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
liked a model about 5 hours ago
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B authored a paper about 12 hours ago
Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models authored a paper about 12 hours ago
Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs