no code implementations • 29 Jan 2024 • Manav Singhal, Tushar Aggarwal, Abhijeet Awasthi, Nagarajan Natarajan, Aditya Kanade
We propose a new benchmark NoFunEval to evaluate code LMs on non-functional requirements and simple classification instances for both functional and non-functional requirements.
no code implementations • 22 Sep 2023 • Nalin Wadhwa, Jui Pradhan, Atharv Sonwane, Surya Prakash Sahu, Nagarajan Natarajan, Aditya Kanade, Suresh Parthasarathy, Sriram Rajamani
We present a tool, CORE (short for COde REvisions), architected using a pair of LLMs organized as a duo comprised of a proposer and a ranker.
1 code implementation • 19 Jun 2023 • Lakshya A Agrawal, Aditya Kanade, Navin Goyal, Shuvendu K. Lahiri, Sriram K. Rajamani
We construct a repository-level dataset PragmaticCode for method-completion in Java and evaluate MGD on it.
Ranked #1 on Code Completion on DotPrompts
no code implementations • 23 May 2023 • Priyanshu Gupta, Avishree Khare, Yasharth Bajpai, Saikat Chakraborty, Sumit Gulwani, Aditya Kanade, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari
In our experiments with two datasets, the knowledge of prior edits boosts the performance of the LLMs significantly and enables them to generate 29% and 54% more correctly edited code in top-1 suggestions relative to the current state-of-the-art symbolic and neural approaches, respectively.
no code implementations • 31 Jan 2023 • Harshit Joshi, Abishai Ebenezer, José Cambronero, Sumit Gulwani, Aditya Kanade, Vu Le, Ivan Radiček, Gust Verbruggen
We evaluate FLAME on formula repair, formula completion, and similarity-based formula retrieval.
1 code implementation • 15 Dec 2022 • Ravi Raja, Stanly Samuel, Chiranjib Bhattacharyya, Deepak D'Souza, Aditya Kanade
In this paper, we introduce a tool BNSynth, that is the first to solve the BFS problem under a given bound on the solution space.
1 code implementation • 17 Sep 2022 • Surya Prakash Sahu, Madhurima Mandal, Shikhar Bharadwaj, Aditya Kanade, Petros Maniatis, Shirish Shevade
Compared to the existing datasets, in CodeQueries, the queries are about code semantics, the context is file level and the answers are code spans.
no code implementations • 16 Apr 2022 • Aditya Kanade, Mansi Sharma, Manivannan Muniyandi
Four novel feature extractors are proposed and studied that allow the transformer network to operate on skeletal data.
no code implementations • 6 Dec 2021 • Aditya Kanade, Mansi Sharma, M. Manivannan
We propose Tele-EvalNet, a novel system consisting of two components: a live feedback model and an overall performance evaluation model.
1 code implementation • 12 Jul 2021 • Soham Pal, Yash Gupta, Aditya Kanade, Shirish Shevade
Machine-Learning-as-a-Service providers expose machine learning (ML) models through application programming interfaces (APIs) to developers.
1 code implementation • 7 Feb 2020 • Soham Pal, Yash Gupta, Aditya Shukla, Aditya Kanade, Shirish Shevade, Vinod Ganapathy
We demonstrate that (1) it is possible to use ACTIVETHIEF to extract deep classifiers trained on a variety of datasets from image and text domains, while querying the model with as few as 10-30% of samples from public datasets, (2) the resulting model exhibits a higher transferability success rate of adversarial examples than prior work, and (3) the attack evades detection by the state-of-the-art model extraction detection method, PRADA.
2 code implementations • ICML 2020 • Aditya Kanade, Petros Maniatis, Gogul Balakrishnan, Kensen Shi
We fine-tune CuBERT on our benchmark tasks, and compare the resulting models to different variants of Word2Vec token embeddings, BiLSTM and Transformer models, as well as published state-of-the-art models, showing that CuBERT outperforms them all, even with shorter training, and with fewer labeled examples.
1 code implementation • NeurIPS 2019 • Rahul Gupta, Aditya Kanade, Shirish Shevade
In this work, we present NeuralBugLocator, a deep learning based technique, that can localize the bugs in a faulty program with respect to a failing test, without even running the program.
no code implementations • 25 Sep 2019 • Sumanth Dathathri, Johannes Welbl, Krishnamurthy (Dj) Dvijotham, Ramana Kumar, Aditya Kanade, Jonathan Uesato, Sven Gowal, Po-Sen Huang, Pushmeet Kohli
Formal verification of machine learning models has attracted attention recently, and significant progress has been made on proving simple properties like robustness to small perturbations of the input features.
no code implementations • 25 Sep 2019 • Aditya Kanade, Petros Maniatis, Gogul Balakrishnan, Kensen Shi
A major advancement in natural-language understanding has been the use of pre-trained token embeddings; BERT and other works have further shown that pre-trained contextual embeddings can be extremely powerful and can be finetuned effectively for a variety of downstream supervised tasks.
no code implementations • 28 May 2019 • Rahul Gupta, Aditya Kanade, Shirish Shevade
To localize the bugs, we analyze the trained network using a state-of-the-art neural prediction attribution technique and see which lines of the programs make it predict the test outcomes.
no code implementations • 22 May 2019 • Soham Pal, Yash Gupta, Aditya Shukla, Aditya Kanade, Shirish Shevade, Vinod Ganapathy
Machine learning models trained on confidential datasets are increasingly being deployed for profit.
2 code implementations • ICLR 2019 • Marko Vasic, Aditya Kanade, Petros Maniatis, David Bieber, Rishabh Singh
We show that it is beneficial to train a model that jointly and directly localizes and repairs variable-misuse bugs.
no code implementations • 11 Jun 2018 • Ketan Patil, Aditya Kanade
AFL performs extremely well in fuzz testing large applications and finding critical vulnerabilities, but AFL involves a lot of heuristics while deciding the favored test case(s), skipping test cases during fuzzing, assigning fuzzing iterations to test case(s).
no code implementations • 13 Apr 2018 • Ishan Rastogi, Aditya Kanade, Shirish Shevade
In this work, we propose an automated method to identify semantic bugs in student programs, called ATAS, which builds upon the recent advances in both symbolic execution and active learning.
1 code implementation • 31 Jan 2018 • Rahul Gupta, Aditya Kanade, Shirish Shevade
Novice programmers often struggle with the formal syntax of programming languages.
Ranked #4 on Program Repair on DeepFix
1 code implementation • 4 Feb 2017 • Rahul Gupta, Soham Pal, Aditya Kanade, Shirish Shevade
The problem of automatically fixing programming errors is a very active research topic in software engineering.