Huabin Liu's Homepage

Short Bio

Currently, Huabin Liu (刘华斌) is a researcher at the DeepLearning Lab of Ant Research Institute, whose research focuses on diffusion large language model (dLLM) pre-training, with an emphasis on pre-training data recipe, efficient training paradigms and MoE architectures.

I received my Ph.D. from Shanghai Jiao Tong University (SJTU), working with Prof. Weiyao Lin on video understanding and analysis. From 2024 to 2025, I visited the VISLab at University of Amsterdam as a visiting researcher for 1 year, advised by Prof. Cees Snoek and Prof. Filip Ilievski. From 2023 to 2024, I was a research intern at the Shanghai AI Lab, working with Xiao Sun. During 2019, I was lucky to be a research intern at Aibee, supervised by Dian Li and Jianguo Li. Prior to this, I obtained my bachelor’s degree from Xidian University in 2019.

News

[02/2026] 😁 Paper about Few-shot action recogition is accepted to TPAMI.
[02/2026] ✍🏻 Our team release LLaDA 2.1, which supports token editing now!
[12/2025] 🤖 Our team release the largest diffusion large language model (dLLM) LLaDA 2.0
[11/2025] 🥳 Paper about Streaming Video Reasoning is accepted to AAAI.
[06/2025] 👨‍🎓 I successfully defended my Ph.D. dissertation at SJTU！
[06/2025] 😊 Paper about video recognition is accepted to TCSVT.
[02/2025] 😭 Paper about video QA & reasoning is accepted to CVPR 2025, many thanks to Filip and Cees!
[09/2024] 😊 Paper about video causal discovery & reasoning is accepted to NeurIPS 2024.
[07/2024] 🥳 Paper about video QA & reasoning is accepted to ECCV 2024.
[03/2024] 😃 Paper about dense video captioning is accepted to CVPR 2024.
[01/2024] 🛫 Start my visit to the VISLab at University of Amsterdam as a visiting researcher.
[12/2023] 😆 Paper about instructional video understanding is accepted to AAAI 2024.
[07/2023] 😚 Paper about human-centric video analysis is accepted to IJCV journal.
[07/2022] 😁 Paper about few-shot action recognition is accepted to ACM MM 2022.
[11/2021] 😊 Paper about few-shot action recognition is accepted to AAAI 2022.
[05/2021] 🥳 Paper about fine-grained image recognition is accepted to TMM journal.
[12/2020] 🏆 Our hosted HiEve Challenge won the best Challenge organization award in ACM MM 2020.

Tech Report [Google Scholar][DBLP]

Report

LLaDA2.1: Speeding Up Text Diffusion via Token Editing

Inclusion AI Team, Ant Group

Technical Report, 2026

PDF Project Page BibTex

Report

LLaDA2.0: Scaling Up Diffusion Language Models to 100B

Inclusion AI Team, Ant Group

Technical Report, 2025

PDF Project Page BibTex

Publications [Google Scholar][DBLP]

TPAMI

Few-shot Action Recognition via Intra-and Inter-Video Information Maximization

Huabin Liu, Weiyao Lin, Tieyuan Chen, Yuxi Li, Shuyuan Li, John See

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026.

PDF BibTex

TPAMI

MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning

Tieyuan Chen, Huabin Liu, Yi Wang, Yihang Chen, Tianyao He, Chaofan Gan, Huanyu He, Weiyao Lin

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025.

PDF BibTex

AAAI

CogStream: Context-guided Streaming Video Question Answering

Zicheng Zhao*, Kangyu Wang*, Shijie Li*, Rui Qian, Weiyao Lin, Huabin Liu^† (^† Corresponding author，* Equal Contribution)

AAAI, 2026

PDF Project Page BibTex

TCSVT

CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning

Tieyuan Chen, Huabin Liu^†, Chern Hong Lim, John See, Xing Gao, Junhui Hou, Weiyao Lin^† (^† Corresponding author)

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.

PDF BibTex

CVPR

Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning

Huabin Liu, Filip Ilievski, Cees G. M. Snoek

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

PDF BibTex

NeurIPS

MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning

Tieyuan Chen*, Huabin Liu*, Tianyao He, Yihang Chen, Chaofan Gan, Xiao Ma, Cheng Zhong, Yang Zhang, Yingxue Wang, Hui Lin, Weiyao Lin (* Co-first author)

Neural Information Processing Systems (NeurIPS), 2024

PDF Code Spotlight

ECCV

TimeCraft: Navigate Weakly-Supervised Temporal Grounded Video Question Answering via Bi-directional Reasoning

Huabin Liu, Xiao Ma, Cheng Zhong, Yang Zhang, Weiyao Lin

European Conference on Computer Vision (ECCV), 2024

PDF BibTex

CVPR

DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement

Hao Wu*, Huabin Liu*, Yu Qiao, Xiao Sun (* Co-first author)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

PDF Code BibTex

IJCV

Achieving Procedure-Aware Instructional Video Correlation Learning under Weak Supervision from a Collaborative Perspective

Tianyao He*, Huabin Liu*, Zeling Ni, Yuxi Li, Xiao Ma, Cheng Zhong, Yang Zhang, Yingxue Wang, Weiyao Lin (* Co-first author)

International Journal of Computer Vision (IJCV), 2024

PDF Code

AAAI

Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis

Tianyao He, Huabin Liu, Yuxi Li, Xiao Ma, Cheng Zhong, Yang Zhang, Weiyao Lin

AAAI Conference on Artificial Intelligence (AAAI), 2024.

PDF Code BibTex

IJCV

HiEve: A Large-Scale Benchmark for Human-Centric Video Analysis in Complex Events

Weiyao Lin, Huabin Liu, Shizhan Liu, Yuxi Li, Guojun Qi, Nicu Sebe

International Journal of Computer Vision (IJCV)

PDF Project Page BibTex

ACM MM

Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition

Huabin Liu, Weixian Lv, John See, Weiyao Lin

ACM International Conference on Multimedia (ACM MM), 2023

PDF Code BibTex

CVPR

Speed Up Object Detection on Gigapixel-Level Images With Patch Arrangement

Jiahao Fan, Huabin Liu, Wenjie Yang, John See, Weiyao Lin

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

PDF BibTex

AAAI

TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition

Shuyuan Li, Huabin Liu*, Rui Qian, Yuxi Li, John See, Mengjuan Fei, Xiaoyuan Yu, Weiyao Lin (* Co-first author)

AAAI Conference on Artificial Intelligence (AAAI), 2023.

PDF Code BibTex

TMM

Learning scale-consistent attention part network for fine-grained image recognition

Huabin Liu, Jianguo Li, Dian Li, John See, Weiyao Lin

IEEE Transactions on Multimedia (TMM), 24, 2902-2913

PDF BibTex

BMVC

Temporal Alignment via Event Boundary for Few-shot Action Recongnition

Shuyuan Li*, Huabin Liu*, Mengjuan Fei, Xiaoyuan Yu, Weiyao Lin (* Equal Contribution)

British Machine Vision Conference (BMVC), 2021

PDF BibTex

ICCV

Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization

Rui Qian, Yuxi Li, Huabin Liu, John See, Shuangrui Ding, Dian Li, Weiyao Lin

IEEE/CVF International Conference on Computer Vision (ICCV), 2021

PDF Code BibTex

TOMM

Scene Graph Lossless Compression with Adaptive Prediction for Objects and Relations

Weiyao Lin, Yufeng Zhang, Wenrui Dai, Huabin Liu, John See, Hongkai Xiong

ACM Transactions on Multimedia Computing, Communications and Applications (ACM TOMM), 2024

PDF

Awards

[06/2025] Outstanding Ph.D. Graduate of SJTU.
[12/2023] Funded by China Scholarship Council (CSC) as a visiting researcher for 1 year
[09/2022] CETC scholarship for Ph.D. students in SJTU (¥20000).
[10/2019] Selected as member of Wu Wenjun (吴文俊) AI honorary PhD student in SJTU (< 1%).
[06/2019] Outstanding undergraduate student of Xidian University (XDU)
[2015-2018] First Prize Scholarship of Xidian University (< 4%), 3 times
[2015-2018] Outstanding Student of Xidian University (< 3%), 2 times
[10/2017] First prize of National college students Mathematical Contest in Shaanxi (< 3%)

Services

Organization Committee

Demonstration Chair, IEEE International Conference on Multimedia and Expo (ICME) 2026
Registration Chair, Pattern Recognition and Computer Vision (PRCV) 2025

Reviewers

TPAMI, IJCV, CVPR, ECCV

Contact

No.800, Dongchuan Road, Minhang District, Shanghai, China

huabinliu (at) sjtu.edu.cn

a377323665