Songming Liu

9 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 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (21)

Venues

ICML (6) NeurIPS (2) ICLR (1)

Top co-authors

Hang Su (9) Jun Zhu (8) Zhongkai Hao (6) Chengyang Ying (5) Ze Cheng (4) Chang Su (3) Hengkai Tan (2) Jiachen Yao (2) Jian Song (2) Zhengyi Wang (2)

Research topics

Deep Learning (8) Machine Learning (7) Application Areas (6) Architectures (6) Artificial Intelligence (4) Core AI (4) Mathematics & Optimization (3) Learning Types (3) Mathematics (3) Techniques (3) Models (2) Optimization & Theory (2) Reinforcement Learning (1) Robotics (1) Applications (1)

Keywords

partial differential equation (5) neural operator (3) domain decomposition (2) neural network optimization (2) transformer architecture (2) physics-informed neural network (2) scientific machine learning (2) pdes (2) diffusion model (1) boundary condition (1) k-d tree (1) frequency domain (1) attention mechanism (1) short-time fourier transform (1) foundation model (1) physics simulation (1) operator learning (1) geometric learning (1) scientific computing (1) fast fourier transform (1)

Papers

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation ICLR 2025 DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training ICML 2024 Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning ICML 2024 PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs NeurIPS 2024 Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations ICML 2024 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 NUNO: A General Framework for Learning Parametric PDEs with Non-Uniform Data ICML 2023 A Unified Hard-Constraint Framework for Solving Geometrically Complex PDEs NeurIPS 2022