research
∙
06/16/2023
Demystifying GPT Self-Repair for Code Generation
Large Language Models (LLMs) have shown remarkable aptitude in code gene...
share
research
∙
02/03/2023
SPARLING: Learning Latent Representations with Extremely Sparse Activations
Real-world processes often contain intermediate state that can be modele...
research
∙
11/29/2022
Top-Down Synthesis for Library Learning
This paper introduces corpus-guided top-down synthesis as a mechanism fo...
research
∙
11/22/2022
Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark
We provide a new multi-task benchmark for evaluating text-to-image model...
research
∙
11/16/2022
LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions
Humans tame the complexity of mathematical reasoning by developing hiera...
research
∙
10/20/2022
ObSynth: An Interactive Synthesis System for Generating Object Models from Natural Language Specifications
We introduce ObSynth, an interactive system leveraging the domain knowle...
research
∙
10/10/2022
Neurosymbolic Programming for Science
Neurosymbolic Programming (NP) techniques have the potential to accelera...
research
∙
06/15/2022
Searching Entangled Program Spaces
Many problem domains, including program synthesis and rewrite-based opti...
research
∙
06/13/2022
Metric Program Synthesis
We present a new domain-agnostic synthesis technique for generating prog...
research
∙
10/11/2021
Safe Human-Interactive Control via Shielding
Ensuring safety for human-interactive robotics is important due to the p...
research
∙
02/22/2021
Program Synthesis Guided Reinforcement Learning
A key challenge for reinforcement learning is solving long-horizon plann...
research
∙
01/05/2021
Neurosymbolic Transformers for Multi-Agent Communication
We study the problem of inferring communication structures that can solv...
research
∙
12/23/2020
Representing Partial Programs with Blended Abstract Semantics
Synthesizing programs from examples requires searching over a vast, comb...
research
∙
10/10/2020
Automatically Deriving Control-Flow Graph Generators from Operational Semantics
We develop the first theory of control-flow graphs from first principles...
research
∙
07/09/2020
Program Synthesis with Pragmatic Communication
Program synthesis techniques construct or infer programs from user-provi...
research
∙
07/07/2020
Computer-Aided Personalized Education
The shortage of people trained in STEM fields is becoming acute, and uni...
research
∙
07/02/2020
Verifiably Safe Exploration for End-to-End Reinforcement Learning
Deploying deep reinforcement learning in safety-critical settings requir...
research
∙
06/15/2020
DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning
Expert problem-solving is driven by powerful languages for thinking abou...
research
∙
03/12/2020
Learning Compositional Rules via Neural Program Synthesis
Many aspects of human reasoning, including language, require learning ru...
research
∙
12/29/2019
Synthesizing Queries via Interactive Sketching
We propose a novel approach to program synthesis, focusing on synthesizi...
research
∙
06/09/2019
Write, Execute, Assess: Program Synthesis with a REPL
We present a neural program synthesis approach integrating components wh...
research
∙
03/25/2019
The Random Conditional Distribution for Higher-Order Probabilistic Inference
The need to condition distributional properties such as expectation, var...
research
∙
03/08/2019
Deductive Optimization of Relational Data Storage
Optimizing the physical data storage and retrieval of data are two key d...
research
∙
02/17/2019
Learning to Infer Program Sketches
Our goal is to build systems which write code automatically from the kin...
research
∙
01/16/2019
Soft Constraints for Inference with Declarative Knowledge
We develop a likelihood free inference procedure for conditioning a prob...
research
∙
12/02/2018
Verifying Fairness Properties via Concentration
As machine learning systems are increasingly used to make real world leg...
research
∙
07/21/2018
Delta-Decision Procedures for Exists-Forall Problems over the Reals
Solving nonlinear SMT problems over real numbers has wide applications i...
research
∙
05/22/2018
Verifiable Reinforcement Learning via Policy Extraction
While deep reinforcement learning has successfully solved many challengi...
research
∙
03/20/2018
The Three Pillars of Machine Programming
In this position paper, we describe our vision of the future of machine ...
research
∙
03/20/2018
The Three Pillars of Machine-Based Programming
In this position paper, we describe our vision of the future of machine-...
research
∙
02/21/2018
Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections
The paper describes a new algorithm to generate minimal, stable, and sym...
research
∙
02/13/2018
REAS: Combining Numerical Optimization with SAT Solving
In this paper, we present ReaS, a technique that combines numerical opti...
research
∙
11/29/2017
SyGuS-Comp 2017: Results and Analysis
Syntax-Guided Synthesis (SyGuS) is the computational problem of finding ...
research
∙
11/09/2017
Learning to select examples for program synthesis
Program synthesis is a class of regression problems where one seeks a so...
research
∙
10/28/2017
Capturing the Future by Replaying the Past
Delimited continuations are the mother of all monads! So goes the slogan...
research
∙
07/30/2017
Learning to Infer Graphics Programs from Hand-Drawn Images
We introduce a model that learns to convert simple hand drawings into gr...
research
∙
07/14/2017
Incremental Parametric Syntax for Multi-Language Transformation
We present a new approach for building source-to-source transformations ...
research
∙
04/20/2017
Learning to Acquire Information
We consider the problem of diagnosis where a set of simple observations ...
research
∙
07/11/2016
sk_p: a neural program corrector for MOOCs
We present a novel technique for automatic program correction in MOOCs, ...
research
∙
04/08/2012