xiangtai Li, Haobo Yuan, Wei Li, Henghui Ding, Size Wu, Wenwei Zhang, Yining Li, Kai Chen, Chen Change Loy [CVPR-2024] One model to perform image/video/open-vocabulary/multi-dataset/interactive segmentation in one shot. | Project Page
  • Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation, Xiangtai Li*, Wenwei Zhang*, Jiangmiao Pang*, Kai Chen, Guangliang Cheng, Yunhai Tong, Chen Change Loy [CVPR-2022, Oral] Top 2%. The first unified video segmentation model and codebase for VPS, VIS, VSS. | Code

    • Code can be found on my GitHub.

    ๐ŸŽ– Honors and Awards

    • National Scholarship, Ministry of Education of China in PKU (2019-2020, 2020-2021).

    • President Scholarship of PKU (year 2020-2021).

    • 2017, 2022 Beijing Excellent Graduates.

    • 2017, 2022 BUPT Excellent Graduates, PKU Excellent Graduates.

    ๐Ÿ“– Educations

    • 2017.09 - 2022.07, PhD in Peking University (PKU).

    • 2013.09 - 2017.07, Bachelor in Beijing University of Posts and Telecommunications (BUPT).

    ๐Ÿ’ฌ Invited Talks

    • 2024.03 Invited talk on Open-Vocabulary Segmentation and Segment Anything at VALSE, online. Slides, Video.

    • 2023.08 Invited talk on Video Segmentation at VALSE, online. Slides, Video.

    • 2022.05 Invited talk on Panoptic Segmentation and Beyond in Baidu PaddleSeg Group.

    • 2021.12 Invited talk on Video Segmentation in DiDi Auto-Driving Group.

    • 2021.10 Invited talk on Aligned Segmentation at Huawei Noah Auto-Driving Group.

    ๐Ÿ’ป Internships