Xiangyu Zeng

Lanxingxuan's activity

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

liked 2 models about 4 hours ago

ZhuYuhan/VideoJev-4B

Feature Extraction • 4B • Updated about 6 hours ago • 2

ZhuYuhan/VideoJev-35B-A3B

Feature Extraction • 34B • Updated about 6 hours ago • 2

updated a dataset about 20 hours ago

Lanxingxuan/LVBench_4000_Video_Crop_v8_Training_Archive

Updated about 19 hours ago • 77

liked a dataset about 23 hours ago

yyd7/OneStreamer-1M

Preview • Updated about 5 hours ago • 1.79k • 3

updated a collection 1 day ago

OneStreamer

Collection

Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction • 4 items • Updated 1 day ago • 2

updated 2 datasets 2 days ago

Lanxingxuan/VideoMME_v8_Stopped_Products_20260912

Viewer • Updated 1 day ago • 2.56k • 68

Lanxingxuan/Video_Crop_Data_uniform_frames_20260905_v1

Viewer • Updated 2 days ago • 804 • 13

liked a dataset 5 days ago

InteractionBench/InteractionBench

Viewer • Updated 16 days ago • 1.06k • 634 • 2

upvoted 2 collections 8 days ago

Video-o3

Collection

Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning • 7 items • Updated Jul 19 • 4

OneStreamer

Collection

Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction • 4 items • Updated 1 day ago • 2

liked 5 models 8 days ago

jdopensource/JoyAI-VL-Interaction-INT4

Video-Text-to-Text • 9B • Updated Jul 31 • 251 • 8

jdopensource/JoyAI-VL-Interaction-INT8

Video-Text-to-Text • 9B • Updated Jul 31 • 89 • 4

jdopensource/JoyAI-VL-Interaction-FP8

Video-Text-to-Text • 9B • Updated Jul 31 • 72 • 4

jdopensource/JoyAI-VL-Interaction-NVFP4

Video-Text-to-Text • 9B • Updated Jul 31 • 57 • 5

jdopensource/JoyAI-VL-Interaction-Preview

Video-Text-to-Text • 9B • Updated Jun 22 • 160 • 91

liked a Space 10 days ago

Running on Zero

MCP

2

OneStreamer-4B

🎬

2

Streaming video LLM that answers at the right time

upvoted a paper 10 days ago

Benchmarking and Enhancing Skill-Level Memory for Partially Observable Robotic Manipulation

Paper • 2609.38886 • Published 13 days ago • 31

liked a dataset 10 days ago

MCG-NJU/OneStreamer-1M

Preview • Updated 2 days ago • 1.37k • 4

liked a model 10 days ago

MCG-NJU/OneStreamer-4B

Video-Text-to-Text • 4B • Updated 10 days ago • 270 • 10

authored a paper 11 days ago

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

Paper • 2610.01762 • Published 12 days ago • 238