Yifan Wen — accepted AI-conference papers

2026

Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation

Yongjie Bai, Zhouxia Wang, Yang Liu, Kaijun Luo, Yifan Wen, Mingtong Dai +5

CVPR 2026

Recent vision-language-action (VLA) models for multi-task robot manipulation often rely on fixed camera setups and shared visual encoders, which limit their performance under occlusions and during cross-task transfer. To address these challenges, we propose Task-aware Virtual View Exploration (TVVE)

Cited by 0 Source ↗code ↗Scholar ↗

2026

PhyScene3D: Physically Consistent 3D Interactive Tabletop Scene Generation

Weixing Chen, Zhuoqian Feng, Yexin Zhang, Yifan Wen, Yang Liu, Yinghong Liao +3

ICML 2026poster

Generating physically consistent 3D tabletop scenes is a fundamental yet underexplored problem for interactive and generalist robotic learning. The challenge stems from dense object hierarchies and irregular affordances. Existing methods, ranging from decoupled symbolic solvers to end-to-end regress…

Cited by 0 Source ↗Scholar ↗