🎓How I Study AIHISA

📖Read

📄Papers 📰Blogs 🎬Courses

💡Learn

🛤️Paths 📚Topics 💡Concepts 🎴Shorts

🎯Practice

📝Daily Log 🎯Prompts 🧠Review

Search Settings

How I Study AI - Learn AI Papers & Lectures the Easy Way

Papers2

All Beginner Intermediate Advanced

All Sources arXiv

#LongBench

Reinforced Fast Weights with Next-Sequence Prediction

Hee Seung Hwang, Xindi Wu et al.Feb 18arXiv

Fast weight models remember context with a tiny, fixed memory, but standard next-token training teaches them to think only one word ahead.

#fast weight models#next-sequence prediction#reinforcement learning for LMs

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding

Gang Lin, Dongfang Li et al.Feb 4arXiv

Long texts make language models slow because they must keep and re-check a huge memory called the KV cache for every new word they write.

#long-context LLM#sparse attention#head specialization