Songming Liu
9 papers · 2022–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (3) π Cross-Pollinator (8) πΊοΈ Taxonomy Completionist (19) π§ Keyword Pioneer π Interdisciplinary Bridge
π
Keyword Champion
(2)
π
Trend Setter
Conferences
ICML (6)
NIPS (2)
ICLR (1)
Top co-authors
Keywords
partial differential equation
(5)
domain decomposition
(2)
neural operator
(2)
neural network optimization
(2)
physics-informed neural network
(2)
scientific machine learning
(2)
geometric learning
(1)
physics simulation
(1)
non-uniform datum
(1)
finite element method
(1)
surrogate modeling
(1)
geometric gating
(1)
gradient momentum
(1)
multiscale training
(1)
numerical analysis
(1)
neural network
(1)
loss reweighting
(1)
multi-scale training
(1)
irregular mesh
(1)
transformer architecture
(1)
Papers
RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
ICLR 2025
Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations
ICML 2024
DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
ICML 2024
PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
NIPS 2024
Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning
ICML 2024
NUNO: A General Framework for Learning Parametric PDEs with Non-Uniform Data
ICML 2023
GNOT: A General Neural Operator Transformer for Operator Learning
ICML 2023
MultiAdam: Parameter-wise Scale-invariant Optimizer for Multiscale Training of Physics-informed Neural Networks
ICML 2023
A Unified Hard-Constraint Framework for Solving Geometrically Complex PDEs
NIPS 2022