科学仿真论文趋势 2023–2026

PDE 与仿真加速

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 167 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

科学仿真论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023644216
202416115638
20252458845
2026251025868

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部科学仿真论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 52 篇，第 1 / 2 页

  1. ICML 2026Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation
  2. ICML 2026Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell Snapshots
  3. ICML 2026Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression
  4. ICML 2026Conformal C2ST: Turning weak classifiers into strong two-sample tests
  5. ICML 2026ePC: Fast and Deep Predictive Coding in Digital Simulation
  6. ICML 2026Euler–Poincaré Neural Dynamics: A Geometric-Mechanics Framework for Scientific Simulation
  7. ICML 2026Flow Matching Calibration for Simulation-Based Inference under Model Misspecification
  8. ICML 2026Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls
  9. ICML 2026GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training
  10. ICML 2026Grounding LLMs in Scientific Discovery via Embodied Actions
  11. ICML 2026History-Bootstrapped Flow Matching for Inverse Boiling Reconstruction
  12. ICML 2026Hyperbolic Neural Operator
  13. ICML 2026Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation
  14. ICML 2026Learning Biophysical Models of Large-Scale Multineuronal Data To Enable Precise Neurostimulation
  15. ICML 2026MeshTok: Efficient Multi-Scale Tokenization for Scalable PDE Transformers
  16. ICML 2026Minimum Distance Summaries for Robust Neural Posterior Estimation
  17. ICML 2026PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-Resolution
  18. ICML 2026RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections
  19. ICML 2026SafeLab: An Interactive High-Fidelity Benchmark for Embodied Safety in Scientific Robotics
  20. ICML 2026Scalable Simulation-Based Model Inference with Test-Time Complexity Control
  21. ICML 2026ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management
  22. ICML 2026SciNet: Evaluating AI Agents in Relation-Aware Scientific Literature Retrieval
  23. ICML 2026Simple yet Effective: Low-Rank Spatial Attention for Neural Operators
  24. ICML 2026Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs
  25. ICML 2026Towards Diverse Scientific Hypothesis Search with Large Language Models
  26. ICML 2025Addressing Misspecification in Simulation-based Inference through Data-driven Calibration
  27. ICML 2025BARNN: A Bayesian Autoregressive and Recurrent Neural Network
  28. ICML 2025Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problems
  29. ICML 2025Latent Mamba Operator for Partial Differential Equations
  30. ICML 2025Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models
  31. ICML 2025SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields
  32. ICML 2025Schwarz–Schur Involution: Lightspeed Differentiable Sparse Linear Solvers
  33. ICML 2025Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE Solvers
  34. ICML 2024All-in-one simulation-based inference
  35. ICML 2024Finite Volume Features, Global Geometry Representations, and Residual Training for Deep Learning-based CFD Simulation
  36. ICML 2024LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery
  37. ICML 2024Mechanistic Neural Networks for Scientific Machine Learning
  38. ICML 2024Operator SVD with Neural Networks via Nested Low-Rank Approximation
  39. ICML 2024Orthogonal Bootstrap: Efficient Simulation of Input Uncertainty
  40. ICML 2024Position: Embracing Negative Results in Machine Learning
  41. ICML 2024Position: The Causal Revolution Needs Scientific Pragmatism
  42. ICML 2024SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models
  43. ICML 2024Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation
  44. ICML 2024Simulation of Graph Algorithms with Looped Transformers
  45. ICML 2024Simulation-Based Inference with Quantile Regression
  46. ICML 2024Simultaneous identification of models and parameters of scientific simulators
  47. ICML 2024Smooth Min-Max Monotonic Networks
  48. ICML 2024Variational Inference with Coverage Guarantees in Simulation-Based Inference
  49. ICML 2023Learning Neural PDE Solvers with Parameter-Guided Channel Attention
  50. ICML 2023NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查科学仿真在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "scientific-simulation"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇科学仿真论文？
共 167 篇，按年份分别是 2023 年 16 篇、2024 年 38 篇、2025 年 45 篇、2026 年 68 篇。
NeurIPS 2026 有多少篇科学仿真论文？
NeurIPS 2026 有 25 篇科学仿真论文，上一届是 24 篇。
ICLR 2026 有多少篇科学仿真论文？
ICLR 2026 有 10 篇科学仿真论文，上一届是 5 篇。
ICML 2026 有多少篇科学仿真论文？
ICML 2026 有 25 篇科学仿真论文，上一届是 8 篇。
CVPR 2026 有多少篇科学仿真论文？
CVPR 2026 有 8 篇科学仿真论文，上一届是 8 篇。
哪个会议的科学仿真论文最多？
NeurIPS，2023–2026 年共 71 篇。

「气候与物理科学」下的其他主题