papers

Publications (32)

cs.LG2020

GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation

Marc Brockschmidt

This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM). Many standard GNN variants propagate information along the edges of a graph b…

cs.LG2016

TerpreT: A Probabilistic Programming Language for Program Induction

Alexander L. Gaunt, Marc Brockschmidt, Rishabh Singh +4

We study machine learning formulations of inductive program synthesis; given input-output examples, we try to synthesize source code that maps inputs to corresponding outputs. Our…

cs.LG2019

Program Synthesis and Semantic Parsing with Learned Code Idioms

Richard Shin, Miltiadis Allamanis, Marc Brockschmidt +1

Program synthesis of general-purpose source code from natural language specifications is challenging due to the need to reason about high-level patterns in the target program and l…

cs.LG2017

Gated Graph Sequence Neural Networks

Yujia Li, Daniel Tarlow, Marc Brockschmidt +1

Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning t…

cs.LG2020

CodeSearchNet Challenge: Evaluating the State of Semantic Code Search

Hamel Husain, Ho-Hsiang Wu, Tiferet Gazit +2

Semantic code search is the task of retrieving relevant code given a natural language query. While related to other information retrieval tasks, it requires bridging the gap betwee…

cs.PL2017

Differentiable Functional Program Interpreters

John K. Feser, Marc Brockschmidt, Alexander L. Gaunt +1

Programming by Example (PBE) is the task of inducing computer programs from input-output examples. It can be seen as a type of machine learning where the hypothesis space is the se…

cs.LO2015

Compositional Safety Verification with Max-SMT

Marc Brockschmidt, Daniel Larraz, Albert Oliveras +2

We present an automated compositional program verification technique for safety properties based on conditional inductive invariants. For a given program part (e.g., a single loop)…

stat.ML2023

Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics

Leon Klein, Andrew Y. K. Foong, Tor Erlend Fjelde +5

Molecular dynamics (MD) simulation is a widely used technique to simulate molecular systems, most commonly at the all-atom resolution where equations of motion are integrated with…

cs.LG2021

Self-Supervised Bug Detection and Repair

Miltiadis Allamanis, Henry Jackson-Flux, Marc Brockschmidt

Machine learning-based program analyses have recently shown the promise of integrating formal and probabilistic reasoning towards aiding software development. However, in the absen…

cs.LO2014

CTL+FO Verification as Constraint Solving

Tewodros A. Beyene, Marc Brockschmidt, Andrey Rybalchenko

Expressing program correctness often requires relating program data throughout (different branches of) an execution. Such properties can be represented using CTL+FO, a logic that a…

cs.LG2020

Copy that! Editing Sequences by Copying Spans

Sheena Panthaplackel, Miltiadis Allamanis, Marc Brockschmidt

Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code. In this paper, we argue t…

cs.LG2022

Learning to Complete Code with Sketches

Daya Guo, Alexey Svyatkovskiy, Jian Yin +3

Code completion is usually cast as a language modelling problem, i.e., continuing an input in a left-to-right fashion. However, in practice, some parts of the completion (e.g., str…

cs.LG2017

SmartPaste: Learning to Adapt Source Code

Miltiadis Allamanis, Marc Brockschmidt

Deep Neural Networks have been shown to succeed at a range of natural language tasks such as machine translation and text summarization. While tasks on source code (ie, formal lang…

cs.LG2019

Generative Code Modeling with Graphs

Marc Brockschmidt, Miltiadis Allamanis, Alexander L. Gaunt +1

Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural,…

cs.LG2018

Learning to Represent Programs with Graphs

Miltiadis Allamanis, Marc Brockschmidt, Mahmoud Khademi

Learning tasks on source code (i.e., formal languages) have been considered recently, but most work has tried to transfer natural language methods and does not capitalize on the un…

cs.AI2022

Exploring Representation of Horn Clauses using GNNs (Extended Technical Report)

Chencheng Liang, Philipp Rümmer, Marc Brockschmidt

Learning program semantics from raw source code is challenging due to the complexity of real-world programming language syntax and due to the difficulty of reconstructing long-dist…

cs.SE2026

Customizing an LLM for Enterprise Software Engineering

Aditya Kini, Satish Chandra, Milad Hashemi +15

Enterprise software development is a continuous evolutionary process, characterized by incremental additions, architectural revisions, production deployments and rigorous maintenan…

cs.LG2019

Constrained Graph Variational Autoencoders for Molecule Design

Qi Liu, Miltiadis Allamanis, Marc Brockschmidt +1

Graphs are ubiquitous data structures for representing interactions between entities. With an emphasis on the use of graphs to represent chemical molecules, we explore the task of…

cs.LG2017

DeepCoder: Learning to Write Programs

Matej Balog, Alexander L. Gaunt, Marc Brockschmidt +2

We develop a first line of attack for solving programming competition-style problems from input-output examples using deep learning. The approach is to train a neural network to pr…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.LG2022

HEAT: Hyperedge Attention Networks

Dobrik Georgiev, Marc Brockschmidt, Miltiadis Allamanis

Learning from structured data is a core machine learning task. Commonly, such data is represented as graphs, which normally only consider (typed) binary relationships between pairs…

cs.LG2021

Analyzing Information Leakage of Updates to Natural Language Models

Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople +5

To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analy…

cs.CL2018

Robust Text-to-SQL Generation with Execution-Guided Decoding

Chenglong Wang, Kedar Tatwawadi, Marc Brockschmidt +4

We consider the problem of neural semantic parsing, which translates natural language questions into executable SQL queries. We introduce a new mechanism, execution guidance, to le…

cs.LG2019

Disentangling Interpretable Generative Parameters of Random and Real-World Graphs

Niklas Stoehr, Emine Yilmaz, Marc Brockschmidt +1

While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open p…

cs.LG2016

Summary - TerpreT: A Probabilistic Programming Language for Program Induction

Alexander L. Gaunt, Marc Brockschmidt, Rishabh Singh +4

We study machine learning formulations of inductive program synthesis; that is, given input-output examples, synthesize source code that maps inputs to corresponding outputs. Our k…

cs.LO2016

T2: Temporal Property Verification

Marc Brockschmidt, Byron Cook, Samin Ishtiaq +2

We present the open-source tool T2, the first public release from the TERMINATOR project. T2 has been extended over the past decade to support automatic temporal-logic proving tech…

cs.LG2018

Graph Partition Neural Networks for Semi-Supervised Classification

Renjie Liao, Marc Brockschmidt, Daniel Tarlow +3

We present graph partition neural networks (GPNN), an extension of graph neural networks (GNNs) able to handle extremely large graphs. GPNNs alternate between locally propagating i…

cs.LG2021

Structured Neural Summarization

Patrick Fernandes, Miltiadis Allamanis, Marc Brockschmidt

Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input. Based on the promising…

cs.LG2019

Learning to Represent Edits

Pengcheng Yin, Graham Neubig, Miltiadis Allamanis +2

We introduce the problem of learning distributed representations of edits. By combining a "neural editor" with an "edit encoder", our models learn to represent the salient informat…

cs.LO2020

Inferring Lower Runtime Bounds for Integer Programs

Florian Frohn, Matthias Naaf, Marc Brockschmidt +1

We present a technique to infer lower bounds on the worst-case runtime complexity of integer programs, where in contrast to earlier work, our approach is not restricted to tail-rec…

cs.LG2017

Differentiable Programs with Neural Libraries

Alexander L. Gaunt, Marc Brockschmidt, Nate Kushman +1

We develop a framework for combining differentiable programming languages with neural networks. Using this framework we create end-to-end trainable systems that learn to write inte…

cs.LG2024

Learning to Extend Molecular Scaffolds with Structural Motifs

Krzysztof Maziarz, Henry Jackson-Flux, Pashmina Cameron +5

Recent advancements in deep learning-based modeling of molecules promise to accelerate in silico drug discovery. A plethora of generative models is available, building molecules ei…