2 citations · 5 across the 15 of their papers we have counts for
3 papers · 2 filters
Sentence-Anchored Gist Compression for Long-Context LLMs
Dmitrii Tarasov, Elizaveta Goncharova, Kuznetsov Andrey
This work investigates context compression for Large Language Models (LLMs) using learned compression tokens to reduce the memory and computational demands of processing long seque…
SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens
Nikita Dragunov, Temurbek Rahmatullaev, Elizaveta Goncharova +5
The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-squared error or diffusion object…
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers
Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev +4
We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation…