04:00
2026-08-05
arxiv.org
machine-learning
ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads
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…