-
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 • 114 -
Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning
Paper • 2510.19338 • Published • 115 -
The Smol Training Playbook
📚3.04kThe secrets to building world-class LLMs
Jonatan Borkowski
j14i
AI & ML interests
None yet
Recent Activity
updated
a collection
1 day ago
Reading list liked
a model 1 day ago
Qwen/Qwen3.5-9B liked
a Space 5 days ago
HuggingFaceM4/faster-qwen3-tts-demo