no code implementations • 9 Oct 2023 • Anirudh Khatry, Yasharth Bajpai, Priyanshu Gupta, Sumit Gulwani, Ashish Tiwari
The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and corpus elements are both natural language (NL) utterances (homogeneous) and the goal is to pick most relevant elements from the corpus in the Top-K, where K is large, such as 10, 25, 50 or even 100 (relaxed).
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 • 2 May 2023 • Anirudh Khatry, Joyce Cahoon, Jordan Henkel, Shaleen Deep, Venkatesh Emani, Avrilia Floratou, Sumit Gulwani, Vu Le, Mohammad Raza, Sherry Shi, Mukul Singh, Ashish Tiwari
Existing approaches have utilized data context in a limited way by simply adding relevant information from the input data into the prompts sent to the LLM.
no code implementations • 1 Nov 2022 • Ashish Tiwari, Sresth Tosniwal, Shanmuganathan Raman
Graph convolution networks (GCNs) have been enormously successful in learning representations over several graph-based machine learning tasks.
no code implementations • 25 Jul 2022 • Yuhao Zhang, Yasharth Bajpai, Priyanshu Gupta, Ameya Ketkar, Miltiadis Allamanis, Titus Barik, Sumit Gulwani, Arjun Radhakrishna, Mohammad Raza, Gustavo Soares, Ashish Tiwari
Our experiments show that Overwatch has 78% precision and that Overwatch not only completed edits when developers missed the opportunity to use the IDE tool support but also predicted new edits that have no tool support in the IDE.
no code implementations • 24 Jul 2022 • Rohan Bavishi, Harshit Joshi, José Pablo Cambronero Sánchez, Anna Fariha, Sumit Gulwani, Vu Le, Ivan Radicek, Ashish Tiwari
To address this problem, we developed LaMirage, a LAst-MIle RepAir-engine GEnerator that combines symbolic and neural techniques to perform last-mile repair in low-code formula languages.
no code implementations • 5 Jul 2022 • Ashish Tiwari, Shanmuganathan Raman
Despite the success of existing traditional and deep learning-based methods, it is still challenging due to: (i) the requirement of three or more differently illuminated images, (ii) the inability to model unknown general reflectance, and (iii) the requirement of accurate 3D ground truth surface normals and known lighting information for training.
2 code implementations • ICLR 2022 • Gabriel Poesia, Oleksandr Polozov, Vu Le, Ashish Tiwari, Gustavo Soares, Christopher Meek, Sumit Gulwani
Then, Synchromesh feeds the examples to a pre-trained language model and samples programs using Constrained Semantic Decoding (CSD): a general framework for constraining the output to a set of valid programs in the target language.
no code implementations • 3 Sep 2021 • Kia Rahmani, Mohammad Raza, Sumit Gulwani, Vu Le, Daniel Morris, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari
Examples provide a precise but incomplete specification, and natural language provides an ambiguous but more "complete" task description.
no code implementations • 30 Jul 2021 • Kaustubh Sadekar, Ashish Tiwari, Shanmuganathan Raman
In this work, we revisit shadow art using differentiable rendering based optimization frameworks to obtain the 3D sculpture from a set of shadow (binary) images and their corresponding projection information.
no code implementations • 27 Jan 2021 • Kaustubh Sadekar, Ashish Tiwari, Prajwal Singh, Shanmuganathan Raman
This work proposes LS-HDIB - a large-scale handwritten document image binarization dataset containing over a million document images that span numerous real-world scenarios.
no code implementations • 22 Jun 2020 • Ashish Tiwari, Arjun Radhakrishna, Sumit Gulwani, Daniel Perelman
In the context of interactive program synthesis, we use the above result to develop an {\em{active program learner}} that generates the significant inputs to pose as queries to the user in each iteration.
no code implementations • 12 Sep 2019 • Sumit Gulwani, Kunal Pathak, Arjun Radhakrishna, Ashish Tiwari, Abhishek Udupa
Programming-by-Example (PBE) systems synthesize an intended program in some (relatively constrained) domain-specific language from a small number of input-output examples provided by the user.
no code implementations • 23 Aug 2018 • Ankush Desai, Shromona Ghosh, Sanjit A. Seshia, Natarajan Shankar, Ashish Tiwari
SOTER provides language primitives to declaratively construct a RTA module consisting of an advanced, high-performance controller (uncertified), a safe, lower-performance controller (certified), and the desired safety specification.
no code implementations • NeurIPS 2018 • Marcell Vazquez-Chanlatte, Susmit Jha, Ashish Tiwari, Mark K. Ho, Sanjit A. Seshia
In this paper, we formulate the specification inference task as a maximum a posteriori (MAP) probability inference problem, apply the principle of maximum entropy to derive an analytic demonstration likelihood model and give an efficient approach to search for the most likely specification in a large candidate pool of specifications.
no code implementations • 26 Sep 2017 • Souradeep Dutta, Susmit Jha, Sriram Sanakaranarayanan, Ashish Tiwari
We demonstrate the effectiveness of the proposed approach for verification of NNs used in automated control as well as those used in classification.
no code implementations • 21 Dec 2016 • Anna Lukina, Lukas Esterle, Christian Hirsch, Ezio Bartocci, Junxing Yang, Ashish Tiwari, Scott A. Smolka, Radu Grosu
Inspired by Importance Splitting, the length of the horizon and the number of particles are chosen such that at least one particle reaches a next-level state, that is, a state where the cost decreases by a required delta from the previous-level state.