6 citations · 19 across the 9 of their papers we have counts for
9 papers
PopPy: Opportunistically Exploiting Parallelism in Python Agentic Workflows
Stephen Mell, David Mell, Konstantinos Kallas +4
Agentic workflows, which compose calls to ML models using a general-purpose programming language like Python, are widely used for a variety of user-facing tasks, from software engi…
Synthesizing Trajectory Queries from Examples
Stephen Mell, Favyen Bastani, Steve Zdancewic +1
Data scientists often need to write programs to process predictions of machine learning models, such as object detections and trajectories in video data. However, writing such quer…
Optimal Program Synthesis via Abstract Interpretation
Stephen Mell, Steve Zdancewic, Osbert Bastani
We consider the problem of synthesizing programs with numerical constants that optimize a quantitative objective, such as accuracy, over a set of input-output examples. We propose…
Quasar: A Programming Language Specialized for LLM Code Actions
Stephen Mell, Botong Zhang, David Mell +5
Large language models (LLMs) often call external tools to solve tasks. One effective strategy is for LLMs to write code, enabling them to use complex control flow such as condition…
Opportunistically Parallel Lambda Calculus
Stephen Mell, Konstantinos Kallas, Steve Zdancewic +1
Scripting languages are widely used to compose external calls such as native libraries and network services. In such scripts, execution time is often dominated by waiting for these…
Ideograph: A Language for Expressing and Manipulating Structured Data
Stephen Mell, Osbert Bastani, Steve Zdancewic
We introduce Ideograph, a language for expressing and manipulating structured data. Its types describe kinds of structures, such as natural numbers, lists, multisets, binary trees,…