no code implementations • 25 Mar 2024 • Sadanand Modak, Noah Patton, Isil Dillig, Joydeep Biswas
This paper addresses the problem of preference learning, which aims to learn user-specific preferences (e. g., "good parking spot", "convenient drop-off location") from visual input.
no code implementations • 13 Dec 2023 • Divyanshu Saxena, Nihal Sharma, Donghyun Kim, Rohit Dwivedula, Jiayi Chen, Chenxi Yang, Sriram Ravula, Zichao Hu, Aditya Akella, Sebastian Angel, Joydeep Biswas, Swarat Chaudhuri, Isil Dillig, Alex Dimakis, P. Brighten Godfrey, Daehyeok Kim, Chris Rossbach, Gang Wang
This paper lays down the research agenda for a domain-specific foundation model for operating systems (OSes).
no code implementations • 29 May 2023 • Jiayi Wei, Greg Durrett, Isil Dillig
In this work, we explore a multi-round code auto-editing setting, aiming to predict edits to a code region based on recent changes within the same codebase.
1 code implementation • NeurIPS 2023 • Xi Ye, Qiaochu Chen, Isil Dillig, Greg Durrett
In this paper, we propose a new satisfiability-aided language modeling (SatLM) approach for improving the reasoning capabilities of LLMs.
no code implementations • 6 Apr 2023 • Celeste Barnaby, Qiaochu Chen, Roopsha Samanta, Isil Dillig
This paper presents a new synthesis-based approach for batch image processing.
1 code implementation • 16 Mar 2023 • Jiayi Wei, Greg Durrett, Isil Dillig
There has been growing interest in automatically predicting missing type annotations in programs written in Python and JavaScript.
no code implementations • 28 Sep 2022 • Greg Anderson, Swarat Chaudhuri, Isil Dillig
In reinforcement learning for safety-critical settings, it is often desirable for the agent to obey safety constraints at all points in time, including during training.
1 code implementation • 2 Mar 2022 • Jiayi Wei, Jarrett Holtz, Isil Dillig, Joydeep Biswas
Accurate kinodynamic models play a crucial role in many robotics applications such as off-road navigation and high-speed driving.
no code implementations • 10 Nov 2021 • Jürgen Cito, Isil Dillig, Vijayaraghavan Murali, Satish Chandra
We integrate counterfactual explanation generation to models of source code in a real-world setting.
no code implementations • 11 Sep 2021 • Madelon Hulsebos, Sneha Gathani, James Gale, Isil Dillig, Paul Groth, Çağatay Demiralp
However, we observe that there exists a gap between the performance of these models on these benchmarks and their applicability in practice.
no code implementations • 1 Feb 2021 • Chenglong Wang, Yu Feng, Rastislav Bodik, Isil Dillig, Alvin Cheung, Amy J. Ko
Modern visualization tools aim to allow data analysts to easily create exploratory visualizations.
Human-Computer Interaction Programming Languages
no code implementations • Findings (EMNLP) 2021 • Xi Ye, Qiaochu Chen, Isil Dillig, Greg Durrett
Multimodal program synthesis, which leverages different types of user input to synthesize a desired program, is an attractive way to scale program synthesis to challenging settings; however, it requires integrating noisy signals from the user, like natural language, with hard constraints on the program's behavior.
1 code implementation • NeurIPS 2020 • Greg Anderson, Abhinav Verma, Isil Dillig, Swarat Chaudhuri
We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces.
no code implementations • ACL 2020 • Xi Ye, Qiaochu Chen, Isil Dillig, Greg Durrett
Existing datasets for regular expression (regex) generation from natural language are limited in complexity; compared to regex tasks that users post on StackOverflow, the regexes in these datasets are simple, and the language used to describe them is not diverse.
1 code implementation • ICLR 2020 • Jiayi Wei, Maruth Goyal, Greg Durrett, Isil Dillig
Given this program abstraction, we then use a graph neural network to propagate information between related type variables and eventually make type predictions.
1 code implementation • 16 Aug 2019 • Xi Ye, Qiaochu Chen, Xinyu Wang, Isil Dillig, Greg Durrett
Our system achieves state-of-the-art performance on the prior datasets and solves 57% of the real-world dataset, which existing neural systems completely fail on.
no code implementations • 22 Apr 2019 • Greg Anderson, Shankara Pailoor, Isil Dillig, Swarat Chaudhuri
In recent years, the notion of local robustness (or robustness for short) has emerged as a desirable property of deep neural networks.
1 code implementation • 20 Dec 2018 • Shuvendu K. Lahiri, Shuo Chen, Yuepeng Wang, Isil Dillig
In this paper, we describe the formal verification of Smart Contracts offered as part of the Azure Blockchain Content and Samples on github.
Programming Languages F.3.1