|
Research
My research focuses on developing machine learning models for solving constraint reasoning problems.
I am particularly interested in generative modeling approaches, including diffusion methods and Transformer-based architectures.
My work explores how these models can align their reasoning capabilities with the structure of constraints to generate valid and high-quality solutions.
|
Adapting iterative neural constraint heuristics as Large Neighbourhood Search.
|
Large Neighborhood Search meets Iterative Neural Constraint Heuristics (CPAIOR-2026)
Yudong W. Xu,
Wenhao Li,
Elias B. Khalil,
Scott Sanner
Paper
/
Code
|
Using graph hypernetworks to directly generate full neural-network weights.
|
Structure-Aware Graph Hypernetworks for Neural Program Synthesis (ICLR-2026)
Wenhao Li,
Yudong Xu,
Elias B. Khalil,
Scott Sanner
Paper
/
Code
|
Iteratively solving constraint reasoning problems with self-supervised Transformers.
|
Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction (ICML-2025)
Yudong W. Xu,
Wenhao Li,
Scott Sanner,
Elias B. Khalil
Paper
/
Poster
/
Slides
/
Code
|
Enhancing the vision transformer (ViT) architecture to solve the Abstraction and Reasoning Corpus.
|
Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects (TMLR-2025)
Wenhao Li,
Yudong Xu,
Scott Sanner,
Elias B. Khalil
Paper
/
Tweet
/
|
An exploration of LLMs' ability to solve the Abstraction and Reasoning Corpus.
|
LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations (TMLR-2024)
Yudong Xu,
Wenhao Li,
Pashootan Vaezipoor,
Scott Sanner,
Elias B. Khalil
In Transactions on Machine Learning Research
Website
/
Paper
/
Data
/
Tweet
/
|
A graph-based symbolic AI approach to solving the Abstraction and Reasoning Corpus.
|
Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus (AAAI-2023)
Yudong Xu,
Elias B. Khalil,
Scott Sanner
In Proceedings of the 37th AAAI Conference on Artificial Intelligence
Paper
/
Code
/
Poster
/
Slides
/
|
|
Services
|
Reviewer,
ICLR 2025-2026, ICML 2026, NeurIPS 2026, TMLR 2024-2026, IJCAI 2024, AAAI 2026
Teaching Assistant,
MIE369 - Introduction to Artificial Intelligence
, Winter 2024, 2025, 2026
Guest Lecturer,
MIE1516 - Structured Learning and Inference
, Fall 2025
|
|