1 citations · 1 across the 3 of their papers we have counts for
7 papers
Towards Execution-Grounded Automated AI Research
Chenglei Si, Zitong Yang, Yejin Choi +3
Automated AI research holds great potential to accelerate scientific discovery. However, current LLMs often generate plausible-looking but ineffective ideas. Execution grounding ma…
Robust Sampling for Active Statistical Inference
Puheng Li, Tijana Zrnic, Emmanuel Candès
Active statistical inference is a new method for inference with AI-assisted data collection. Given a budget on the number of labeled data points that can be collected and assuming…
Imputation-Powered Inference
Sarah Zhao, Emmanuel Candès
Modern multi-modal and multi-site data frequently suffer from blockwise missingness, where subsets of features are missing for groups of individuals, creating complex patterns that…
Synthetic bootstrapped pretraining
Zitong Yang, Aonan Zhang, Hong Liu +4
We introduce Synthetic Bootstrapped Pretraining (SBP), a language model (LM) pretraining procedure that first learns a model of relations between documents from the pretraining dat…
Probably Approximately Correct Labels
Emmanuel J. Candès, Andrew Ilyas, Tijana Zrnic
Obtaining high-quality labeled datasets is often costly, requiring either human annotation or expensive experiments. In theory, powerful pre-trained AI models provide an opportunit…
s1: Simple test-time scaling
Niklas Muennighoff, Zitong Yang, Weijia Shi +7
Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI's o1 model showed this capability but…