SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens
Paper • 2508.05305 • Published • 48 •
3
Anton Razzhigaev
razzant
AI & ML interests
Language models, multimodal models, knowledge graphs, chatbots
Organizations
commented a
paper 9 months ago
commented 3
papers about 1 year ago
ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
Paper • 2505.02819 • Published • 26 •
4
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders
Paper • 2503.03601 • Published • 233 •
3
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers
Paper • 2502.15007 • Published • 175 •
5
commented a
paper over 1 year ago