-
TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar
Paper ā¢ 2510.14972 ā¢ Published ā¢ 35 -
LightMem: Lightweight and Efficient Memory-Augmented Generation
Paper ā¢ 2510.18866 ā¢ Published ā¢ 114 -
Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning
Paper ā¢ 2510.19338 ā¢ Published ā¢ 115 -
The Smol Training Playbook
š2.98kThe secrets to building world-class LLMs
Jonatan Borkowski PRO
j14i
AI & ML interests
None yet
Recent Activity
liked
a model
about 20 hours ago
unsloth/GLM-5
upvoted
an
article
3 days ago
Transformers.js v4 Preview: Now Available on NPM!
Organizations
-
LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios
Paper ā¢ 2509.09926 ā¢ Published ā¢ 14 -
What Breaks Knowledge Graph based RAG? Empirical Insights into Reasoning under Incomplete Knowledge
Paper ā¢ 2508.08344 ā¢ Published -
MemMamba: Rethinking Memory Patterns in State Space Model
Paper ā¢ 2510.03279 ā¢ Published ā¢ 73 -
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
Paper ā¢ 2510.07499 ā¢ Published ā¢ 48
-
TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar
Paper ā¢ 2510.14972 ā¢ Published ā¢ 35 -
LightMem: Lightweight and Efficient Memory-Augmented Generation
Paper ā¢ 2510.18866 ā¢ Published ā¢ 114 -
Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning
Paper ā¢ 2510.19338 ā¢ Published ā¢ 115 -
The Smol Training Playbook
š2.98kThe secrets to building world-class LLMs
-
LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios
Paper ā¢ 2509.09926 ā¢ Published ā¢ 14 -
What Breaks Knowledge Graph based RAG? Empirical Insights into Reasoning under Incomplete Knowledge
Paper ā¢ 2508.08344 ā¢ Published -
MemMamba: Rethinking Memory Patterns in State Space Model
Paper ā¢ 2510.03279 ā¢ Published ā¢ 73 -
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
Paper ā¢ 2510.07499 ā¢ Published ā¢ 48
datasets
0
None public yet