no code implementations • NeurIPS 2023 • Zhiao Huang, Feng Chen, Yewen Pu, Chunru Lin, Hao Su, Chuang Gan
Combining gradient-based trajectory optimization with differentiable physics simulation is an efficient technique for solving soft-body manipulation problems.
1 code implementation • 9 Nov 2023 • Saujas Vaduguru, Daniel Fried, Yewen Pu
Programming-by-example is the task of synthesizing a program that is consistent with a set of user-provided input-output examples.
no code implementations • 17 Oct 2023 • Leonardo Hernandez Cano, Yewen Pu, Robert D. Hawkins, Josh Tenenbaum, Armando Solar-Lezama
Compared to learning from demonstrations or experiences, programmatic learning allows the machine to acquire a novel skill as soon as the program is written, and, by building a library of programs, a machine can quickly learn how to perform complex tasks.
no code implementations • 11 Sep 2023 • Ruocheng Wang, Eric Zelikman, Gabriel Poesia, Yewen Pu, Nick Haber, Noah D. Goodman
Because of the prohibitive cost of generation with state-of-the-art LLMs, we consider a middle step to filter the set of hypotheses that will be implemented into programs: we either ask the LLM to summarize into a smaller set of hypotheses, or ask human annotators to select a subset of the hypotheses.
1 code implementation • 1 Sep 2023 • Yewen Pu, Saujas Vaduguru, Priyan Vaithilingam, Elena Glassman, Daniel Fried
We prove that for a pragmatic synthesizer that uses a single demonstration, our global ranking method exactly replicates RSA's ranked responses.
1 code implementation • NeurIPS 2023 • Di Huang, Ziyuan Nan, Xing Hu, Pengwei Jin, Shaohui Peng, Yuanbo Wen, Rui Zhang, Zidong Du, Qi Guo, Yewen Pu, Yunji Chen
We deploy ANPL on the Abstraction and Reasoning Corpus (ARC), a set of unique tasks that are challenging for state-of-the-art AI systems, showing it outperforms baseline programming systems that (a) without the ability to decompose tasks interactively and (b) without the guarantee that the modules can be correctly composed together.
Ranked #4 on Code Generation on HumanEval
1 code implementation • 21 Oct 2022 • Ning Shi, Bin Tang, Bo Yuan, Longtao Huang, Yewen Pu, Jie Fu, Zhouhan Lin
Text editing, such as grammatical error correction, arises naturally from imperfect textual data.
no code implementations • 5 Apr 2022 • Saujas Vaduguru, Kevin Ellis, Yewen Pu
Surprisingly, we find that the synthesizer assuming a factored approximation performs better than a synthesizer assuming an exact joint distribution when evaluated on natural human inputs.
2 code implementations • 15 Jun 2021 • Samuel Acquaviva, Yewen Pu, Marta Kryven, Theodoros Sechopoulos, Catherine Wong, Gabrielle E Ecanow, Maxwell Nye, Michael Henry Tessler, Joshua B. Tenenbaum
We present LARC, the \textit{Language-complete ARC}: a collection of natural language descriptions by a group of human participants who instruct each other on how to solve ARC tasks using language alone, which contains successful instructions for 88\% of the ARC tasks.
no code implementations • 19 Apr 2021 • Karl D. D. Willis, Pradeep Kumar Jayaraman, Joseph G. Lambourne, Hang Chu, Yewen Pu
Engineering sketches form the 2D basis of parametric Computer-Aided Design (CAD), the foremost modeling paradigm for manufactured objects.
1 code implementation • NeurIPS 2021 • Yichen David Yang, Jeevana Priya Inala, Osbert Bastani, Yewen Pu, Armando Solar-Lezama, Martin Rinard
Our results demonstrate that our approach can obtain the benefits of program-guided reinforcement learning without requiring the user to provide a new guiding program for every new task.
1 code implementation • NeurIPS 2020 • Jeevana Priya Inala, Yichen Yang, James Paulos, Yewen Pu, Osbert Bastani, Vijay Kumar, Martin Rinard, Armando Solar-Lezama
We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication.
no code implementations • ICLR 2021 • Maxwell Nye, Yewen Pu, Matthew Bowers, Jacob Andreas, Joshua B. Tenenbaum, Armando Solar-Lezama
In this search process, a key challenge is representing the behavior of a partially written program before it can be executed, to judge if it is on the right track and predict where to search next.
1 code implementation • 5 Oct 2020 • Karl D. D. Willis, Yewen Pu, Jieliang Luo, Hang Chu, Tao Du, Joseph G. Lambourne, Armando Solar-Lezama, Wojciech Matusik
Parametric computer-aided design (CAD) is a standard paradigm used to design manufactured objects, where a 3D shape is represented as a program supported by the CAD software.
no code implementations • 28 Sep 2020 • Karl Willis, Yewen Pu, Jieliang Luo, Hang Chu, Tao Du, Joseph Lambourne, Armando Solar-Lezama, Wojciech Matusik
We provide a dataset of 8, 625 designs, comprising sequential sketch and extrude modeling operations, together with a complementary environment called the Fusion 360 Gym, to assist with performing CAD reconstruction.
no code implementations • NeurIPS 2020 • Yewen Pu, Kevin Ellis, Marta Kryven, Josh Tenenbaum, Armando Solar-Lezama
Given a specification, we score a candidate program both on its consistency with the specification, and also whether a rational speaker would chose this particular specification to communicate that program.
1 code implementation • NeurIPS 2019 • Charith Mendis, Cambridge Yang, Yewen Pu, Dr.Saman Amarasinghe, Michael Carbin
We show that the learnt policy produces a vectorization scheme which is better than industry standard compiler heuristics both in terms of static measures and runtime performance.
no code implementations • NeurIPS 2019 • Kevin Ellis, Maxwell Nye, Yewen Pu, Felix Sosa, Josh Tenenbaum, Armando Solar-Lezama
We present a neural program synthesis approach integrating components which write, execute, and assess code to navigate the search space of possible programs.
1 code implementation • NeurIPS 2018 • Osbert Bastani, Yewen Pu, Armando Solar-Lezama
While deep reinforcement learning has successfully solved many challenging control tasks, its real-world applicability has been limited by the inability to ensure the safety of learned policies.
no code implementations • ICLR 2018 • Yewen Pu, Zachery Miranda, Armando Solar-Lezama, Leslie Pack Kaelbling
In this paper we address this challenge by constructing a representative subset of examples that is both small and is able to constrain the solver sufficiently.
1 code implementation • ICML 2018 • Yewen Pu, Zachery Miranda, Armando Solar-Lezama, Leslie Pack Kaelbling
Program synthesis is a class of regression problems where one seeks a solution, in the form of a source-code program, mapping the inputs to their corresponding outputs exactly.
1 code implementation • 20 Apr 2017 • Yewen Pu, Leslie P. Kaelbling, Armando Solar-Lezama
Finding the optimal subset of observations is intractable in general, thus we focus on the problem of active diagnosis, where the agent selects the next most-informative observation based on the results of previous observations.
no code implementations • 11 Jul 2016 • Yewen Pu, Karthik Narasimhan, Armando Solar-Lezama, Regina Barzilay
We present a novel technique for automatic program correction in MOOCs, capable of fixing both syntactic and semantic errors without manual, problem specific correction strategies.