V. Solodkin

MAdam: MLMC Adam under Markovian Noise with Application to Average-Reward Policy Optimization

Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation Steering

This work develops a self-contained methodology for learning parameter-efficient rotational transformations based on Riemannian optimization and empirically validate the proposed rotation-based steering scheme, demonstrating its superiority in intervention efficiency.

Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs

A novel white-box attack inspired by locate-then-edit approaches from the field of Knowledge Editing is proposed, modifying the editing framework by incorporating as- sociative knowledge retrieved from the model, thereby extending constraint removal to an entire thematic category rather than being limited to prompts fr...