6 citations · 19 across the 9 of their papers we have counts for
3 papers · 1 filter
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…