De-An Huang

deahuang's activity

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

published a dataset 3 days ago

deahuang/FRAG-Datasets

Preview • Updated 3 days ago • 6

updated a dataset 3 days ago

deahuang/FRAG-Datasets

Preview • Updated 3 days ago • 6

upvoted a paper 5 days ago

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

Paper • 2504.15271 • Published 6 days ago • 63

authored a paper 5 days ago

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

Paper • 2504.15271 • Published 6 days ago • 63

authored a paper about 2 months ago

Token-Efficient Long Video Understanding for Multimodal LLMs

Paper • 2503.04130 • Published Mar 6 • 94

authored a paper 3 months ago

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

Paper • 2501.08326 • Published Jan 14 • 35

updated a model 8 months ago

deahuang/lita-vicuna-v1-3-13b

Updated Aug 29, 2024 • 77 • 1

updated a dataset 8 months ago

deahuang/LITA-Datasets

Preview • Updated Aug 29, 2024 • 21 • 3

updated a model 8 months ago

deahuang/MinVIS-Model-Zoo

Updated Aug 29, 2024 • 1

authored a paper 8 months ago

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Paper • 2408.15998 • Published Aug 28, 2024 • 88

upvoted a paper 8 months ago

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Paper • 2408.15998 • Published Aug 28, 2024 • 88

liked 3 models 8 months ago

NVEagle/Eagle-X5-7B

Image-Text-to-Text • Updated Sep 16, 2024 • 894 • 26

NVEagle/Eagle-X5-13B-Chat

Image-Text-to-Text • Updated Sep 16, 2024 • 4.93k • 28

NVEagle/Eagle-X5-13B

Image-Text-to-Text • Updated Sep 16, 2024 • 91 • 15

upvoted a paper about 1 year ago

LITA: Language Instructed Temporal-Localization Assistant

Paper • 2403.19046 • Published Mar 27, 2024 • 20

authored 2 papers about 1 year ago

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

Paper • 2403.14148 • Published Mar 21, 2024 • 21

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching

Paper • 2402.14167 • Published Feb 21, 2024 • 12

authored a paper over 1 year ago

Eureka: Human-Level Reward Design via Coding Large Language Models

Paper • 2310.12931 • Published Oct 19, 2023 • 26