Viacheslav Sinii

You Do Not Fully Utilize Transformer's Representation Capacity

The Differences Between Direct Alignment Algorithms are a Blur

ESSA: Evolutionary Strategies for Scalable Alignment

PRPO: Collaborative Online Policy Learning in Personalized RLHF

N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs

Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors