Related papers: SCIZOR: A Self-Supervised Approach to Data Curatio…
Careful curation of data sources can significantly improve the performance of LLM pre-training, but predominant approaches rely heavily on intuition or costly trial-and-error, making them difficult to generalize across different data…
This paper introduces the SOAR framework for imitation learning. SOAR is an algorithmic template that learns a policy from expert demonstrations with a primal dual style algorithm that alternates cost and policy updates. Within the policy…
When human acquire physical skills (e.g., tennis) from experts, we tend to first learn from merely observing the expert. But this is often insufficient. We then engage in practice, where we try to emulate the expert and ensure that our…
It is known that reinforcement learning (RL) is data-hungry. To improve sample-efficiency of RL, it has been proposed that the learning algorithm utilize data from 'approximately similar' processes. However, since the process models are…
Although Large language Model (LLM)-powered information extraction (IE) systems have shown impressive capabilities, current fine-tuning paradigms face two major limitations: high training costs and difficulties in aligning with LLM…
Imitation learning from a large set of human demonstrations has proved to be an effective paradigm for building capable robot agents. However, the demonstrations can be extremely costly and time-consuming to collect. We introduce MimicGen,…
This paper presents a new approach to identifying and eliminating mislabeled training instances for supervised learning. The goal of this approach is to improve classification accuracies produced by learning algorithms by improving the…
Imitation learning is a powerful approach for learning autonomous driving policy by leveraging data from expert driver demonstrations. However, driving policies trained via imitation learning that neglect the causal structure of expert…
Many robotics problems, from robot motion planning to object manipulation, can be modeled as mixed-integer convex programs (MICPs). However, state-of-the-art algorithms are still unable to solve MICPs for control problems quickly enough for…
Data scaling has revolutionized fields like natural language processing and computer vision, providing models with remarkable generalization capabilities. In this paper, we investigate whether similar data scaling laws exist in robotics,…
A long-standing goal in robotics is to build robots that can perform a wide range of daily tasks from perceptions obtained with their onboard sensors and specified only via natural language. While recently substantial advances have been…
Reliable machine learning and statistical analysis rely on diverse, well-distributed training data. However, real-world datasets are often limited in size and exhibit underrepresentation across key subpopulations, leading to biased…
Behavioral cloning has proven to be effective for learning sequential decision-making policies from expert demonstrations. However, behavioral cloning often suffers from the causal confusion problem where a policy relies on the noticeable…
The natural association between visual observations and their corresponding sound provides powerful self-supervisory signals for learning video representations, which makes the ever-growing amount of online videos an attractive source of…
Machine learning algorithms have become increasingly prevalent in multiple domains, such as autonomous driving, healthcare, and finance. In such domains, data preparation remains a significant challenge in developing accurate models,…
Imitation learning is a promising approach for training autonomous vehicles (AV) to navigate complex traffic environments by mimicking expert driver behaviors. While existing imitation learning frameworks focus on leveraging expert…
With the rapid growth of computing powers and recent advances in deep learning, we have witnessed impressive demonstrations of novel robot capabilities in research settings. Nonetheless, these learning systems exhibit brittle generalization…
Learning to produce contact-rich, dynamic behaviors from raw sensory data has been a longstanding challenge in robotics. Prominent approaches primarily focus on using visual or tactile sensing, where unfortunately one fails to capture…
The task of Composed Image Retrieval (CoIR) involves queries that combine image and text modalities, allowing users to express their intent more effectively. However, current CoIR datasets are orders of magnitude smaller compared to other…
Large-scale models are pretrained on massive web-crawled datasets containing documents of mixed quality, making data filtering essential. A popular method is Classifier-based Quality Filtering (CQF), which trains a binary classifier to…