9 papers
FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow
Zhifei Yang, Guangyao Zhai, Keyang Lu +6
Scene generation has extensive industrial applications, demanding both high realism and precise control over geometry and appearance. Language-driven retrieval methods compose plau…
STARE-VLA: Progressive Stage-Aware Reinforcement for Fine-Tuning Vision-Language-Action Models
Feng Xu, Guangyao Zhai, Xin Kong +4
Recent advances in Vision-Language-Action (VLA) models, powered by large language models and reinforcement learning-based fine-tuning, have shown remarkable progress in robotic man…
Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
Guangyao Zhai, Yue Zhou, Xinyan Deng +3
Few-shot anomaly detection streamlines and simplifies industrial safety inspection. However, limited samples make accurate differentiation between normal and abnormal features chal…
KGN-Pro: Keypoint-Based Grasp Prediction through Probabilistic 2D-3D Correspondence Learning
Bingran Chen, Baorun Li, Jian Yang +2
High-level robotic manipulation tasks demand flexible 6-DoF grasp estimation to serve as a basic function. Previous approaches either directly generate grasps from point-cloud data…
Video Perception Models for 3D Scene Synthesis
Rui Huang, Guangyao Zhai, Zuria Bauer +5
Traditionally, 3D scene synthesis requires expert knowledge and significant manual effort. Automating this process could greatly benefit fields such as architectural design, roboti…
SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph Manipulation
Haoliang Shang, Hanyu Wu, Guangyao Zhai +4
Scene graphs capture complex relationships among objects, serving as strong priors for content generation and manipulation. Yet, reasonably manipulating scene graphs -- whether by…