635 citations · 666 across the 8 of their papers we have counts for
8 papers
Reflective VLA: In-Context Action Consequences Make VLAs Generalize
Qing Lian, Kent Yu, Lei Zhang
Most vision-language-action (VLA) models are reactive: they predict the next action from the current instruction and observation, implicitly assuming that the current observation f…
MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
Yuxin Liu, Ziang Ye, Yueqing Sun +6
Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rather than established beforeh…
Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models
Yiran Ling, Qing Lian, Jinghang Li +6
In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied reasoning by allowing users to…
Human-Timescale Adaptation in an Open-Ended Task Space
Adaptive Agent Team, Jakob Bauer, Kate Baumli +25
Foundation models have shown impressive adaptation and scalability in supervised and self-supervised learning problems, but so far these successes have not fully translated to rein…
Learning Robust Real-Time Cultural Transmission without Human Data
Cultural General Intelligence Team, Avishkar Bhoopchand, Bethanie Brownfield +16
Cultural transmission is the domain-general social skill that allows agents to acquire and use information from each other in real-time with high fidelity and recall. In humans, it…
Proving Theorems using Incremental Learning and Hindsight Experience Replay
Eser Aygün, Laurent Orseau, Ankit Anand +5
Traditional automated theorem provers for first-order logic depend on speed-optimized search and many handcrafted heuristics that are designed to work best over a wide range of dom…
Predicting Sim-to-Real Transfer with Probabilistic Dynamics Models
Lei M. Zhang, Matthias Plappert, Wojciech Zaremba
We propose a method to predict the sim-to-real transfer performance of RL policies. Our transfer metric simplifies the selection of training setups (such as algorithm, hyperparamet…
Solving Rubik's Cube with a Robot Hand
OpenAI, Ilge Akkaya, Marcin Andrychowicz +16
We demonstrate that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot. This is made possible by two key comp…