Unified Latents (UL): How to train your latents
Paper • 2602.17270 • Published • 60
latent
-
-
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Paper • 2604.02029 • Published • 151 -
Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space
Paper • 2512.24617 • Published • 66 -
Cross-Tokenizer LLM Distillation through a Byte-Level Interface
Paper • 2604.07466 • Published • 7 -
Fast Byte Latent Transformer
Paper • 2605.08044 • Published • 12 -
Attention Residuals
Paper • 2603.15031 • Published • 187 -
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
Paper • 2605.22791 • Published • 31