Search Results for author:
Found 47 papers, 20 papers with code
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
Large Language Models (LLMs) applied to code-related applications have emerged as a prominent field, attracting significant interest from both academia and industry.
The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?
In this work, we focus on these counterfeit samples: programs sampled from a language model that 1) have a high enough log-probability to be generated at a moderate temperature and 2) pass weak correctness checks.
CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
The best setup, GPT-4 with chain of thought (CoT), achieves a pass@1 of 75% and 81% on input and output prediction, respectively.
LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers
Logical reasoning, i. e., deductively inferring the truth value of a conclusion from a set of premises, is an important task for artificial intelligence with wide potential impacts on science, mathematics, and society.
Learning a Hierarchical Planner from Humans in Multiple Generations
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.
Is Self-Repair a Silver Bullet for Code Generation?
We hypothesize that this is because self-repair is bottlenecked by the model's ability to provide feedback on its own code; using a stronger model to artificially boost the quality of the feedback, we observe substantially larger performance gains.
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.
SPARLING: Learning Latent Representations with Extremely Sparse Activations
Real-world processes often contain intermediate state that can be modeled as an extremely sparse tensor.
Top-Down Synthesis for Library Learning
This paper introduces corpus-guided top-down synthesis as a mechanism for synthesizing library functions that capture common functionality from a corpus of programs in a domain specific language (DSL).
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.
LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions
Humans tame the complexity of mathematical reasoning by developing hierarchies of abstractions.
ObSynth: An Interactive Synthesis System for Generating Object Models from Natural Language Specifications
We introduce ObSynth, an interactive system leveraging the domain knowledge embedded in large language models (LLMs) to help users design object models from high level natural language prompts.
Neurosymbolic Programming for Science
Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery.
JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints
Physical products are often complex assemblies combining a multitude of 3D parts modeled in computer-aided design (CAD) software.
AutumnSynth: Synthesis of Reactive Programs with Structured Latent State
The human ability to efficiently discover causal theories of their environments from observations is a feat of nature that remains elusive in machines.
Program Synthesis Guided Reinforcement Learning for Partially Observed Environments
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.
Neurosymbolic Transformers for Multi-Agent Communication
We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication.
Representing Partial Programs with Blended Abstract Semantics
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.
Causal Inductive Synthesis Corpus
We introduce the Causal Inductive Synthesis Corpus (CISC) -- a manually constructed collection of interactive domains.
Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences
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.
Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Reconstruction
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.
Program Synthesis with Pragmatic Communication
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.
Verifiably Safe Exploration for End-to-End Reinforcement Learning
We also prove that our method of enforcing the safety constraints preserves all safe policies from the original environment.
DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning
It builds expertise by creating programming languages for expressing domain concepts, together with neural networks to guide the search for programs within these languages.
Synthesizing Programmatic Policies that Inductively Generalize
We show that our algorithm can be used to learn policies that inductively generalize to novel environments, whereas traditional neural network policies fail to do so.
Learning Compositional Rules via Neural Program Synthesis
Many aspects of human reasoning, including language, require learning rules from very little data.
Write, Execute, Assess: Program Synthesis with a REPL
We present a neural program synthesis approach integrating components which write, execute, and assess code to navigate the search space of possible programs.
Deductive Optimization of Relational Data Storage
Optimizing the physical data storage and retrieval of data are two key database management problems.
Programming Languages Databases
Learning to Infer Program Sketches
Our goal is to build systems which write code automatically from the kinds of specifications humans can most easily provide, such as examples and natural language instruction.
Probabilistic Verification of Fairness Properties via Concentration
As machine learning systems are increasingly used to make real world legal and financial decisions, it is of paramount importance that we develop algorithms to verify that these systems do not discriminate against minorities.
Library Learning for Neurally-Guided Bayesian Program Induction
Successful approaches to program induction require a hand-engineered domain-specific language (DSL), constraining the space of allowed programs and imparting prior knowledge of the domain.
Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction
Successful approaches to program induction require a hand-engineered domain-specific language (DSL), constraining the space of allowed programs and imparting prior knowledge of the domain.
Verifiable Reinforcement Learning via Policy Extraction
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.
The Three Pillars of Machine Programming
In this position paper, we describe our vision of the future of machine programming through a categorical examination of three pillars of research.
Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections
We argue that such a correction is a useful way to provide feedback to a user when the network's output is different from a desired output.
REAS: Combining Numerical Optimization with SAT Solving
In this paper, we present ReaS, a technique that combines numerical optimization with SAT solving to synthesize unknowns in a program that involves discrete and floating point computation.
Learning to select examples for program synthesis
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.
SyGuS-Comp 2017: Results and Analysis
Syntax-Guided Synthesis (SyGuS) is the computational problem of finding an implementation f that meets both a semantic constraint given by a logical formula phi in a background theory T, and a syntactic constraint given by a grammar G, which specifies the allowed set of candidate implementations.
Selecting Representative Examples for Program Synthesis
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.
Capturing the Future by Replaying the Past
Along the way, we explain delimited continuations and monadic reflection, show how the Filinski construction lets thermometer continuations express any monadic effect, share an elegant special-case for nondeterminism, and discuss why our construction is not prevented by theoretical results that exceptions and state cannot macro-express continuations.
Programming Languages
Learning to Infer Graphics Programs from Hand-Drawn Images
These drawing primitives are like a trace of the set of primitive commands issued by a graphics program.
One Tool, Many Languages: Language-Parametric Transformation with Incremental Parametric Syntax
We present a new approach for building source-to-source transformations that can run on multiple programming languages, based on a new way of representing programs called incremental parametric syntax.
Programming Languages D.3.4; D.3.1
Learning to Acquire Information
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.
Sampling for Bayesian Program Learning
Towards learning programs from data, we introduce the problem of sampling programs from posterior distributions conditioned on that data.
SyGuS-Comp 2016: Results and Analysis
Syntax-Guided Synthesis (SyGuS) is the computational problem of finding an implementation f that meets both a semantic constraint given by a logical formula $\varphi$ in a background theory T, and a syntactic constraint given by a grammar G, which specifies the allowed set of candidate implementations.
sk_p: a neural program corrector for MOOCs
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.
Unsupervised Learning by Program Synthesis
We introduce an unsupervised learning algorithmthat combines probabilistic modeling with solver-based techniques for program synthesis. We apply our techniques to both a visual learning domain and a language learning problem, showing that our algorithm can learn many visual concepts from only a few examplesand that it can recover some English inflectional morphology. Taken together, these results give both a new approach to unsupervised learning of symbolic compositional structures, and a technique for applying program synthesis tools to noisy data.
