Picture for Zeyu Wang

Zeyu Wang

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

Add code
Nov 29, 2024
Viaarxiv icon

CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions

Add code
Nov 25, 2024
Viaarxiv icon

Reassessing Layer Pruning in LLMs: New Insights and Methods

Add code
Nov 23, 2024
Figure 1 for Reassessing Layer Pruning in LLMs: New Insights and Methods
Figure 2 for Reassessing Layer Pruning in LLMs: New Insights and Methods
Figure 3 for Reassessing Layer Pruning in LLMs: New Insights and Methods
Figure 4 for Reassessing Layer Pruning in LLMs: New Insights and Methods
Viaarxiv icon

DeforHMR: Vision Transformer with Deformable Cross-Attention for 3D Human Mesh Recovery

Add code
Nov 18, 2024
Viaarxiv icon

DiT4Edit: Diffusion Transformer for Image Editing

Add code
Nov 05, 2024
Figure 1 for DiT4Edit: Diffusion Transformer for Image Editing
Figure 2 for DiT4Edit: Diffusion Transformer for Image Editing
Figure 3 for DiT4Edit: Diffusion Transformer for Image Editing
Figure 4 for DiT4Edit: Diffusion Transformer for Image Editing
Viaarxiv icon

KALE-LM: Unleash The Power Of AI For Science Via Knowledge And Logic Enhanced Large Model

Add code
Sep 27, 2024
Viaarxiv icon

ExFMan: Rendering 3D Dynamic Humans with Hybrid Monocular Blurry Frames and Events

Add code
Sep 21, 2024
Viaarxiv icon

DreamMapping: High-Fidelity Text-to-3D Generation via Variational Distribution Mapping

Add code
Sep 11, 2024
Viaarxiv icon

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

Add code
Aug 30, 2024
Viaarxiv icon

CinePreGen: Camera Controllable Video Previsualization via Engine-powered Diffusion

Add code
Aug 30, 2024
Viaarxiv icon