activity
20242026
collaborators

11 papers

cs.LG2026

ReBRAC-v2: The Return of the King

Denis Tarasov, Robert K. Katzschmann

Recent offline reinforcement learning methods increasingly rely on expressive generative policies and specialized value-guidance mechanisms. We ask whether comparable progress can…

cs.RO2026

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows

Chenyu Yang, Denis Tarasov, Davide Liconti +3

Real-world fine-tuning of dexterous manipulation policies remains challenging due to limited real-world interaction budgets and highly multimodal action distributions. Diffusion-ba…

cs.LG2026

Yes, Q-learning Helps Offline In-Context RL

Denis Tarasov, Alexander Nikulin, Ilya Zisman +6

Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have limitations in offline RL set…

cs.CV2026

cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning

Maksim Kolodiazhnyi, Denis Tarasov, Dmitrii Zhemchuzhnikov +6

Computer-Aided Design (CAD) plays a central role in engineering and manufacturing, making it possible to create precise and editable 3D models. Using a variety of sensor or user-pr…

cs.LG2026

Vision-Language Models Unlock Task-Centric Latent Actions

Alexander Nikulin, Ilya Zisman, Albina Klepach +5

Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when o…

cs.CV2026

Object-Centric Latent Action Learning

Albina Klepach, Alexander Nikulin, Ilya Zisman +6

Leveraging vast amounts of unlabeled internet video data for embodied AI is currently bottlenecked by the lack of action labels and the presence of action-correlated visual distrac…