On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability
Paper • 2608.30320 • Published • 63
Tomas Rolin
laserbeans
AI & ML interests
Alignment, superintelligence, retrocausality, single source of truth
Recent Activity
liked a dataset about 9 hours ago
espnet/yodas3 liked a model about 9 hours ago
Contrastive-LM/CLM-v0.1-8B liked a model about 17 hours ago
pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-W4A8Organizations
upvoted a paper about 1 month ago