Jun Zhang

JungleGym's activity

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

liked 3 datasets 17 days ago

lmwang/VideoChat3-Stage3-Training-Data

Preview • Updated 13 days ago • 4.74k • 5

MCG-NJU/VideoChat3-OL617k

Preview • Updated 23 days ago • 1.59k • 12

MCG-NJU/VideoChat3-LV116k

Viewer • Updated 21 days ago • 8.07k • 71.8k • 15

liked 2 models 17 days ago

MCG-NJU/VideoChat3-4B

Video-Text-to-Text • 4B • Updated 18 days ago • 3.64k • 23

MCG-NJU/I3D-ViT

Image Feature Extraction • 0.4B • Updated 23 days ago • 10.8k • 12

liked a dataset 17 days ago

MCG-NJU/VideoChat3-Academic2M

Viewer • Updated 21 days ago • 19.2k • 6.35k • 23

upvoted a collection 19 days ago

VideoChat3

Collection

10 items • Updated 13 days ago • 26

upvoted a paper 19 days ago

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

Paper • 2607.17423 • Published 21 days ago • 167

liked a dataset 21 days ago

MCG-NJU/TimeLens2-93K

Viewer • Updated 19 days ago • 71.4k • 10.9k • 12

liked 3 models 21 days ago

MCG-NJU/TimeLens2-4B

Video-Text-to-Text • 4B • Updated 19 days ago • 569 • 10

MCG-NJU/TimeLens2-2B

Video-Text-to-Text • 2B • Updated 19 days ago • 1.16k • 6

MCG-NJU/TimeLens2-8B

Video-Text-to-Text • 9B • Updated 19 days ago • 7.95k • 11

upvoted a collection 21 days ago

TimeLens2

Collection

Generalist Video Temporal Grounding with Multimodal LLMs • 8 items • Updated 12 days ago • 15

upvoted a paper 23 days ago

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published 24 days ago • 172

upvoted a paper about 2 months ago

JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence

Paper • 2606.14777 • Published Jun 10 • 216

New activity in TencentARC/TimeLens-8B 4 months ago

Restore Qwen3-VL default cache config

#2 opened 4 months ago by

JungleGym

Fix processor resize defaults for vLLM compatibility

#1 opened 4 months ago by

JungleGym

upvoted a paper 5 months ago

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

Paper • 2603.03447 • Published Mar 3 • 37

updated a dataset 5 months ago

JungleGym/TimeLens-Qwen2.5-VL-7B-filter-data

Viewer • Updated Mar 12 • 289k • 31

liked a model 5 months ago

stepfun-ai/Step-3.5-Flash-Base

Text Generation • 198B • Updated Mar 9 • 195 • 87