材料发现论文趋势 2023–2026

主要结论

• 材料发现论文从 2023 年的 30 篇增长到 2026 年的 77 篇，三年间扩大到约 2.6 倍。
• ICML 是发材料发现论文最多的会议，2023–2026 年共 70 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是应用 · chemistry physics and earth sciences：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 8 篇。
• 在「气候与物理科学」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的天气预报是 6.1 倍，材料发现是 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 2026AMGenC: Generating Charge Balanced Amorphous Materials
• ICML 2026Adaptive Symmetry Discovery for Dynamical System Identification
• ICLR 2026Bures Generalized Category Discovery
• CVPR 2026TAR Token-Aware Refinement for Fine-grained Generalized Category Discovery
• NeurIPS 2025Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective
• ICML 2025Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?
• ICLR 2025DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery
• CVPR 2025Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement
• NeurIPS 2024WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery Benchmarking
• ICML 2024Amortized Equation Discovery in Hybrid Dynamical Systems
• ICLR 2024Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery
• CVPR 2024Eclipse: Disambiguating Illumination and Materials using Unintended Shadows
• NeurIPS 2023An Optimization-based Approach To Node Role Discovery in Networks: Approximating Equitable Partitions
• ICML 2023Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery
• ICLR 2023Improving the imputation of missing data with Markov Blanket discovery
• CVPR 2023Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery
• NeurIPS 2026Ballad: Bandit-Based LLM Routing for Automated Heuristic Discovery
• ICML 2026CURE: Consistency-under-Unified Semantic Regularization for Generalized Category Discovery
• ICLR 2026From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers
• CVPR 2026Decouple Your Discovery and Memory in Continual Generalized Category Discovery

全部材料发现论文

共 77 篇，第 2 / 2 页

51. NeurIPS 2026Causal discovery needs explicit epistemic standards
52. NeurIPS 2026CausalTab: Pretraining Across Causal Environments for Tabular Causal Discovery
53. NeurIPS 2026Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations
54. NeurIPS 2026Cross-Model Circuit Discovery
55. NeurIPS 2026Crosscoding Through Time: Sparse Feature Discovery Across Sequence Positions
56. NeurIPS 2026CruxBench: A Benchmark of Information Discovery
57. NeurIPS 2026Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics
58. NeurIPS 2026DrugSAGE: Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
59. NeurIPS 2026Fiedler-Regularized Causal Discovery for Sparse Connected DAGs
60. NeurIPS 2026Finite Resources False Discovery Rate Control on Structured Hypothesis Spaces
61. NeurIPS 2026From I/O to Code with Discovery Agent
62. NeurIPS 2026Hodge Laplacian Quasi-Harmonic Flows for Option Discovery
63. NeurIPS 2026HyperTree: Scalable Unsupervised Hierarchy Discovery in Hyperbolic Space
64. NeurIPS 2026Improving constraint-based discovery with robust propagation and LLM priors
65. NeurIPS 2026LEIA: Learned Environment for Interactive Architected Materials
66. NeurIPS 2026Mapping Uncharted Symmetries: Machine Discovery in Combinatorics
67. NeurIPS 2026MaterialsSaddles: 34 Million Transition States and a Flow-Matching Saddle-Point Predictor for Materials
68. NeurIPS 2026MOOD: Benchmarking Post-Hoc OOD Detection for Materials Property Prediction
69. NeurIPS 2026NORMA: Norm-Guided Explanation Subgraph Discovery
70. NeurIPS 2026Offline Materials Optimization with CliqueFlowmer
71. NeurIPS 2026PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data
72. NeurIPS 2026Preserving DEG Rankings for Gene Discovery in Histology-Based Spatial Gene Expression Prediction
73. NeurIPS 2026SciResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
74. NeurIPS 2026Seen-Constrained Model-Order Selection for Unknown-$K$ Generalized Category Discovery
75. NeurIPS 2026Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning
76. NeurIPS 2026TagBO: LLM-Driven Task-Aware Graph Bayesian Optimization for Scientific Discovery
77. NeurIPS 2026Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery

常见问题

2023–2026 年四大会议一共有多少篇材料发现论文？

共 208 篇，按年份分别是 2023 年 30 篇、2024 年 48 篇、2025 年 53 篇、2026 年 77 篇。

NeurIPS 2026 有多少篇材料发现论文？

NeurIPS 2026 有 33 篇材料发现论文，上一届是 15 篇。

ICLR 2026 有多少篇材料发现论文？

ICLR 2026 有 11 篇材料发现论文，上一届是 12 篇。

ICML 2026 有多少篇材料发现论文？

ICML 2026 有 27 篇材料发现论文，上一届是 13 篇。

CVPR 2026 有多少篇材料发现论文？

CVPR 2026 有 6 篇材料发现论文，上一届是 13 篇。

哪个会议的材料发现论文最多？

ICML，2023–2026 年共 70 篇。