activity
20242026
collaborators

8 papers

cs.LG2026

Plan, Don't Pose: Long Composite Motion Generation with Text-Aligned BFM

Nikolay Shvetsov, Maksim Bobrin, Nazar Buzun +2

Text-to-motion (T2M) generation has broad applications in character animation, virtual avatars, and human-robot interaction. Existing methods typically generate pose trajectories o…

cs.LG2026

Midpoint Generative Models

Daniil Shlenskii, Nikita Gushchin, Lev Novitskiy +2

We introduce Midpoint Generative Models (MGM), a principled framework for training one-step generative models. MGM is based on a simple symmetry of Flow Matching with linear interp…

cs.LG2026

Dual Advantage Fields

Alexey Zemtsov, Maxim Bobrin, Alexander Nikulin +5

Offline goal-conditioned reinforcement learning requires both long-horizon reachability estimates and local action comparisons. Dual goal representations provide value fields that…

cs.LG2026

Zero-Shot Off-Policy Learning

Arip Asadulaev, Maksim Bobrin, Salem Lahlou +3

Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to t…

cs.LG2026

Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics

Maksim Bobrin, Ilya Zisman, Alexander Nikulin +2

Behavioral Foundation Models (BFMs) proved successful in producing policies for arbitrary tasks in a zero-shot manner, requiring no test-time training or task-specific fine-tuning.…

cs.LG2025

HOTA: Hamiltonian framework for Optimal Transport Advection

Nazar Buzun, Daniil Shlenskii, Maxim Bobrin +1

Optimal transport (OT) has become a natural framework for guiding the probability flows. Yet, the majority of recent generative models assume trivial geometry (e.g., Euclidean) and…