Scholar
Xiaobin Hu
Google Scholar ID: 3lMuodUAAAAJ
Tencent Youtu Lab;Technische Universität München (TUM)
Deep learning
Computer vision
VLM
Agents
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
5,641
H-index
20
i10-index
28
Publications
20
Co-authors
25
list available
Contact
Email
xbhunanu@126.com
GitHub
Open ↗
Publications
86 items
Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding
2026
Cited
0
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
2026
Cited
0
TurboT2VA: Fast Large-Scale Text-to-Video-Audio Generation via Score-Regularized Consistency Distillation
2026
Cited
0
LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications
2026
Cited
0
Evidence-RL: Towards Evidence-intensive Visual Reasoning
2026
Cited
0
ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation
2026
Cited
0
Quo Vadis, World Modeling?
2026
Cited
0
SPEAR: Selection-aware Personalized End-to-end Adaptive Rewriting and Retrieval for Community Search
2026
Cited
0
Load more
Resume (English only)
Academic Achievements
Recipient of Shanghai Overseas Talents Award (Baiyulan Young Talent Program), 2023
Oct 2025: PointSeg awarded ICCV Workshop Best Demonstration Award
Jul 2025: IPVG accepted by ACM MM 2025 and runner-up in the 2025 ACM Multimedia Challenge (Identity-preserving Video Generation)
Jul 2025: DICE-Talk and StrandDesigner accepted by ACM MM 2025
Jun 2025: OracleFusion and UniCombine accepted by ICCV 2025
Feb 2025: Eight papers (Sonic, VTON-HandFit, FTEdit, CustAny, GroundingFace, SVFR, DVHGNN, Mobilemamba) accepted by CVPR 2025 (ranked 92nd globally)
Jul 2024: 3Diffusion accepted by ACM MM 2024
Jul 2024: RLR and DiffuMatting accepted by ECCV 2024
Jul 2024: One paper accepted by IEEE TCSVT
May 2024: One paper accepted by Pattern Recognition (PR)
Selected publications include: Sonic (CVPR 2025), OracleFusion (ICCV 2025), VTON-HandFit (arXiv 2024), DiffuMatting (ECCV 2024), RLR (ECCV 2024), Manipvqa (IROS 2024), HitNet (AAAI 2023), Plug-and-Play 3D (TPAMI 2022), among others
Co-authors
25 total
Bjoern Menze
Universität Zürich
Donghao Luo
Youtu lab@Tencent, Shanghai Jiao Tong University
Jiangning Zhang (张江宁)
Youtu Lab, Tencent | Zhejiang University
Wenqi Ren
Sun Yat-sen University
Chengjie WANG(汪铖杰)
Tencent Youtu Lab, Shanghai Jiao Tong University
Co-author 6
Xiaochun Cao
Sun Yat-sen University
Hongwei Bran Li
Martinos Center, MGH, Harvard Medical School