video-SALMONN 2 is a powerful audio-visual large language model (LLM) that generates high-quality audio-visual video captions.
AI & ML interests
https://www.ee.tsinghua.edu.cn/en/
Recent Activity
Organization Card
Department of Electronic Engineering, Tsinghua University
models 18
tsinghua-ee/video-SALMONN2_plus_3B_full
5B ā¢ Updated
ā¢ 10
tsinghua-ee/video-SALMONN2_plus_7B_full
9B ā¢ Updated
ā¢ 14
tsinghua-ee/video_SALMONN2plus_3B_audioAlign
5B ā¢ Updated
ā¢ 9
tsinghua-ee/D-ORCA-8B-0210
10B ā¢ Updated
ā¢ 22 ā¢ 1
tsinghua-ee/WAVE-7B
Updated
ā¢ 23 ā¢ 1
tsinghua-ee/video_SALMONN2_7B_audioAlign
Updated
ā¢ 21
tsinghua-ee/video_SALMONN2plus_72B_audioAlign
Updated
ā¢ 4
tsinghua-ee/video_SALMONN2plus_7B_audioAlign
9B ā¢ Updated
ā¢ 500
tsinghua-ee/SALMONN
Automatic Speech Recognition ā¢ Updated
ā¢ 51
tsinghua-ee/video-SALMONN-2_plus_72B
Updated
ā¢ 6 ā¢ 2
datasets 8
tsinghua-ee/ELViM
Viewer
ā¢ Updated
ā¢ 211 ā¢ 17
tsinghua-ee/SACRED-Bench
Viewer
ā¢ Updated
ā¢ 2.48k ā¢ 56
tsinghua-ee/F-16-NBA
Preview
ā¢ Updated
ā¢ 51
tsinghua-ee/AVUTBenchmark
Viewer
ā¢ Updated
ā¢ 3.28k ā¢ 5.49k ā¢ 1
tsinghua-ee/video-SALMONN_2_testset
Preview
ā¢ Updated
ā¢ 143
tsinghua-ee/QualiSpeech
Viewer
ā¢ Updated
ā¢ 14.6k ā¢ 600 ā¢ 21
tsinghua-ee/RivaBench
Viewer
ā¢ Updated
ā¢ 542 ā¢ 469 ā¢ 2
tsinghua-ee/SAVEBench
Preview
ā¢ Updated
ā¢ 72 ā¢ 3