6 papers
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…
Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training
Artyom Sorokin, Nazar Buzun, Alexander Anokhin +7
Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and inference cost. However, most e…
Unlocking the Duality between Flow and Field Matching
Daniil Shlenskii, Alexander Varlamov, Nazar Buzun +1
Conditional Flow Matching (CFM) unifies conventional generative paradigms such as diffusion models and flow matching. Interaction Field Matching (IFM) is a newer framework that gen…
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…
ENOT: Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport
Nazar Buzun, Maksim Bobrin, Dmitry V. Dylov
We present a new approach for Neural Optimal Transport (NOT) training procedure, capable of accurately and efficiently estimating optimal transportation plan via specific regulariz…
Align Your Intents: Offline Imitation Learning via Optimal Transport
Maksim Bobrin, Nazar Buzun, Dmitrii Krylov +1
Offline Reinforcement Learning (RL) addresses the problem of sequential decision-making by learning optimal policy through pre-collected data, without interacting with the environm…