👋 Open to Work

Zhenghao Xing

harryhsing

3 9 7

https://harryhsing.github.io/

AI & ML interests

Multimodal Agents · Video Reasoning

Recent Activity

upvoted an article 3 days ago

A curriculum for post-training agents

updated a model 25 days ago

harryhsing/EchoTraffic-7B

updated a dataset 25 days ago

harryhsing/AV-TAU

View all activity

Organizations

upvoted an article 3 days ago

Article

A curriculum for post-training agents

huggingface

•

12 days ago

• 91

updated a model 25 days ago

harryhsing/EchoTraffic-7B

Updated 25 days ago

updated a dataset 25 days ago

harryhsing/AV-TAU

Viewer • Updated 25 days ago • 148k • 67 • 5

updated 2 Spaces 4 months ago

OmniAgent-RL

🎬

Agentic video understanding with active perception loop

OminAgent Slides

📊

Answer video questions by actively searching frames and audio

published a Space 4 months ago

OminAgent Slides

📊

Answer video questions by actively searching frames and audio

liked a Space 4 months ago

OmniAgent-RL

🎬

Agentic video understanding with active perception loop

liked a dataset 4 months ago

markov-ai/gaming-500-hours

Viewer • Updated Jun 30 • 776 • 14.5k • 268

New activity in harryhsing/AV-TAU 4 months ago

Application

#3 opened 4 months ago by

chenhaitao

authored a paper 5 months ago

Native Active Perception as Reasoning for Omni-Modal Understanding

Paper • 2606.19341 • Published Jun 17 • 21

upvoted a paper 5 months ago

Native Active Perception as Reasoning for Omni-Modal Understanding

Paper • 2606.19341 • Published Jun 17 • 21

submitted a paper to Daily Papers 5 months ago

Native Active Perception as Reasoning for Omni-Modal Understanding

Paper • 2606.19341 • Published Jun 17 • 21

updated 2 models 5 months ago

harryhsing/OmniAgent-SFT-7B

Video-Text-to-Text • 11B • Updated Jun 18 • 28 • 1

harryhsing/OmniAgent-RL-7B

Video-Text-to-Text • 9B • Updated Jun 18 • 68 • 1

liked a model 5 months ago

yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF

Text Generation • 12B • Updated Jun 19 • 111k • 2.99k

published 2 models 5 months ago

harryhsing/OmniAgent-SFT-7B

Video-Text-to-Text • 11B • Updated Jun 18 • 28 • 1

harryhsing/OmniAgent-RL-7B

Video-Text-to-Text • 9B • Updated Jun 18 • 68 • 1

upvoted 2 papers 6 months ago

CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation

Paper • 2604.19636 • Published Apr 21 • 78

Qwen3.5-Omni Technical Report

Paper • 2604.15804 • Published Apr 17 • 61

upvoted a paper 7 months ago

FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios

Paper • 2604.07413 • Published Apr 8 • 99

Zhenghao Xing

AI & ML interests

Recent Activity

Organizations

harryhsing's activity

A curriculum for post-training agents

OmniAgent-RL

OminAgent Slides

OminAgent Slides

OmniAgent-RL

Application