Daniil Gavrilov

kefirski

t-tech

·

https://kefirski.me

AI & ML interests

hustle

Recent Activity

liked a Space 3 days ago

t-tech/t-search-blog

authored a paper 7 days ago

Rank-Then-Act: Reward-Free Control from Frame-Order Progress

authored a paper 7 days ago

Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control

View all activity

Organizations

commented a paper 12 months ago

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

Paper • 2508.04280 • Published Aug 6, 2025 • 35 •

commented a paper over 1 year ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published Feb 5, 2025 • 59 •

commented a paper almost 2 years ago

Mechanistic Permutability: Match Features Across Layers

Paper • 2410.07656 • Published Oct 10, 2024 • 20 •