collaborators

5 papers

cs.CV2026

PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies

Haitao Lin, Hanyang Yu, Jingshun Huang +5

Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-spec…

cs.CV2026

MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models

Hanyang Yu, Haitao Lin, Jingbo Zhang +4

World Action Models (WAMs) present a promising paradigm for robotic control via video prediction. However, current WAMs suffer from fundamental spatial bottlenecks: standard text i…

cs.CV2025

Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View

Jinyu Zhang, Haitao Lin, Jiashu Hou +2

Estimating an object's 6D pose, size, and shape from visual input is a fundamental problem in computer vision, with critical applications in robotic grasping and manipulation. Exis…

cs.CV2025

You Only Estimate Once: Unified, One-stage, Real-Time Category-level Articulated Object 6D Pose Estimation for Robotic Grasping

Jingshun Huang, Haitao Lin, Tianyu Wang +3

This paper addresses the problem of category-level pose estimation for articulated objects in robotic manipulation tasks. Recent works have shown promising results in estimating pa…

cs.CV2025

CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image

Jingshun Huang, Haitao Lin, Tianyu Wang +3

This paper tackles category-level pose estimation of articulated objects in robotic manipulation tasks and introduces a new benchmark dataset. While recent methods estimate part po…