Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models Paper • 2503.09573 • Published 1 day ago • 31
MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections Paper • 2502.12170 • Published 29 days ago • 12
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers Paper • 2502.15007 • Published 21 days ago • 162
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? Paper • 2502.14502 • Published 21 days ago • 85
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity Paper • 2502.13063 • Published 23 days ago • 67