7 papers
SAFECAST: Robust Failure Detection for VLA Policies with Contrast-Set Training and Calibration
Harshitha Rajaprakash, Aditeya Prajapati, Rong Xue +2
Vision-language-action policies often fail under deployment-time distribution shifts such as clutter, distractor objects, lighting changes, novel objects, altered initial states, a…
DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents
Tianyi Zhang, Mousumi Das, Abrar Anwar +2
Large Language Models (LLMs) often struggle with persuasion in high-stakes scenarios. People's individual personalities and concerns require tailored strategies rather than a one-s…
Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
Chancharik Mitra, Yusen Luo, Raj Saravanan +7
Vision-Language Action (VLAs) models promise to extend the remarkable success of vision-language models (VLMs) to robotics. Yet, unlike VLMs in the vision-language domain, VLAs for…
RobotFleet: An Open-Source Framework for Centralized Multi-Robot Task Planning
Rohan Gupta, Trevor Asbery, Zain Merchant +2
Coordinating heterogeneous robot fleets to achieve multiple goals is challenging in multi-robot systems. We introduce an open-source and extensible framework for centralized multi-…
ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations
Jiahui Zhang, Yusen Luo, Abrar Anwar +5
We introduce ReWiND, a framework for learning robot manipulation tasks solely from language instructions without per-task demonstrations. Standard reinforcement learning (RL) and i…
Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection
Abrar Anwar, Rohan Gupta, Zain Merchant +3
Evaluating learned robot control policies to determine their physical task-level capabilities costs experimenter time and effort. The growing number of policies and tasks exacerbat…