Wee Sun Lee lists you as their PhD student. Claim this profile to confirm it and keep the rest of your record right.
Claim this profileAcademic lineage
View as a treeAdvisors
Works13 from public data
- Tell2Design: A Dataset for Language-Guided Floor Plan Generation51
This work considers the task of generating designs directly from natural language descriptions, and considers floor plan generation as the initial research area, and introduces a novel dataset, Tell2Design, which contains more than 80k floor plan designs associated with natural language instructions.
- Hierarchical Neural Constructive Solver for Real-world TSP Scenarios17
This paper introduces realistic Traveling Salesman Problem (TSP) scenarios relevant to industrial settings and proposes integrating a learnable choice layer inspired by Hypernetworks to prioritize choices based on the current location, and a learnable approximate clustering algorithm inspired by the Expectation-Maximization algorithm to facilitate grouping the unvisited cities.
- Constrained Layout Generation with Factor Graphs14
This paper addresses the challenge of object-centric lay-out generation under spatial constraints, seen in multi-ple domains including floorplan design process, with a factor graph based approach with four latent variable nodes for each room, and a factor node for each constraint.
- PF-GNN: Differentiable particle filtering based approximation of universal graph representations14
This work proposes to make GNNs universal by guiding the learning process with exact isomorphism solver techniques which operate on the paradigm of Individualization and Refinement (IR), a method to artificially introduce asymmetry and further refine the coloring when 1-WL stops.
- SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy9
This work advances the Multi-Task VRP setting to the more realistic yet challenging Multi-Task Multi-Distribution VRP setting, and introduces SHIELD, a novel model that leverages both sparsity and hierarchy principles.
- Visual Relationship Detection with Low Rank Non-Negative Tensor Decomposition9
A novel technique of learning conditional triplet distributions in the form of their normalized low rank non-negative tensor decompositions is introduced to efficiently learn higher order discrete multimodal distributions and at the same time keep the parameter size manageable.
- Graph Representation Learning with Individualization and Refinement4
This work follows the classical approach of Individualization and Refinement (IR), a technique followed by most practical isomorphism solvers and outperforms prominent 1-WL GNN models as well as competitive higher-order baselines on several benchmark synthetic and real datasets.
- Differentiable Cluster Graph Neural Network3
This work adopts an entropy regularized objective function and proposes an iterative optimization process, alternating between solving for the cluster assignments and updating the node/cluster-node embeddings, that can effectively capture both local and global information.
- 1
- Improving Molecular Force Fields with Minimal Temporal Information–
This work presents a novel training strategy called FRAMES, that use an auxiliary loss function for exploiting the temporal relationships within MD trajectories to improve the accuracy of the model, and provides evidence that for distilling physical priors of atomic systems, more temporal data is not always better.
- Efficient Global Message Passing for Heterophilous Graphs–
The proposed Prototype Mediated GNN (PM-GNN), a novel framework which efficiently captures global feature information using class prototypes, is proposed, which can scale to large graphs, outperforming strong baselines on multiple heterophilous datasets.
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.