Mikhail Terekhov's picture

1 6

Mikhail Terekhov

terekhov

·

MikhailTerekhov

AI & ML interests

Reinforcement Learning, Multi-objective Reinforcement Learning, RLHF

Recent Activity

liked a dataset 2 days ago

RoganInglis/control-tax

upvoted a paper 6 months ago

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

authored a paper 6 months ago

Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders

View all activity

Organizations

liked a dataset 2 days ago

RoganInglis/control-tax

Viewer • Updated Aug 27, 2025 • 2.37k • 25 • 3

liked a dataset about 1 year ago

codeparrot/apps

Updated Oct 20, 2022 • 19.1k • 201

liked 2 datasets over 1 year ago

Rapidata/text-2-image-Rich-Human-Feedback

Viewer • Updated Mar 7, 2025 • 13k • 271 • 35

Rapidata/117k_human_coherence_flux1.0_V_flux1.1Blueberry

Viewer • Updated Jan 10, 2025 • 4.5k • 38 • 14

liked a model over 1 year ago

allenai/open-instruct-pythia-6.9b-tulu

Text Generation • Updated Jun 13, 2023 • 868 • 6

liked a dataset over 1 year ago

hamishivi/alpaca-farm-davinci-003-2048-token

Viewer • Updated Jun 9, 2023 • 805 • 80 • 3