Search Results for author:
Found 34 papers, 14 papers with code
Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models
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.
Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark
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.
From Human Days to Machine Seconds: Automatically Answering and Generating Machine Learning Final Exams
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.
A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level
We automatically synthesize programs using few-shot learning and OpenAI's Codex transformer and execute them to solve course problems at 81% automatic accuracy.
Tracking Blobs in the Turbulent Edge Plasma of a Tokamak Fusion Device
The analysis of turbulence in plasmas is fundamental in fusion research.
Solving Linear Algebra by Program Synthesis
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.
Solving Probability and Statistics Problems by Program Synthesis
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.
AlphaD3M: Machine Learning Pipeline Synthesis
We introduce AlphaD3M, an automatic machine learning (AutoML) system based on meta reinforcement learning using sequence models with self play.
Predicting Critical Biogeochemistry of the Southern Ocean for Climate Monitoring
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.
Predicting Atlantic Multidecadal Variability
Atlantic Multidecadal Variability (AMV) describes variations of North Atlantic sea surface temperature with a typical cycle of between 60 and 70 years.
Solving the Families In the Wild Kinship Verification Challenge by Program Synthesis
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.
Pedestrian Wind Factor Estimation in Complex Urban Environments
Urban planners and policy makers face the challenge of creating livable and enjoyable cities for larger populations in much denser urban conditions.
Image2Lego: Customized LEGO Set Generation from Images
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.
Solving Machine Learning Problems
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.
Privileged Zero-Shot AutoML
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.
A Machine Learning and Computer Vision Approach to Rapidly Optimize Multiscale Droplet Generation
Generating droplets from a continuous stream of fluid requires precise tuning of a device to find optimized control parameter conditions.
Online Preconditioning of Experimental Inkjet Hardware by Bayesian Optimization in Loop
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.
Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis
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.
Real-Time AutoML
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.
High Quality Real-Time Structured Debate Generation
Automatically generating debates is a challenging task that requires an understanding of arguments and how to negate or support them.
GalaxyTSP: A New Billion-Node Benchmark for TSP
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.
Vehicle Trajectory Prediction by Transfer Learning of Semi-Supervised Models
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.
Learning to Solve Combinatorial Optimization Problems on Real-World Graphs in Linear Time
Combinatorial optimization algorithms for graph problems are usually designed afresh for each new problem with careful attention by an expert to the problem structure.
Accurate Trajectory Prediction for Autonomous Vehicles
Predicting vehicle trajectories, angle and speed is important for safe and comfortable driving.
Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning
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
Accurate Protein Structure Prediction by Embeddings and Deep Learning Representations
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.
Using Segmentation Masks in the ICCV 2019 Learning to Drive Challenge
In this work we predict vehicle speed and steering angle given camera image frames.
Winning the ICCV 2019 Learning to Drive Challenge
Autonomous driving has a significant impact on society.
Visual Natural Language Query Auto-Completion for Estimating Instance Probabilities
Given the complete query, we fine tune a BERT embedding for estimating probabilities of a broad set of instances.
Prose for a Painting
Painting captions are often dry and simplistic which motivates us to describe a painting creatively in the style of Shakespearean prose.
AutoML using Metadata Language Embeddings
We use these embeddings in a neural architecture to learn the distance between best-performing pipelines.
Particle Smoothing Variational Objectives
We apply SVO to three nonlinear latent dynamics tasks and provide statistics to rigorously quantify the predictions of filtered and smoothed objectives.
Automatic Machine Learning by Pipeline Synthesis using Model-Based Reinforcement Learning and a Grammar
Automatic machine learning is an important problem in the forefront of machine learning.
High Quality Prediction of Protein Q8 Secondary Structure by Diverse Neural Network Architectures
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.
