Wenxuan Huang
Osilly
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent authored a paper 8 days ago
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents authored a paper 8 days ago
From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over MemoryOrganizations
models 12
Osilly/Vision-DeepResearch-30B-A3B
31B • Updated • 10 • 2
Osilly/IRG
Updated
Osilly/Vision-DeepResearch-8B
9B • Updated • 17 • 6
Osilly/Acital-Qwen-2.5VL-7B
8B • Updated • 5 • 1
Osilly/Dynamic-LLaVA-13B
13B • Updated • 3
Osilly/Dynamic-LLaVA-TokenPacker-13B
Updated
Osilly/Dynamic-LLaVA-TokenPacker-7B
Updated
Osilly/Dynamic-LLaVA-7B
7B • Updated • 6
Osilly/Vision-R1-32B
33B • Updated • 13 • 1
Osilly/Vision-R1-72B
73B • Updated • 11 • 1
datasets 9
Osilly/IRG-Dataset
Updated • 5
Osilly/Vision-DeepResearch-Eval
Viewer • Updated • 2.79k • 803
Osilly/VDR-Bench
Viewer • Updated • 2k • 732
Osilly/VDR-Bench-testmini
Viewer • Updated • 500 • 95
Osilly/Vision-DeepResearch-Toy-SFT-Data
Viewer • Updated • 1k • 97
Osilly/Vision-DeepResearch-Toy-RL-Data
Viewer • Updated • 1k • 53
Osilly/IRG-Toy-Dataset
Viewer • Updated • 600 • 39 • 1
Osilly/Vision-R1-rl
Viewer • Updated • 11.3k • 216 • 3
Osilly/Vision-R1-cold
Preview • Updated • 216 • 15