15 citations · 51 across the 20 of their papers we have counts for
21 papers
Composer 2 Technical Report
Cursor Research, :, Aaron Chan +53
Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability…
Data Retrieval with Importance Weights for Few-Shot Imitation Learning
Amber Xie, Rahul Chand, Dorsa Sadigh +1
While large-scale robot datasets have propelled recent progress in imitation learning, learning from smaller task specific datasets remains critical for deployment in new environme…
Scaffolding Dexterous Manipulation with Vision-Language Models
Vincent de Bakker, Joey Hejna, Tyler Ga Wei Lum +6
Dexterous robotic hands are essential for performing complex manipulation tasks, yet remain difficult to train due to the challenges of demonstration collection and high-dimensiona…
Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning
Jaden Clark, Joey Hejna, Dorsa Sadigh
Expressive robotic behavior is essential for the widespread acceptance of robots in social environments. Recent advancements in learned legged locomotion controllers have enabled m…
Robot Data Curation with Mutual Information Estimators
Joey Hejna, Suvir Mirchandani, Ashwin Balakrishna +7
The performance of imitation learning policies often hinges on the datasets with which they are trained. Consequently, investment in data collection for robotics has grown across b…
Vision Language Models are In-Context Value Learners
Yecheng Jason Ma, Joey Hejna, Ayzaan Wahid +15
Predicting temporal progress from visual trajectories is important for intelligent robots that can learn, adapt, and improve. However, learning such progress estimator, or temporal…
So You Think You Can Scale Up Autonomous Robot Data Collection?
Suvir Mirchandani, Suneel Belkhale, Joey Hejna +3
A long-standing goal in robot learning is to develop methods for robots to acquire new skills autonomously. While reinforcement learning (RL) comes with the promise of enabling aut…
MotIF: Motion Instruction Fine-tuning
Minyoung Hwang, Joey Hejna, Dorsa Sadigh +1
While success in many robotics tasks can be determined by only observing the final state and how it differs from the initial state - e.g., if an apple is picked up - many tasks req…
Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning
Joey Hejna, Chethan Bhateja, Yichen Jiang +2
Increasingly large imitation learning datasets are being collected with the goal of training foundation models for robotics. However, despite the fact that data selection has been…
PERSONA: A Reproducible Testbed for Pluralistic Alignment
Louis Castricato, Nathan Lile, Rafael Rafailov +2
The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values. However, current preference optimization approaches often fail to capture the…
Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
Rafael Rafailov, Yaswanth Chittepu, Ryan Park +5
Reinforcement Learning from Human Feedback (RLHF) has been crucial to the recent success of Large Language Models (LLMs), however, it is often a complex and brittle process. In the…
Aligning Language Models with Demonstrated Feedback
Omar Shaikh, Michelle S. Lam, Joey Hejna +4
Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible t…
Octo: An Open-Source Generalist Robot Policy
Octo Model Team, Dibya Ghosh, Homer Walke +16
Large policies pretrained on diverse robot datasets have the potential to transform robotic learning: instead of training new policies from scratch, such generalist robot policies…
From to : Your Language Model is Secretly a Q-Function
Rafael Rafailov, Joey Hejna, Ryan Park +1
Reinforcement Learning From Human Feedback (RLHF) has been critical to the success of the latest generation of generative AI models. In response to the complex nature of the classi…
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Alexander Khazatsky, Karl Pertsch, Suraj Nair +98
The creation of large, diverse, high-quality robot manipulation datasets is an important stepping stone on the path toward more capable and robust robotic manipulation policies. Ho…
Contrastive Preference Learning: Learning from Human Feedback without RL
Joey Hejna, Rafael Rafailov, Harshit Sikchi +4
Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, u…
Improving Long-Horizon Imitation Through Instruction Prediction
Joey Hejna, Pieter Abbeel, Lerrel Pinto
Complex, long-horizon planning and its combinatorial nature pose steep challenges for learning-based agents. Difficulties in such settings are exacerbated in low data regimes where…
Inverse Preference Learning: Preference-based RL without a Reward Function
Joey Hejna, Dorsa Sadigh
Reward functions are difficult to design and often hard to align with human intent. Preference-based Reinforcement Learning (RL) algorithms address these problems by learning rewar…
Distance Weighted Supervised Learning for Offline Interaction Data
Joey Hejna, Jensen Gao, Dorsa Sadigh
Sequential decision making algorithms often struggle to leverage different sources of unstructured offline interaction data. Imitation learning (IL) methods based on supervised lea…
Extreme Q-Learning: MaxEnt RL without Entropy
Divyansh Garg, Joey Hejna, Matthieu Geist +1
Modern Deep Reinforcement Learning (RL) algorithms require estimates of the maximal Q-value, which are difficult to compute in continuous domains with an infinite number of possibl…
Few-Shot Preference Learning for Human-in-the-Loop RL
Joey Hejna, Dorsa Sadigh
While reinforcement learning (RL) has become a more popular approach for robotics, designing sufficiently informative reward functions for complex tasks has proven to be extremely…