activity
20162026
most citedOptimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness

84 citations · 356 across the 59 of their papers we have counts for

collaborators
Showing 2023Show all

8 papers · 1 filter

cs.OS2023

On a Foundation Model for Operating Systems

Divyanshu Saxena, Nihal Sharma, Donghyun Kim +15

This paper lays down the research agenda for a domain-specific foundation model for operating systems (OSes). Our case for a foundation model revolves around the observations that…

cs.SE2023★ 1 cited

Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing

Jiayi Wei, Greg Durrett, Isil Dillig

Developers often dedicate significant time to maintaining and refactoring existing code. However, most prior work on generative models for code focuses solely on creating new code,…

cs.PL2023

Data Extraction via Semantic Regular Expression Synthesis

Qiaochu Chen, Arko Banerjee, Çağatay Demiralp +2

Many data extraction tasks of practical relevance require not only syntactic pattern matching but also semantic reasoning about the content of the underlying text. While regular ex…

cs.CL2023★ 4 cited

SatLM: Satisfiability-Aided Language Models Using Declarative Prompting

Xi Ye, Qiaochu Chen, Isil Dillig +1

Prior work has combined chain-of-thought prompting in large language models (LLMs) with programmatic representations to perform effective and transparent reasoning. While such an a…

cs.CR2023★ 2 cited

Certifying Zero-Knowledge Circuits with Refinement Types

Junrui Liu, Ian Kretz, Hanzhi Liu +7

Zero-knowledge (ZK) proof systems have emerged as a promising solution for building security-sensitive applications. However, bugs in ZK applications are extremely difficult to det…

cs.PL2023★ 12 cited

ImageEye: Batch Image Processing Using Program Synthesis

Celeste Barnaby, Qiaochu Chen, Roopsha Samanta +1

This paper presents a new synthesis-based approach for batch image processing. Unlike existing tools that can only apply global edits to the entire image, our method can apply fine…