Yixin Chen

16

Papers

183

Total Citations

Papers (16)

Move as You Say Interact as You Can: Language-guided Human Motion Generation with Scene Affordance

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation

Decompositional Neural Scene Reconstruction with Generative Diffusion Prior

Large Language Model Meets Graph Neural Network in Knowledge Distillation

TACO: Taming Diffusion for in-the-wild Video Amodal Completion

Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing

InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing

Learning system dynamics without forgetting

Scaling Up Dynamic Human-Scene Interaction Modeling

Dynamic Motion Blending for Versatile Motion Editing

MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes

ASGS: Single-Domain Generalizable Open-Set Object Detection via Adaptive Subgraph Searching

GWM: Towards Scalable Gaussian World Models for Robotic Manipulation

Sheared Backpropagation for Fine-tuning Foundation Models

METASCENES: Towards Automated Replica Creation for Real-world 3D Scans