电网优化论文趋势 2023–2026

主要结论

• 电网优化论文从 2023 年的 24 篇增长到 2026 年的 62 篇，三年间扩大到约 2.6 倍。
• NeurIPS 是发电网优化论文最多的会议，2023–2026 年共 57 篇，占四个会议总量的 38%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 10 篇。
• 在「社会公益」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的公共政策分析是 1.8 倍，电网优化是 2.6 倍。

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

• NeurIPS 2026A Grid Efficient Transport Optimization Model for the Wasserstein Barycenter Problem
• ICML 2026Beyond Buffer Limits: Energy-Based Data Reassembly for Continual Learning
• ICLR 2026Behavior Learning (BL)
• CVPR 2026Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization
• NeurIPS 2025The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization
• ICML 2025Compositional Risk Minimization
• ICLR 2025Learning to Solve Differential Equation Constrained Optimization Problems
• CVPR 2025Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation
• NeurIPS 2024PowerGraph: A power grid benchmark dataset for graph neural networks
• ICML 2024Differentiable Distributionally Robust Optimization Layers
• ICLR 2024Language Model Decoding as Direct Metrics Optimization
• CVPR 2024Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization
• NeurIPS 2023Many-body Approximation for Non-negative Tensors
• ICML 2023A Unified Optimization Framework of ANN-SNN Conversion: Towards Optimal Mapping from Activation Values to Firing Rates
• ICLR 2023Actionable Neural Representations: Grid Cells from Minimal Constraints
• CVPR 2023Towards Bridging the Performance Gaps of Joint Energy-Based Models
• NeurIPS 2026A Theory of Spatial Continuous Attractors in Hopfield Energy Landscapes
• ICML 2026Constructing Industrial-Scale Optimization Modeling Benchmark
• ICLR 2026Energy-Regularized Sequential Model Editing on Hyperspheres
• CVPR 2026EnergyAction Unimanual to Bimanual Composition with Energy-Based Models

全部电网优化论文

共 151 篇，第 2 / 4 页

51. NeurIPS 2026Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation
52. NeurIPS 2026Grid Games: The Power Of Multiple Grids for Quantizing Large Language Models
53. NeurIPS 2026Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences
54. NeurIPS 2026NLD4CO: Neural Langevin Dynamics for Combinatorial Optimization
55. NeurIPS 2026Reconciling Operational Energy Trilemma: A Heterogeneous Risk-Constrained MDP Framework with Residual Policy Learning
56. NeurIPS 2026Replay-buffer engineering for noise-robust quantum circuit optimization
57. NeurIPS 2026Self-Correction as Transition Geometry: Internalizing Reasoning via Lifted State Policy Optimization
58. NeurIPS 2026Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks
59. NeurIPS 2026Spectral Annealing: Normalization-Path Exploration for Large-Scale Ising Optimization
60. NeurIPS 2026Speed Predictions for Online Energy-Efficient Scheduling
61. NeurIPS 2026The $1/\mathcal{W}$ Law: Context Length is the Dominant Energy Lever in LLM Inference Fleets
62. NeurIPS 2026Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
63. CVPR 2025Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation
64. CVPR 2025Twinner: Shining Light on Digital Twins in a Few Snaps
65. ICLR 2025Computing Circuits Optimization via Model-Based Circuit Genetic Evolution
66. ICLR 2025Data Center Cooling System Optimization Using Offline Reinforcement Learning
67. ICLR 2025Learning to Solve Differential Equation Constrained Optimization Problems
68. ICLR 2025MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy
69. ICLR 2025NRGBoost: Energy-Based Generative Boosted Trees
70. ICLR 2025On Conformal Isometry of Grid Cells: Learning Distance-Preserving Position Embedding
71. ICLR 2025Poison-splat: Computation Cost Attack on 3D Gaussian Splatting
72. ICLR 2025Regularizing Energy among Training Samples for Out-of-Distribution Generalization
73. ICLR 2025Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold
74. ICLR 2025Taming Transformer Without Using Learning Rate Warmup
75. ICML 2025Compositional Risk Minimization
76. ICML 2025Compressing tree ensembles through Level-wise Optimization and Pruning
77. ICML 2025Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models
78. ICML 2025Efficient Source-free Unlearning via Energy-Guided Data Synthesis and Discrimination-Aware Multitask Optimization
79. ICML 2025Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
80. ICML 2025Joint Learning of Energy-based Models and their Partition Function
81. ICML 2025Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization
82. ICML 2025Predicting mutational effects on protein binding from folding energy
83. NeurIPS 2025A Difference-of-Convex Functions Approach to Energy-Based Iterative Reasoning
84. NeurIPS 2025Accurately Predicting Protein Mutational Effects via a Hierarchical Many-Body Attention Network
85. NeurIPS 2025Aligning Transformers with Continuous Feedback via Energy Rank Alignment
86. NeurIPS 2025Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning
87. NeurIPS 2025Brain-like Variational Inference
88. NeurIPS 2025CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization
89. NeurIPS 2025ConStellaration: A dataset of QI-like stellarator plasma boundaries and optimization benchmarks
90. NeurIPS 2025DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads
91. NeurIPS 2025Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models
92. NeurIPS 2025Generalizable Reasoning through Compositional Energy Minimization
93. NeurIPS 2025Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation
94. NeurIPS 2025Linearly Constrained Diffusion Implicit Models
95. NeurIPS 2025Lorentz Local Canonicalization: How to make any Network Lorentz-Equivariant
96. NeurIPS 2025Masked Diffusion Models as Energy Minimization
97. NeurIPS 2025Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
98. NeurIPS 2025Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies
99. NeurIPS 2025Rethinking Entropy in Test-Time Adaptation: The Missing Piece from Energy Duality
100. NeurIPS 2025The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization

常见问题

2023–2026 年四大会议一共有多少篇电网优化论文？

共 151 篇，按年份分别是 2023 年 24 篇、2024 年 26 篇、2025 年 39 篇、2026 年 62 篇。

NeurIPS 2026 有多少篇电网优化论文？

NeurIPS 2026 有 24 篇电网优化论文，上一届是 19 篇。

ICLR 2026 有多少篇电网优化论文？

ICLR 2026 有 11 篇电网优化论文，上一届是 10 篇。

ICML 2026 有多少篇电网优化论文？

ICML 2026 有 17 篇电网优化论文，上一届是 8 篇。

CVPR 2026 有多少篇电网优化论文？

CVPR 2026 有 10 篇电网优化论文，上一届是 2 篇。

哪个会议的电网优化论文最多？

NeurIPS，2023–2026 年共 57 篇。