128 citations · 154 across the 7 of their papers we have counts for
7 papers
Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
Amrith Setlur, Zijian Wang, Andrew Cohen +2
Typical reinforcement learning (RL) methods for LLM reasoning waste compute on hard problems, where correct on-policy traces are rare, policy gradients vanish, and learning stalls.…
Meta-Designing Quantum Experiments with Language Models
Sören Arlt, Haonan Duan, Felix Li +3
Artificial Intelligence (AI) can solve complex scientific problems beyond human capabilities, but the resulting solutions offer little insight into the underlying physical principl…
A Survey on Data Selection for Language Models
Alon Albalak, Yanai Elazar, Sang Michael Xie +11
A major factor in the recent success of large language models is the use of enormous and ever-growing text datasets for unsupervised pre-training. However, naively training a model…
Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
Helen Qu, Sang Michael Xie
Models trained on a labeled source domain (e.g., labeled images from wildlife camera traps) often generalize poorly when deployed on an out-of-distribution (OOD) target domain (e.g…
Holistic Evaluation of Language Models
Percy Liang, Rishi Bommasani, Tony Lee +47
Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Hol…
Leveraging Large (Visual) Language Models for Robot 3D Scene Understanding
William Chen, Siyi Hu, Rajat Talak +1
Abstract semantic 3D scene understanding is a problem of critical importance in robotics. As robots still lack the common-sense knowledge about household objects and locations of a…
Extending the WILDS Benchmark for Unsupervised Adaptation
Shiori Sagawa, Pang Wei Koh, Tony Lee +17
Machine learning systems deployed in the wild are often trained on a source distribution but deployed on a different target distribution. Unlabeled data can be a powerful point of…