Takashi Maruyama
5 papers · 2022–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🗺️
Taxonomy Completionist
(10)
Venues
Top co-authors
Research topics
Keywords
graph neural network
(2)
message passing
(1)
machine learning
(1)
energy function
(1)
generative model
(1)
diffusion model
(1)
partial differential equation
(1)
surrogate model
(1)
dynamics model
(1)
inverse design
(1)
scientific machine learning
(1)
interatomic potential
(1)
compositional design
(1)
mesh refinement
(1)
deep learning surrogate model
(1)
latent global evolution
(1)
navier-stokes flow
(1)
cartesian tensor
(1)
atomistic simulation
(1)
over smoothing
(1)
Papers
Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching
ICML 2025
Compositional Generative Inverse Design
ICLR 2024
Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
NeurIPS 2024
Learning Controllable Adaptive Simulation for Multi-resolution Physics
ICLR 2023
Learning to Accelerate Partial Differential Equations via Latent Global Evolution
NeurIPS 2022