4 papers
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering
Maksim Savkin, Mikhail Goncharov, Alexander Gambashidze +7
Recent progress in the development of language models has been defined by scale, with each generation absorbing more of the world's knowledge into its weights. However, many practi…
Listener-Rewarded Thinking in VLMs for Image Preferences
Alexander Gambashidze, Li Pengyi, Matvey Skripkin +5
Training robust and generalizable reward models for human visual preferences is essential for aligning text-to-image and text-to-video generative models with human intent. However,…
MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding
Pengyi Li, Irina Abdullaeva, Alexander Gambashidze +2
Modern Video Large Language Models (VLLMs) often rely on uniform frame sampling for video understanding, but this approach frequently fails to capture critical information due to f…
Test-Time Reasoning Through Visual Human Preferences with VLMs and Soft Rewards
Alexander Gambashidze, Konstantin Sobolev, Andrey Kuznetsov +1
Can Visual Language Models (VLMs) effectively capture human visual preferences? This work addresses this question by training VLMs to think about preferences at test time, employin…