collaborators

6 papers

cs.LG2026

Trust-Region Behavior Blending for On-Policy Distillation

Daniil Plyusov, Alexey Gorbatovski, Alexey Malakhov +4

On-policy distillation (OPD) trains a student on prefixes sampled from its own policy while matching a stronger teacher. This addresses the prefix mismatch of offline distillation,…

cs.LG2026

Next Embedding Prediction Makes World Models Stronger

George Bredis, Nikita Balagansky, Daniil Gavrilov +1

Capturing temporal dependencies is critical for model-based reinforcement learning (MBRL) in partially observable, high-dimensional domains. We introduce NE-Dreamer, a decoder-free…

cs.LG2026

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

Viacheslav Sinii, Nikita Balagansky, Gleb Gerasimov +6

The mechanisms by which reasoning training reshapes LLMs' internal computations remain unclear. We study lightweight steering vectors inserted into the base model's residual stream…

cs.LG2025

VARAN: Variational Inference for Self-Supervised Speech Models Fine-Tuning on Downstream Tasks

Daria Diatlova, Nikita Balagansky, Alexander Varlamov +1

Conventional methods for aggregating layers in fine-tuned self-supervised speech models, such as using the final layer or weighted sum, suffer from information bottlenecks and stat…

cs.LG2025

Teach Old SAEs New Domain Tricks with Boosting

Nikita Koriagin, Yaroslav Aksenov, Daniil Laptev +3

Sparse Autoencoders have emerged as powerful tools for interpreting the internal representations of Large Language Models, yet they often fail to capture domain-specific features n…

cs.LG2025

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy

Nikita Balagansky, Yaroslav Aksenov, Daniil Laptev +4

Sparse Autoencoders (SAEs) have proven to be powerful tools for interpreting neural networks by decomposing hidden representations into disentangled, interpretable features via spa…