no code implementations • 15 Jun 2023 • Sarah J. Zhang, Samuel Florin, Ariel N. Lee, Eamon Niknafs, Andrei Marginean, Annie Wang, Keith Tyser, Zad Chin, Yann Hicke, Nikhil Singh, Madeleine Udell, Yoon Kim, Tonio Buonassisi, Armando Solar-Lezama, Iddo Drori
We curate a comprehensive dataset of 4, 550 questions and solutions from problem sets, midterm exams, and final exams across all MIT Mathematics and Electrical Engineering and Computer Science (EECS) courses required for obtaining a degree.
no code implementations • 22 Nov 2022 • Vitali Petsiuk, Alexander E. Siemenn, Saisamrit Surbehera, Zad Chin, Keith Tyser, Gregory Hunter, Arvind Raghavan, Yann Hicke, Bryan A. Plummer, Ori Kerret, Tonio Buonassisi, Kate Saenko, Armando Solar-Lezama, Iddo Drori
For example, asking a model to generate a varying number of the same object to measure its ability to count or providing a text prompt with several objects that each have a different attribute to identify its ability to match objects and attributes correctly.
no code implementations • 11 Jun 2022 • Iddo Drori, Sarah J. Zhang, Reece Shuttleworth, Sarah Zhang, Keith Tyser, Zad Chin, Pedro Lantigua, Saisamrit Surbehera, Gregory Hunter, Derek Austin, Leonard Tang, Yann Hicke, Sage Simhon, Sathwik Karnik, Darnell Granberry, Madeleine Udell
We curate a dataset and benchmark of questions from machine learning final exams available online and code for answering these questions and generating new questions.
1 code implementation • 31 Dec 2021 • Iddo Drori, Sarah Zhang, Reece Shuttleworth, Leonard Tang, Albert Lu, Elizabeth Ke, Kevin Liu, Linda Chen, Sunny Tran, Newman Cheng, Roman Wang, Nikhil Singh, Taylor L. Patti, Jayson Lynch, Avi Shporer, Nakul Verma, Eugene Wu, Gilbert Strang
We automatically synthesize programs using few-shot learning and OpenAI's Codex transformer and execute them to solve course problems at 81% automatic accuracy.
1 code implementation • 16 Nov 2021 • Woonghee Han, Randall A. Pietersen, Rafael Villamor-Lora, Matthew Beveridge, Nicola Offeddu, Theodore Golfinopoulos, Christian Theiler, James L. Terry, Earl S. Marmar, Iddo Drori
The analysis of turbulence in plasmas is fundamental in fusion research.
no code implementations • 16 Nov 2021 • Iddo Drori, Nakul Verma
We solve MIT's Linear Algebra 18. 06 course and Columbia University's Computational Linear Algebra COMS3251 courses with perfect accuracy by interactive program synthesis.
no code implementations • 16 Nov 2021 • Leonard Tang, Elizabeth Ke, Nikhil Singh, Nakul Verma, Iddo Drori
Our work is the first to introduce a new dataset of university-level probability and statistics problems and solve these problems in a scalable fashion using the program synthesis capabilities of large language models.
no code implementations • 3 Nov 2021 • Iddo Drori, Yamuna Krishnamurthy, Remi Rampin, Raoni de Paula Lourenco, Jorge Piazentin Ono, Kyunghyun Cho, Claudio Silva, Juliana Freire
We introduce AlphaD3M, an automatic machine learning (AutoML) system based on meta reinforcement learning using sequence models with self play.
no code implementations • 30 Oct 2021 • Ellen Park, Jae Deok Kim, Nadege Aoki, Yumeng Melody Cao, Yamin Arefeen, Matthew Beveridge, David Nicholson, Iddo Drori
We trained our neural networks on observations from the Global Ocean Ship-Based Hydrographic Investigations Program (GO-SHIP) and use dropout regularization to provide uncertainty bounds around our predicted values.
no code implementations • 29 Oct 2021 • Glenn Liu, Peidong Wang, Matthew Beveridge, Young-Oh Kwon, Iddo Drori
Atlantic Multidecadal Variability (AMV) describes variations of North Atlantic sea surface temperature with a typical cycle of between 60 and 70 years.
no code implementations • 13 Oct 2021 • Junyi Huang, Maxwell Benjamin Strome, Ian Jenkins, Parker Williams, Bo Feng, Yaning Wang, Roman Wang, Vaibhav Bagri, Newman Cheng, Iddo Drori
Kinship verification is the task of determining whether a parent-child, sibling, or grandparent-grandchild relationship exists between two people and is important in social media applications, forensic investigations, finding missing children, and reuniting families.
no code implementations • 6 Oct 2021 • Sarah Mokhtar, Matthew Beveridge, Yumeng Cao, Iddo Drori
Urban planners and policy makers face the challenge of creating livable and enjoyable cities for larger populations in much denser urban conditions.
no code implementations • 19 Aug 2021 • Kyle Lennon, Katharina Fransen, Alexander O'Brien, Yumeng Cao, Matthew Beveridge, Yamin Arefeen, Nikhil Singh, Iddo Drori
In order to demonstrate the broad applicability of our system, we generate step-by-step building instructions and animations for LEGO models of objects and human faces.
1 code implementation • 2 Jul 2021 • Sunny Tran, Pranav Krishna, Ishan Pakuwal, Prabhakar Kafle, Nikhil Singh, Jayson Lynch, Iddo Drori
Our system demonstrates an overall accuracy of 96% for open-response questions and 97% for multiple-choice questions, compared with MIT students' average of 93%, achieving grade A performance in the course, all in real-time.
no code implementations • 25 Jun 2021 • Nikhil Singh, Brandon Kates, Jeff Mentch, Anant Kharkar, Madeleine Udell, Iddo Drori
This work improves the quality of automated machine learning (AutoML) systems by using dataset and function descriptions while significantly decreasing computation time from minutes to milliseconds by using a zero-shot approach.
1 code implementation • 28 May 2021 • Alexander E. Siemenn, Evyatar Shaulsky, Matthew Beveridge, Tonio Buonassisi, Sara M. Hashmi, Iddo Drori
Generating droplets from a continuous stream of fluid requires precise tuning of a device to find optimized control parameter conditions.
no code implementations • 6 May 2021 • Alexander E. Siemenn, Matthew Beveridge, Tonio Buonassisi, Iddo Drori
Thus, in this work, we develop a computer vision-driven Bayesian optimization framework for optimizing the deposited droplet structures from an inkjet printer such that it is tuned to perform high-throughput experimentation on semiconductor materials.
1 code implementation • ICCV 2021 • Nikhil Singh, Jeff Mentch, Jerry Ng, Matthew Beveridge, Iddo Drori
Measuring the acoustic characteristics of a space is often done by capturing its impulse response (IR), a representation of how a full-range stimulus sound excites it.
no code implementations • 1 Jan 2021 • Iddo Drori, Brandon Kates, Anant Kharkar, Lu Liu, Qiang Ma, Jonah Deykin, Nihar Sidhu, Madeleine Udell
We train a graph neural network in which each node represents a dataset to predict the best machine learning pipeline for a new test dataset.
1 code implementation • 1 Dec 2020 • Eric Bolton, Alex Calderwood, Niles Christensen, Jerome Kafrouni, Iddo Drori
Automatically generating debates is a challenging task that requires an understanding of arguments and how to negate or support them.
no code implementations • NeurIPS Workshop LMCA 2020 • Iddo Drori, Brandon J Kates, William R. Sickinger, Anant Girish Kharkar, Brenda Dietrich, Avi Shporer, Madeleine Udell
We approximate a Traveling Salesman Problem (TSP) three orders of magnitude larger than the largest known benchmark, increasing the number of nodes from millions to billions.
no code implementations • 14 Jul 2020 • Nick Lamm, Shashank Jaiprakash, Malavika Srikanth, Iddo Drori
In this work we show that semi-supervised models for vehicle trajectory prediction significantly improve performance over supervised models on state-of-the-art real-world benchmarks.
no code implementations • 6 Jun 2020 • Iddo Drori, Anant Kharkar, William R. Sickinger, Brandon Kates, Qiang Ma, Suwen Ge, Eden Dolev, Brenda Dietrich, David P. Williamson, Madeleine Udell
Combinatorial optimization algorithms for graph problems are usually designed afresh for each new problem with careful attention by an expert to the problem structure.
no code implementations • 18 Nov 2019 • Michael Diodato, Yu Li, Antonia Lovjer, Minsu Yeom, Albert Song, Yiyang Zeng, Abhay Khosla, Benedikt Schifferer, Manik Goyal, Iddo Drori
Predicting vehicle trajectories, angle and speed is important for safe and comfortable driving.
2 code implementations • 12 Nov 2019 • Qiang Ma, Suwen Ge, Danyang He, Darshan Thaker, Iddo Drori
Furthermore, to approximate solutions to constrained combinatorial optimization problems such as the TSP with time windows, we train hierarchical GPNs (HGPNs) using RL, which learns a hierarchical policy to find an optimal city permutation under constraints.
Ranked #2 on Traveling Salesman Problem on TSPLIB
3 code implementations • 9 Nov 2019 • Iddo Drori, Darshan Thaker, Arjun Srivatsa, Daniel Jeong, Yueqi Wang, Linyong Nan, Fan Wu, Dimitri Leggas, Jinhao Lei, Weiyi Lu, Weilong Fu, Yuan Gao, Sashank Karri, Anand Kannan, Antonio Moretti, Mohammed AlQuraishi, Chen Keasar, Itsik Pe'er
Our dataset consists of amino acid sequences, Q8 secondary structures, position specific scoring matrices, multiple sequence alignment co-evolutionary features, backbone atom distance matrices, torsion angles, and 3D coordinates.
1 code implementation • 23 Oct 2019 • Antonia Lovjer, Minsu Yeom, Benedikt D. Schifferer, Iddo Drori
In this work we predict vehicle speed and steering angle given camera image frames.
no code implementations • 23 Oct 2019 • Michael Diodato, Yu Li, Manik Goyal, Iddo Drori
Autonomous driving has a significant impact on society.
1 code implementation • 10 Oct 2019 • Samuel Sharpe, Jin Yan, Fan Wu, Iddo Drori
Given the complete query, we fine tune a BERT embedding for estimating probabilities of a broad set of instances.
1 code implementation • 8 Oct 2019 • Prerna Kashyap, Samrat Phatale, Iddo Drori
Painting captions are often dry and simplistic which motivates us to describe a painting creatively in the style of Shakespearean prose.
2 code implementations • 8 Oct 2019 • Iddo Drori, Lu Liu, Yi Nian, Sharath C. Koorathota, Jie S. Li, Antonio Khalil Moretti, Juliana Freire, Madeleine Udell
We use these embeddings in a neural architecture to learn the distance between best-performing pipelines.
1 code implementation • 20 Sep 2019 • Antonio Khalil Moretti, Zizhao Wang, Luhuan Wu, Iddo Drori, Itsik Pe'er
We apply SVO to three nonlinear latent dynamics tasks and provide statistics to rigorously quantify the predictions of filtered and smoothed objectives.
no code implementations • 24 May 2019 • Iddo Drori, Yamuna Krishnamurthy, Raoni Lourenco, Remi Rampin, Kyunghyun Cho, Claudio Silva, Juliana Freire
Automatic machine learning is an important problem in the forefront of machine learning.
2 code implementations • 17 Nov 2018 • Iddo Drori, Isht Dwivedi, Pranav Shrestha, Jeffrey Wan, Yueqi Wang, Yunchu He, Anthony Mazza, Hugh Krogh-Freeman, Dimitri Leggas, Kendal Sandridge, Linyong Nan, Kaveri Thakoor, Chinmay Joshi, Sonam Goenka, Chen Keasar, Itsik Pe'er
In the spirit of reproducible research we make our data, models and code available, aiming to set a gold standard for purity of training and testing sets.