🔄 In a Training Loop

dudazhao

ddz16

ddz16

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning

upvoted a paper about 1 month ago

WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models

new activity about 2 months ago

ddz16/Qwen3-VL-8B-CRPO:Add model card and metadata

View all activity

Organizations

None yet

models 2

ddz16/Qwen3-VL-8B-CRPO

Video-Text-to-Text • 770k • Updated May 25 • 3

ddz16/Qwen3-VL-4B-CRPO

Video-Text-to-Text • 570k • Updated May 25 • 2

datasets 1

ddz16/DyBench

Viewer • Updated May 25 • 3.01k • 1.7k