USC Geomtry, Vision, and Learning Lab

USC-GVL's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

zhenyuzhao 

updated a dataset about 1 month ago

USC-GVL/Humanoid-Everyday-H1

Viewer • Updated Dec 27, 2025 • 1.66M • 12 • 1

zhenyuzhao 

published a dataset 2 months ago

USC-GVL/Humanoid-Everyday-H1

Viewer • Updated Dec 27, 2025 • 1.66M • 12 • 1

zhenyuzhao 

updated a dataset 2 months ago

USC-GVL/Humanoid-Everyday-G1

Viewer • Updated Nov 27, 2025 • 1.78M • 33

zhenyuzhao 

published a dataset 2 months ago

USC-GVL/Humanoid-Everyday-G1

Viewer • Updated Nov 27, 2025 • 1.78M • 33

zhenyuzhao 

in USC-GVL/humanoid-everyday 3 months ago

The "action" value meaning

2

#3 opened 3 months ago by

RSuperjie

PointsCoder 

updated a collection 4 months ago

Universal Humanoid 2.0

Collection

2 items • Updated Oct 23, 2025

zhenyuzhao 

updated a dataset 4 months ago

USC-GVL/humanoid-everyday

Preview • Updated Oct 23, 2025 • 4.57k • 17

PointsCoder 

updated a collection 4 months ago

Universal Humanoid 2.0

Collection

2 items • Updated Oct 23, 2025

zhenyuzhao 

in USC-GVL/humanoid-everyday 4 months ago

Timeline on HF release

1

#1 opened 4 months ago by

jesbu1

zhenyuzhao 

published a dataset 4 months ago

USC-GVL/humanoid-everyday

Preview • Updated Oct 23, 2025 • 4.57k • 17

WeiChow 

authored a paper 8 months ago

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query

Paper • 2506.03144 • Published Jun 3, 2025 • 7

OliverZhao 

authored a paper 9 months ago

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

Paper • 2504.18904 • Published Apr 26, 2025 • 9

WeiChow 

authored a paper 10 months ago

An Empirical Study of GPT-4o Image Generation Capabilities

Paper • 2504.05979 • Published Apr 8, 2025 • 64

WeiChow 

updated a dataset 11 months ago

USC-GVL/PhysBench

Updated Mar 5, 2025 • 335 • 15

PointsCoder 

updated a collection 11 months ago

Universal Humanoid 1.0

Collection

Official dataset and models for the paper "Learning from Massive Human Videos for Universal Humanoid Pose Control" • 3 items • Updated Mar 2, 2025 • 2

WeiChow 

in USC-GVL/PhysBench about 1 year ago

Set correct task category

#2 opened about 1 year ago by

nielsr

Add link to paper, task category

#1 opened about 1 year ago by

nielsr

WeiChow 

authored 2 papers about 1 year ago

One Graph Model for Cross-domain Dynamic Link Prediction

Paper • 2402.02168 • Published Feb 3, 2024 • 1

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Paper • 2501.16411 • Published Jan 27, 2025 • 19

PointsCoder 

updated a collection about 1 year ago

PhysBench

Collection

8 items • Updated Jan 31, 2025 • 1