arxiv:2607.05061
Lukas
sirluk
AI & ML interests
None yet
Recent Activity
commentedon their article 1 day ago
Efficient LLM Pretraining: Packed Sequences and Masked Attention upvoted a paper 12 days ago
Kronecker Delta Rule for Long Context Linear Attention updated a model 4 months ago
sirluk/Qwen3-8B-KVpop-4xOrganizations
