activity
20242026
most citedDiving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset

6 citations · 11 across the 19 of their papers we have counts for

collaborators

21 papers

cs.CV2026

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

DeepCybo Team, Yu Bin, Haipeng Cao +51

We present PhysBrain 1.5, a unified model for understanding physical environments, generating actions, and predicting future states. Motivated by the physical loop of observation,…

cs.RO2026

SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models

Changti Wu, Bin Yu, Zhaolong Shen +6

Vision-Language-Action (VLA) models are typically trained by imitation learning on large-scale robot demonstration datasets, but more data does not necessarily yield better policie…

cs.RO2026

Human-as-Humanoid: Enabling Zero-Shot Humanoid Learning from Ego-Exo Human Videos with Human-Aligned Embodiments

Xiaopeng Lin, Ruoqi Yang, Shijie Lian +14

Vision-language-action (VLA) models across robot embodiments require high-quality observation--action supervision to learn deployable action distributions, yet scaling such robot d…

cs.RO2026

RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models

Bin Yu, Yao Zhang, Haishan Liu +9

Vision-language-action (VLA) models are built on the premise that semantic understanding from pretrained language or vision-language backbones should guide robot action prediction.…

cs.RO2026

PhysBrain 1.0 Technical Report

Shijie Lian, Bin Yu, Xiaopeng Lin +10

Vision-language-action models have advanced rapidly, but robot trajectories alone provide limited coverage for learning broad physical understanding. PhysBrain 1.0 studies a comple…

cs.RO2026

FrameSkip: Learning from Fewer but More Informative Frames in VLA Training

Bin Yu, Shijie Lian, Xiaopeng Lin +8

Vision-Language-Action (VLA) policies are commonly trained from dense robot demonstration trajectories, often collected through teleoperation, by sampling every recorded frame as i…