2 citations · 5 across the 15 of their papers we have counts for
7 papers · 1 filter
Simple Vision-Language Math Reasoning via Rendered Text
Matvey Skripkin, Elizaveta Goncharova, Andrey Kuznetsov
We present a lightweight yet effective pipeline for training vision-language models to solve math problems by rendering LaTeX encoded equations into images and pairing them with st…
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…
Image Reconstruction as a Tool for Feature Analysis
Eduard Allakhverdov, Dmitrii Tarasov, Elizaveta Goncharova +1
Vision encoders are increasingly used in modern applications, from vision-only models to multimodal systems such as vision-language models. Despite their remarkable success, it rem…
When Less is Enough: Adaptive Token Reduction for Efficient Image Representation
Eduard Allakhverdov, Elizaveta Goncharova, Andrey Kuznetsov
Vision encoders typically generate a large number of visual tokens, providing information-rich representations but significantly increasing computational demands. This raises the q…
MOVE: A Mixture-of-Vision-Encoders Approach for Domain-Focused Vision-Language Processing
Matvey Skripkin, Elizaveta Goncharova, Dmitrii Tarasov +1
Multimodal language models (MLMs) integrate visual and textual information by coupling a vision encoder with a large language model through the specific adapter. While existing app…
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…