-
TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar
Paper ⢠2510.14972 ⢠Published ⢠35 -
LightMem: Lightweight and Efficient Memory-Augmented Generation
Paper ⢠2510.18866 ⢠Published ⢠113 -
Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning
Paper ⢠2510.19338 ⢠Published ⢠115 -
The Smol Training Playbook
š2.95kThe secrets to building world-class LLMs
Jonatan Borkowski PRO
j14i
AI & ML interests
None yet
Recent Activity
liked
a model
6 days ago
ayanami-kitasan/code-pruner
upvoted
an
article
8 days ago
Introducing AnyLanguageModel: One API for Local and Remote LLMs on Apple Platforms