43 citations · 124 across the 20 of their papers we have counts for
22 papers
TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents
Aaron J. Li, Weijia Xu, Chandan Singh +8
Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering. Their token efficiency is typically evaluated on isolated tasks, wher…
StudentSim: Training LLM-based Student Simulators
Ke Yang, Chenglong Wang, Michel Galley +4
AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow…
MagicCopy: Bring my data along with me beyond boundaries of apps
Priyan Vaithilingam, Elena L. Glassman, Nathalie Henry Riche +3
People working with data often move their data across multiple applications, because they rely on these apps' complementing user experiences to best complete their tasks. Since tra…
ReUseIt: Synthesizing Reusable AI Agent Workflows for Web Automation
Yimeng Liu, Misha Sra, Jeevana Priya Inala +1
AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these task…
Towards Understanding Graphical Perception in Large Multimodal Models
Kai Zhang, Jianwei Yang, Jeevana Priya Inala +4
Despite the promising results of large multimodal models (LMMs) in complex vision-language tasks that require knowledge, reasoning, and perception abilities together, we surprising…
Data Analysis in the Era of Generative AI
Jeevana Priya Inala, Chenglong Wang, Steven Drucker +6
This paper explores the potential of AI-powered tools to reshape data analysis, focusing on design considerations and challenges. We explore how the emergence of large language and…
Contextualized Data-Wrangling Code Generation in Computational Notebooks
Junjie Huang, Daya Guo, Chenglong Wang +7
Data wrangling, the process of preparing raw data for further analysis in computational notebooks, is a crucial yet time-consuming step in data science. Code generation has the pot…
Rethinking Interpretability in the Era of Large Language Models
Chandan Singh, Jeevana Priya Inala, Michel Galley +2
Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously…
DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing
Priyan Vaithilingam, Elena L. Glassman, Jeevana Priya Inala +1
Users often rely on GUIs to edit and interact with visualizations - a daunting task due to the large space of editing options. As a result, users are either overwhelmed by a comple…
Is Self-Repair a Silver Bullet for Code Generation?
Theo X. Olausson, Jeevana Priya Inala, Chenglong Wang +2
Large language models have shown remarkable aptitude in code generation, but still struggle to perform complex tasks. Self-repair -- in which the model debugs and repairs its own c…
CodeExp: Explanatory Code Document Generation
Haotian Cui, Chenglong Wang, Junjie Huang +5
Developing models that can automatically generate detailed code explanation can greatly benefit software maintenance and programming education. However, existing code-to-text gener…
Execution-based Evaluation for Data Science Code Generation Models
Junjie Huang, Chenglong Wang, Jipeng Zhang +6
Code generation models can benefit data scientists' productivity by automatically generating code from context and text descriptions. An important measure of the modeling progress…
Interactive Code Generation via Test-Driven User-Intent Formalization
Shuvendu K. Lahiri, Sarah Fakhoury, Aaditya Naik +8
Large language models (LLMs) have shown great potential in automating significant aspects of coding by producing natural code from informal natural language (NL) intent. However, w…
Fault-Aware Neural Code Rankers
Jeevana Priya Inala, Chenglong Wang, Mei Yang +5
Large language models (LLMs) have demonstrated an impressive ability to generate code for various programming tasks. In many instances, LLMs can generate a correct program for a ta…
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions
Ansong Ni, Jeevana Priya Inala, Chenglong Wang +4
Pretrained language models have shown superior performance on many natural language processing tasks, yet they still struggle at multi-step formal reasoning tasks like grade school…
Safe Human-Interactive Control via Shielding
Jeevana Priya Inala, Yecheng Jason Ma, Osbert Bastani +2
Ensuring safety for human-interactive robotics is important due to the potential for human injury. The key challenge is defining safety in a way that accounts for the complex range…
Program Synthesis Guided Reinforcement Learning for Partially Observed Environments
Yichen David Yang, Jeevana Priya Inala, Osbert Bastani +3
A key challenge for reinforcement learning is solving long-horizon planning problems. Recent work has leveraged programs to guide reinforcement learning in these settings. However,…
Neurosymbolic Transformers for Multi-Agent Communication
Jeevana Priya Inala, Yichen Yang, James Paulos +5
We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication. We quantify the am…
Likelihood-Based Diverse Sampling for Trajectory Forecasting
Yecheng Jason Ma, Jeevana Priya Inala, Dinesh Jayaraman +1
Forecasting complex vehicle and pedestrian multi-modal distributions requires powerful probabilistic approaches. Normalizing flows (NF) have recently emerged as an attractive tool…
REAS: Combining Numerical Optimization with SAT Solving
Jeevana Priya Inala, Sicun Gao, Soonho Kong +1
In this paper, we present ReaS, a technique that combines numerical optimization with SAT solving to synthesize unknowns in a program that involves discrete and floating point comp…
WebRelate: Integrating Web Data with Spreadsheets using Examples
Jeevana Priya Inala, Rishabh Singh
Data integration between web sources and relational data is a key challenge faced by data scientists and spreadsheet users. There are two main challenges in programmatically joinin…
Synthesis of Recursive ADT Transformations from Reusable Templates
Jeevana Priya Inala, Nadia Polikarpova, Xiaokang Qiu +2
Recent work has proposed a promising approach to improving scalability of program synthesis by allowing the user to supply a syntactic template that constrains the space of potenti…