Picture for Chao Ma

Chao Ma

SWAN: Preprocessing SGD Enables Adam-Level Performance On LLM Training With Significant Memory Reduction

Add code
Dec 17, 2024
Viaarxiv icon

OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation

Add code
Dec 15, 2024
Viaarxiv icon

Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos

Add code
Dec 14, 2024
Viaarxiv icon

PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image

Add code
Nov 27, 2024
Viaarxiv icon

Teaching Video Diffusion Model with Latent Physical Phenomenon Knowledge

Add code
Nov 18, 2024
Viaarxiv icon

Deploying Multi-task Online Server with Large Language Model

Add code
Nov 07, 2024
Viaarxiv icon

A Simple Approach to Unifying Diffusion-based Conditional Generation

Add code
Oct 15, 2024
Figure 1 for A Simple Approach to Unifying Diffusion-based Conditional Generation
Figure 2 for A Simple Approach to Unifying Diffusion-based Conditional Generation
Figure 3 for A Simple Approach to Unifying Diffusion-based Conditional Generation
Figure 4 for A Simple Approach to Unifying Diffusion-based Conditional Generation
Viaarxiv icon

Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics

Add code
Oct 10, 2024
Viaarxiv icon

QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model

Add code
Oct 10, 2024
Viaarxiv icon

Rethinking the Principle of Gradient Smooth Methods in Model Explanation

Add code
Oct 10, 2024
Viaarxiv icon