3 7 3

Wenxuan Huang

Osilly

Osilly

AI & ML interests

None yet

Organizations

Collections 3

View 3 collections

Papers 10

models 8

datasets 3

Osilly/IRG-Toy-Dataset

Viewer • Updated Sep 14, 2025 • 600 • 56 • 1

Osilly/Vision-R1-rl

Viewer • Updated Jun 26, 2025 • 11.3k • 180 • 1

Osilly/Vision-R1-cold

Preview • Updated Mar 23, 2025 • 117 • 14

Wenxuan Huang

AI & ML interests

Organizations

Collections 3

Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

Osilly/Dynamic-LLaVA-7B

Osilly/Dynamic-LLaVA-13B

Osilly/Dynamic-LLaVA-TokenPacker-7B

Osilly/IRG-Toy-Dataset

Interleaving Reasoning for Better Text-to-Image Generation

Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

Osilly/Dynamic-LLaVA-7B

Osilly/Dynamic-LLaVA-13B

Osilly/Dynamic-LLaVA-TokenPacker-7B

Osilly/IRG-Toy-Dataset

Interleaving Reasoning for Better Text-to-Image Generation

Papers 10

models 8

Osilly/Dynamic-LLaVA-13B

Osilly/Dynamic-LLaVA-TokenPacker-13B

Osilly/Dynamic-LLaVA-TokenPacker-7B

Osilly/Dynamic-LLaVA-7B

Osilly/Vision-R1-32B

Osilly/Vision-R1-72B

Osilly/Vision-R1-CI-7B

Osilly/Vision-R1-7B

datasets 3

Osilly/IRG-Toy-Dataset

Osilly/Vision-R1-rl

Osilly/Vision-R1-cold

Wenxuan Huang

AI & ML interests

Organizations

Collections 3

Papers 10

models 8 Sort: Recently updated

datasets 3 Sort: Recently updated

models 8

datasets 3