JunnanLi

JunnanLi's activity

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

authored a paper 5 days ago

ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasks

Paper • 2503.06885 • Published 7 days ago • 3

authored a paper about 1 month ago

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Paper • 2501.19324 • Published Jan 31 • 38

liked 2 models about 2 months ago

Salesforce/blip2-opt-2.7b

Image-Text-to-Text • Updated Feb 3 • 407k • 342

Aria-UI/Aria-UI-base

Updated Dec 31, 2024 • 2.59k • 32

updated a model 3 months ago

rhymes-ai/Aria-Chat

Image-Text-to-Text • Updated Dec 15, 2024 • 165 • 11

liked 4 models 3 months ago

rhymes-ai/Aria-Chat

Image-Text-to-Text • Updated Dec 15, 2024 • 165 • 11

rhymes-ai/Aria-Base-64K

Image-Text-to-Text • Updated Dec 1, 2024 • 234 • 13

rhymes-ai/Aria-torchao-int8wo

Updated Oct 25, 2024 • 63 • 12

rhymes-ai/Aria-Base-8K

Image-Text-to-Text • Updated Dec 1, 2024 • 77 • 8

liked a Space 4 months ago

Running

101

101

Open VLM Video Leaderboard

🌎

VLMEvalKit Eval Results in video understanding benchmark

upvoted a paper 4 months ago

VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation

Paper • 2411.13281 • Published Nov 20, 2024 • 20

liked a model 4 months ago

nvidia/NV-Embed-v2

Feature Extraction • Updated 21 days ago • 245k • 397

upvoted a paper 5 months ago

Allegro: Open the Black Box of Commercial-Level Video Generation Model

Paper • 2410.15458 • Published Oct 20, 2024 • 41

liked a model 5 months ago

rhymes-ai/Allegro

Text-to-Video • Updated Oct 31, 2024 • 412 • 255

New activity in rhymes-ai/Aria 5 months ago

Base model not released

11

#2 opened 5 months ago by

adamo1139

authored a paper 5 months ago

Aria: An Open Multimodal Native Mixture-of-Experts Model

Paper • 2410.05993 • Published Oct 8, 2024 • 109

upvoted a paper 5 months ago

Aria: An Open Multimodal Native Mixture-of-Experts Model

Paper • 2410.05993 • Published Oct 8, 2024 • 109

updated 3 datasets 5 months ago

rhymes-ai/RefCOCO

Preview • Updated Oct 10, 2024 • 34

rhymes-ai/NeXTVideo

Preview • Updated Oct 10, 2024 • 42 • 1

rhymes-ai/NLVR2

Preview • Updated Oct 10, 2024 • 56