Qwen3-8B-Base

Researchers introduced ARCHead, a packed language-modeling head compressor that reduces persistent storage by 3.7-3.9x while maintaining model quality. On Qwen3-8B-Base, ARCHead uses 25.6% of BF16 hea…

A study from arXiv (arXiv:2608.00220v1) shows that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for later objecti…

Researchers introduced HSS-Synth, the first data synthesis pipeline for humanities and social sciences, generating 237,000 instruction-tuning samples that outperform 14 leading baselines on 16 benchma…