The datasets behind our Qwen3-VL-8B video RLVR runs: the base 24f/100k mixture and the HopChain v5 multi-hop corpora.
Nguyen Quang Trung
ngqtrung
AI & ML interests
None yet
Recent Activity
updated a model about 18 hours ago
ngqtrung/video-hopchain-8b updated a dataset about 18 hours ago
ngqtrung/video-hopchain liked a model 1 day ago
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9BOrganizations
Video RLVR — final training data
The datasets behind our Qwen3-VL-8B video RLVR runs: the base 24f/100k mixture and the HopChain v5 multi-hop corpora.
Qwen3-VL-8B video RLVR - GRPO checkpoint ladder
Every published checkpoint of the 8B video-QA GRPO campaign, ranked by core-3 mean_accuracy (5,645 rows). Untrained base = 0.4426.
models 19
ngqtrung/video-hopchain-8b
Video-Text-to-Text • 9B • Updated • 60
ngqtrung/aidm-dogs-vs-cats-models
Image Classification • Updated
ngqtrung/video-8b-grpo-twowave-gs140
Video-Text-to-Text • 9B • Updated • 34
ngqtrung/video-8b-grpo-n16-noexplore
Video-Text-to-Text • 9B • Updated • 36
ngqtrung/video-8b-grpo-twowave-tau085-gs40
Video-Text-to-Text • 9B • Updated • 24
ngqtrung/video-8b-grpo-hopchain-v40-vript-gs160
Video-Text-to-Text • 9B • Updated • 30
ngqtrung/video-8b-grpo-n16-warm-explore
Video-Text-to-Text • 9B • Updated • 20
ngqtrung/video-8b-grpo-ppexplore-n16k8
Image-Text-to-Text • 9B • Updated • 7
ngqtrung/video-8b-grpo-ppexplore
Image-Text-to-Text • 9B • Updated • 30 • 1
ngqtrung/video-8b-grpo-sft770
Image-Text-to-Text • 9B • Updated • 8
datasets 56
ngqtrung/video-hopchain
Viewer • Updated • 23.6k • 148
ngqtrung/aidm-dogs-vs-cats-results
Viewer • Updated • 114 • 14
ngqtrung/aidm-dogs-vs-cats-data
Viewer • Updated • 25.5k • 274
ngqtrung/video-r1-mc-24f100k-combined
Viewer • Updated • 106k • 140
ngqtrung/hopchain-v5
Viewer • Updated • 23.6k • 105
ngqtrung/hopchain-v40-1080p
Viewer • Updated • 28.9k • 55 • 1
ngqtrung/vript-hopchain-analysis
Preview • Updated • 13
ngqtrung/hopchain-v34-1080p
Viewer • Updated • 7.9k • 32
ngqtrung/videoqa-samples-videos
Viewer • Updated • 101 • 55
ngqtrung/vero-rl
Viewer • Updated • 95.1k • 13