Picture for Chaomin Shen

Chaomin Shen

ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge

Add code
May 29, 2025
Viaarxiv icon

Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge

Add code
May 28, 2025
Viaarxiv icon

WorldEval: World Model as Real-World Robot Policies Evaluator

Add code
May 25, 2025
Viaarxiv icon

ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration

Add code
Feb 26, 2025
Viaarxiv icon

ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model

Add code
Feb 21, 2025
Viaarxiv icon

DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control

Add code
Feb 09, 2025
Figure 1 for DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
Figure 2 for DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
Figure 3 for DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
Figure 4 for DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
Viaarxiv icon

Efficient Feature Fusion for UAV Object Detection

Add code
Jan 29, 2025
Viaarxiv icon

Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning

Add code
Jan 04, 2025
Figure 1 for Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning
Figure 2 for Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning
Figure 3 for Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning
Figure 4 for Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning
Viaarxiv icon

Diffusion-VLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression

Add code
Dec 04, 2024
Viaarxiv icon

Harmonizing knowledge Transfer in Neural Network with Unified Distillation

Add code
Sep 27, 2024
Viaarxiv icon