Cut ~40% paper text — tables speak for themselves. Remove duplicate episodic memory framing from README. Add serve.py to quick start. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Tommi Niemi / Rotko Networks Hidden-state episodic memory for frozen transformers. No gradients. Teach via one forward pass, recall via cosine similarity + logit injection. 200-line Python reproduction included. pip install transformers torch numpy && python python/epimem.py
