Home  ·   Publications  ·   More

News

[2026-08] Release of VBVR-Pro, a scalable and verifiable suite for native visual reasoning.

[2026-07] Release of SenseNova-Vision: Vision as unified multimodal generation.

[2026-06] Demystifying Video Reasoning has been accepted to ECCV 2026.

[2026-06] EgoLife won the Distinguished Paper Award at the EgoVis Workshop, CVPR 2026.

[2026-05] Release of SenseNova-U1, a production-level unified multimodal model built upon NEO-Unify.

[2026-05] Release of NEO-Unify, an encoder-free unified multimodal model.

[2026-05] A Very Big Video Reasoning Suite (VBVR) has been accepted to ICML 2026.

[2026-04] PointHPS has been accepted to IJCV 2026.

[2026-03] Release of Demystifying Video Reasoning, where we discover Chain-of-Steps!

[2026-02] Release of A Very Big Video Reasoning Suite (VBVR).

[2026-02] SenseNova-SI, ConsistCompose, and VLM-Guided HMR have been accepted to CVPR 2026.

[2026-01] ViMoGen has been accepted to ICLR 2026.

[2025-12] Invited talk on SenseNova-SI (slides and recording) at Plutons.

[2025-12] Invited talk on Embodied Intelligence (slides) at TriFusion Workshop.

[2025-11] Release of SenseNova-SI: Scaling Spatial Intelligence with Multimodal Foundation Models.

[2025-10] Release of the source code of DLP3D. Try it now at dlp3d.ai !

[2025-10] Digital Life Project 2 (DLP3D) has been accepted to SIGGRAPH Asia 2025 (Real-Time Live!).

[2025-10] SMPLest-X has been accepted to TPAMI 2025.

[2025-09] PoseFuse3D-KI has been accepted to NeurIPS 2025.

[2025-08] Release of EASI: Holistic Evaluation of Multimodal LLMs on Spatial Intelligence.

[2025-06] DPoser-X (Oral) has been accepted to ICCV 2025.

[2025-05] ADHMR has been accepted to ICML 2025.

[2025-02] SOLAMI, Disco4D, and EgoLife have been accepted to CVPR 2025.

[2025-01] MeshAnything has been accepted to ICLR 2025.

[2024-12] I have started a new role as a Staff Research Scientist at SenseTime Research.

[2024-09] Release of HuMMan v1.0: Motion Generation Subset and GTA-Human II Dataset.

[2024-08] Release of HuMMan v1.0: 3D Vision Subset.

[2024-08] GTA-Human has been accepted to TPAMI 2024 after two years of review!

[2024-07] WHAC and Large Motion Model have been accepted to ECCV 2024.

[2024-06] I have defended my Ph.D. thesis Scaling Up Parametric Human Recovery! 🎓

[2024-04] Invited talk (slides) at China3DV 2024.

[2024-02] Digital Life Project, AiOS, and GaussianEditor have been accepted to CVPR 2024.

[2024-02] Invited talk on SMPLer-X (recording) at International Digital Economy Academy (IDEA).

[2023-09] Story-to-Motion has been accepted to SIGGRAPH Asia 2023 Technical Communications.

[2023-09] SMPLer-X has been accepted to NeurIPS 2023 Datasets and Benchmarks Track.

[2023-09] RoboSMPLX and FineMoGen have been accepted to NeurIPS 2023.

[2023-08] HuMMan is selected for the PREMIA Best Student Paper Awards.

[2023-07] SynBody, ReMoDiffuse, Zolly (Oral), and DNA-Rendering have been accepted to ICCV 2023.

[2023-04] BiBench has been accepted to ICML 2023.

[2023-04] VRCNet++ has been accepted to TPAMI 2023.

[2023-01] Invited talk (slides) at MPI.

[2023-01] Release of HuMMan v1.0: Reconstruction Subset.

[2022-10] We are organizing ECCV 2022 SenseHuman Workshop.

[2022-09] HMR Benchmarks has been accepted to NeurIPS (Datasets and Benchmarks Track) 2022.

[2022-08] Invited talk on HuMMan (slides) at ECCV'22中国预会议.

[2022-07] HuMMan (Oral) and MeshInversion have been accepted to ECCV 2022.

[2022-05] AvatarCLIP has been accepted to SIGGRAPH 2022 (journal-track).

[2022-04] Selected as Highlighted Reviewer at ICLR 2022.

[2022-03] HCMoCo (Oral), ViT OOD, and PTTR have been accepted to CVPR 2022 .

[2021-12] We have released MMHuman3D: 3D Human Parametric Model Toolbox and Benchmark

[2021-09] Selected as Outstanding Reviewer at ICCV 2021.

[2021-07] We are hosting MVP Challenge.

[2021-06] We are organizing ICCV 2021 SenseHuman Workshop.

My Three Favorite Works [Full List]

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Junxiang Xu*, Ruisi Wang*, Fanyi Pu*, Maijunxian Wang*, Ran Ji*, Tongxi Zhou*, Chenyang Gu, Jing Zuo, Hongcan Xiao, Yimeng Geng, Wanqi Yin, Wei Chen, Oscar Qian, Zhengan Yan, Ziqi Huang, Haiwen Diao, Liang Pan, Bo Li, Xiangyu Fan, Dezhi Luo, Fengyuan Yu, Zehong Zhao, Qingying Gao, Tinghui Zhu, Yilan Zhang, Jingqi Tong, Pinyuan Feng, Zhengze Jiang, Letian Wang, Ziyu Guo, Renrui Zhang, Jieneng Chen, Sonia Joseph, Constantin Venhoff, Saman Motamed, Mengyue Yang, Chandra Sripada, Alan Yuille, Philip Torr, Lvmin Zhang, Vikash Kumar, Daniel Khashabi, Nikolaus Kriegeskorte, Raphaël Millière, Vincent C. Müller, Anyi Rao, Quan Wang, Ziwei Liu, Dahua Lin, Lei Yang, Hokin Deng✉, Zhongang Cai✉.
Technical Report, 2026
(Hugging Face #1 Paper of the Day, 27 August 2026)

Homepage PDF Code HuggingFace

Demystifying Video Reasoning

Ruisi Wang, Zhongang Cai✉, Fanyi Pu, Junxiang Xu, Wanqi Yin, Maijunxian Wang, Ran Ji, Chenyang Gu, Bo Li, Ziqi Huang, Hokin Deng, Dahua Lin, Ziwei Liu, Lei Yang.
European Conference on Computer Vision (ECCV), 2026
(Hugging Face #1 Paper of the Day, 18 March 2026)

Homepage PDF Video Code

Scaling Spatial Intelligence with Multimodal Foundation Models

Zhongang Cai*, Ruisi Wang*, Chenyang Gu*, Fanyi Pu*, Junxiang Xu*, Yubo Wang*, Wanqi Yin*, Zhitao Yang*, Chen Wei*, Qingping Sun*, Tongxi Zhou*, Jiaqi Li*, Hui En Pang*, Oscar Qian*, Yukun Wei, Zhiqian Lin, Xuanke Shi, Kewang Deng, Xiaoyang Han, Zukai Chen, Xiangyu Fan, Hanming Deng, Lewei Lu, Liang Pan, Bo Li, Ziwei Liu✉, Quan Wang✉, Dahua Lin✉, Lei Yang*✉.
Computer Vision and Pattern Recognition (CVPR), 2026

PDF Code HuggingFace ModelScope