Article
12
Wenhao Chai
wchai
AI & ML interests
computer vision, artificial intelligence
Recent Activity
upvoted an article about 5 hours ago
Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents submitted a paper about 16 hours ago
When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis upvoted a paper about 16 hours ago
When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token AnalysisOrganizations
Efficient, Performant Video Detailed Captioning and a New Benchmark
-
AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
Paper • 2410.03051 • Published • 6 -
wchai/AuroraCap-7B-VID-xtuner
Video-Text-to-Text • 7B • Updated • 65 • 6 -
wchai/AuroraCap-7B-IMG-xtuner
Image-Text-to-Text • 7B • Updated • 20 • 2 -
wchai/Video-Detailed-Caption
Viewer • Updated • 1.03k • 835 • 17
Efficient, Performant Video Detailed Captioning and a New Benchmark
-
AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
Paper • 2410.03051 • Published • 6 -
wchai/AuroraCap-7B-VID-xtuner
Video-Text-to-Text • 7B • Updated • 65 • 6 -
wchai/AuroraCap-7B-IMG-xtuner
Image-Text-to-Text • 7B • Updated • 20 • 2 -
wchai/Video-Detailed-Caption
Viewer • Updated • 1.03k • 835 • 17
From Dense Token to Sparse Memory for Long Video Understanding
datasets 10
wchai/govreport-longppl-keytokens
Viewer • Updated • 100 • 9
wchai/imagenet-wds
Viewer • Updated • 1.34M • 34 • 1
wchai/imagenet_train_256_sd-vae-ft-mse-flax
Updated • 8
wchai/lmms_VDC_test
Viewer • Updated • 5.14k • 1.79k • 2
wchai/eval_video
Updated • 13
wchai/AuroraCap-trainset
Preview • Updated • 1.23k • 9
wchai/AuroraCap-recaption
Viewer • Updated • 22.4k • 55 • 5
wchai/Video-Detailed-Caption
Viewer • Updated • 1.03k • 835 • 17
wchai/video_set
Updated • 67
wchai/audio_set
Updated • 54