Keming Wu

wukeming11's activity

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

updated a collection about 9 hours ago

StreamOPD

Collection

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding • 2 items • Updated about 9 hours ago

authored a paper about 23 hours ago

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding

Paper • 2608.16320 • Published 5 days ago • 8

updated 2 collections 1 day ago

StreamOPD

Collection

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding • 2 items • Updated about 9 hours ago

WorldReasonBench

Collection

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors • 3 items • Updated 1 day ago

upvoted a paper 2 days ago

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding

Paper • 2608.16320 • Published 5 days ago • 8

updated a model 4 days ago

UniX-Lab/StreamOPD-4B-ST-CueGate

Video-Text-to-Text • 5B • Updated 4 days ago • 45

published a model 4 days ago

UniX-Lab/StreamOPD-4B-ST-CueGate

Video-Text-to-Text • 5B • Updated 4 days ago • 45

liked a model 9 days ago

Qwen/Qwen3.8-2.4T-A95B

Text Generation • 2.4T • Updated 9 days ago • 15.7k • • 1.13k

liked a model 10 days ago

kcz358/aero-realtime-4B

Video-Text-to-Text • 5B • Updated 8 days ago • 219 • 9

upvoted a paper about 1 month ago

Evidence-Grounded AI for Musculoskeletal Care

Paper • 2607.12527 • Published Jul 14 • 17

liked a dataset 2 months ago

longvideotool/LongVT-Source

Viewer • Updated Dec 10, 2025 • 100 • 2.68k • 5

upvoted a paper 2 months ago

MMAE: A Massive Multitask Audio Editing Benchmark

Paper • 2606.07229 • Published Jun 5 • 45

authored 2 papers 3 months ago

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Paper • 2605.10434 • Published May 11 • 29

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning

Paper • 2605.20342 • Published May 19 • 34

upvoted a paper 3 months ago

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning

Paper • 2605.20342 • Published May 19 • 34

liked 2 datasets 3 months ago

ParaVT/ParaVT-Source

Updated Jun 2 • 6.63k • 2

ParaVT/ParaVT-Parquet

Viewer • Updated Jul 7 • 101k • 413 • 3

liked a model 3 months ago

ParaVT/ParaVT-8B

Video-Text-to-Text • 9B • Updated Jun 2 • 321 • 4