4 papers · 1 filter
Rotate the Loop: Blockwise Conformality for Looped Transformers
Alexey Zemtsov, Albina Klepach, Vadim Lomshakov +5
Looped transformers reuse one shared block across many recurrent steps, so depth becomes a quantity that can be spent at runtime rather than a stack of distinct layers. Those extra…
Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner
Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin +11
Recent progress in in-context reinforcement learning (ICRL) has demonstrated its potential for training generalist agents that can acquire new tasks directly at inference. Algorith…
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…
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…