Junxuan Liang

3 papers · 2025–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12)

Venues

CVPR (2) ICLR (1)

Top co-authors

Yong-Lu Li (3) Cewu Lu (3) Xinpeng Liu (2) Zili Lin (1) Zixuan Chen (1) Jiaxin Li (1) Yejie Guo (1) Zixuan Cai (1) Chenshuo Zhang (1) Haowen Hou (1)

Research topics

Artificial Intelligence (2) Computer Vision (2) Machine Learning (2) Analysis (2) Core AI (2) Core Methods (2) Deep Learning (1) Robotics (1) Capabilities (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Processing (1)

Keywords

semantic segmentation (1) video segmentation (1) video understanding (1) instance segmentation (1) dynamics modeling (1) human motion (1) inverse dynamics (1) object segmentation (1) phase transition (1) latent space (1) video object segmentation (1) motion imitation (1) human dynamics modeling (1) heterogeneous data aggregation (1) homogeneous latent space (1) inverse-forward dynamics (1) kinematics representation (1) physics simulator (1) ground reaction force (1) data-driven solver (1)

Papers

Homogeneous Dynamics Space for Heterogeneous Humans CVPR 2025 ImDy: Human Inverse Dynamics from Imitated Observations ICLR 2025 M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation CVPR 2025