The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation Paper • 2610.20456 • Published 2 days ago • 8
Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts Paper • 2610.01153 • Published 15 days ago • 24
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation Paper • 2610.00686 • Published 16 days ago • 12
Agora: Git as Shared Memory for Collective AutoResearch Paper • 2609.18094 • Published about 1 month ago • 59
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 376