1.3k citations · 2.1k across the 35 of their papers we have counts for
38 papers
Inference Plans for Hybrid Particle Filtering
Ellie Y. Cheng, Eric Atkinson, Guillaume Baudart +2
Advanced probabilistic programming languages (PPLs) using hybrid particle filtering combine symbolic exact inference and Monte Carlo methods to improve inference performance. These…
BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text
Elliot Bolton, Abhinav Venigalla, Michihiro Yasunaga +8
Models such as GPT-4 and Med-PaLM 2 have demonstrated impressive performance on a wide variety of biomedical NLP tasks. However, these models have hundreds of billions of parameter…
The T-Complexity Costs of Error Correction for Control Flow in Quantum Computation
Charles Yuan, Michael Carbin
Numerous quantum algorithms require the use of quantum error correction to overcome the intrinsic unreliability of physical qubits. However, error correction imposes a unique perfo…
The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning
Tian Jin, Nolan Clement, Xin Dong +4
How does scaling the number of parameters in large language models (LLMs) affect their core capabilities? We study two natural scaling techniques -- weight pruning and simply train…
Turaco: Complexity-Guided Data Sampling for Training Neural Surrogates of Programs
Alex Renda, Yi Ding, Michael Carbin
Programmers and researchers are increasingly developing surrogates of programs, models of a subset of the observable behavior of a given program, to solve a variety of software dev…
Verifying Performance Properties of Probabilistic Inference
Eric Atkinson, Ellie Y. Cheng, Guillaume Baudart +2
In this extended abstract, we discuss the opportunity to formally verify that inference systems for probabilistic programming guarantee good performance. In particular, we focus on…