Picture for Hao Tan

Hao Tan

Refer to the report for detailed contributions

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

Add code
Jun 23, 2025
Viaarxiv icon

MS4UI: A Dataset for Multi-modal Summarization of User Interface Instructional Videos

Add code
Jun 14, 2025
Viaarxiv icon

Test-Time Training Done Right

Add code
May 29, 2025
Viaarxiv icon

Neural BRDF Importance Sampling by Reparameterization

Add code
May 13, 2025
Viaarxiv icon

RayZer: A Self-supervised Large View Synthesis Model

Add code
May 01, 2025
Viaarxiv icon

Gaussian Mixture Flow Matching Models

Add code
Apr 07, 2025
Viaarxiv icon

Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport

Add code
Mar 19, 2025
Viaarxiv icon

VEGGIE: Instructional Editing and Reasoning of Video Concepts with Grounded Generation

Add code
Mar 19, 2025
Viaarxiv icon

RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets

Add code
Feb 13, 2025
Viaarxiv icon

Adaptive Few-shot Prompting for Machine Translation with Pre-trained Language Models

Add code
Jan 03, 2025
Viaarxiv icon