collaborators

12 papers

cs.CV2026

STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching

Hao Wang, Haoran Geng, Xiaotong Yang +7

Stereo matching is a fundamental task in 3D reconstruction. Despite remarkable advances, the prevailing paradigms formulate stereo matching as a deterministic regression problem, c…

cs.RO2026

GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation

Wenbo Cui, Chengyang Zhao, Songlin Wei +5

Effectively manipulating articulated objects in household scenarios is a crucial step toward achieving general embodied artificial intelligence. Mainstream research in 3D vision ha…

cs.RO2026

SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation

Songlin Wei, Zhenhao Ni, Jie Liu +9

Humanoid foundation models are advancing faster than we can evaluate them. While real-world testing is expensive and difficult to reproduce, existing simulation benchmarks focus pr…

cs.RO2026

: An Open Foundation Model Towards Universal Humanoid Loco-Manipulation

Songlin Wei, Hongyi Jing, Boqian Li +12

We introduce (Psi-Zero), an open foundation model to address challenging humanoid loco-manipulation tasks. While existing approaches often attempt to address this fundamenta…

cs.RO2026

ICLR: In-Context Imitation Learning with Visual Reasoning

Toan Nguyen, Weiduo Yuan, Songlin Wei +3

In-context imitation learning enables robots to adapt to new tasks from a small number of demonstrations without additional training. However, existing approaches typically conditi…

cs.CV2025

Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation

Shaocong Xu, Songlin Wei, Qizhe Wei +12

Transparent objects remain notoriously hard for perception systems: refraction, reflection and transmission break the assumptions behind stereo, ToF and purely discriminative monoc…