103 citations · 251 across the 38 of their papers we have counts for
7 papers · 1 filter
mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
Jonas Pai, Liam Achenbach, Victoriano Montesinos +3
Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected static web data. As a…
Multimodal Reinforcement Learning with Adaptive Verifier for AI Agents
Reuben Tan, Baolin Peng, Zhengyuan Yang +15
Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-bas…
Multimodal Spatial Language Maps for Robot Navigation and Manipulation
Chenguang Huang, Oier Mees, Andy Zeng +1
Grounding language to a navigating agent's observations can leverage pretrained multimodal foundation models to match perceptions to object or event descriptions. However, previous…
Training Strategies for Efficient Embodied Reasoning
William Chen, Suneel Belkhale, Suvir Mirchandani +4
Robot chain-of-thought reasoning (CoT) -- wherein a model predicts helpful intermediate representations before choosing actions -- provides an effective method for improving the ge…
Towards Embodiment Scaling Laws in Robot Locomotion
Bo Ai, Liu Dai, Nico Bohlinger +7
Cross-embodiment generalization underpins the vision of building generalist embodied agents for any robot, yet its enabling factors remain poorly understood. We investigate embodim…
FAST: Efficient Action Tokenization for Vision-Language-Action Models
Karl Pertsch, Kyle Stachowicz, Brian Ichter +6
Autoregressive sequence models, such as Transformer-based vision-language action (VLA) policies, can be tremendously effective for capturing complex and generalizable robotic behav…
Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding
Joshua Jones, Oier Mees, Carmelo Sferrazza +3
Interacting with the world is a multi-sensory experience: achieving effective general-purpose interaction requires making use of all available modalities -- including vision, touch…