深度学习 · large language models论文趋势 2023–2026

主要结论

• 深度学习 · large language models论文从 2023 年的 488 篇增长到 2026 年的 1,131 篇，三年间扩大到约 2.3 倍。
• ICML 是发深度学习 · large language models论文最多的会议，2023–2026 年共 1,608 篇，占四个会议总量的 69%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 5 篇增至 2026 年的 184 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 3；同组增长最快的扩散模型是 4.1 倍，深度学习 · large language models是 2.3 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

• ICML 2026“very likely” Means “uncertain”? How LLMs Diverge from Humans in Linguistic Uncertainty Quantification
• ICML 2025(How) Do Language Models Track State?
• ICLR 2025AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models
• NeurIPS 2024$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
• NeurIPS 20233D-LLM: Injecting the 3D World into Large Language Models
• ICML 2023Are Large Kernels Better Teachers than Transformers for ConvNets?
• ICML 2026$f$-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models
• ICML 2025A Tale of Two Structures: Do LLMs Capture the Fractal Complexity of Language?
• ICLR 2025Emergence of a High-Dimensional Abstraction Phase in Language Transformers
• NeurIPS 2024$\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning
• NeurIPS 2023A fast heuristic to optimize time-space tradeoff for large models
• ICML 2023Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models
• ICML 2026$L^3$: Large Lookup Layers
• ICML 2025Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
• ICLR 2025Holistically Evaluating the Environmental Impact of Creating Language Models
• NeurIPS 2024A distributional simplicity bias in the learning dynamics of transformers
• NeurIPS 2023A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints
• ICML 2023Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning
• ICML 2026$V_0$: A Generalist Value Model for Any Policy at State Zero
• ICML 2025Accelerating Unbiased LLM Evaluation via Synthetic Feedback

全部深度学习 · large language models论文

共 488 篇，第 2 / 10 页

51. ICML 2023PAC Prediction Sets for Large Language Models of Code
52. ICML 2023Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation
53. ICML 2023Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models
54. ICML 2023Poisoning Language Models During Instruction Tuning
55. ICML 2023POUF: Prompt-Oriented Unsupervised Fine-tuning for Large Pre-trained Models
56. ICML 2023Pretraining Language Models with Human Preferences
57. ICML 2023QASA: Advanced Question Answering on Scientific Articles
58. ICML 2023Regularizing Towards Soft Equivariance Under Mixed Symmetries
59. ICML 2023SAM operates far from home: eigenvalue regularization as a dynamical phenomenon
60. ICML 2023Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models
61. ICML 2023Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning
62. ICML 2023Self-supervised learning of Split Invariant Equivariant representations
63. ICML 2023SGD with Large Step Sizes Learns Sparse Features
64. ICML 2023Solving High-Dimensional PDEs with Latent Spectral Models
65. ICML 2023Special Properties of Gradient Descent with Large Learning Rates
66. ICML 2023Structure-informed Language Models Are Protein Designers
67. ICML 2023Towards Sustainable Learning: Coresets for Data-efficient Deep Learning
68. ICML 2023Tractable Control for Autoregressive Language Generation
69. ICML 2023Trompt: Towards a Better Deep Neural Network for Tabular Data
70. ICML 2023Understanding the Distillation Process from Deep Generative Models to Tractable Probabilistic Circuits
71. ICML 2023When Sparsity Meets Contrastive Models: Less Graph Data Can Bring Better Class-Balanced Representations
72. ICML 2023Whose Opinions Do Language Models Reflect?
73. ICML 2023Why do Nearest Neighbor Language Models Work?
74. NeurIPS 2023[Re] CrossWalk: Fairness-enhanced Node Representation Learning
75. NeurIPS 20233D-LLM: Injecting the 3D World into Large Language Models
76. NeurIPS 2023A Computationally Efficient Sparsified Online Newton Method
77. NeurIPS 2023A fast heuristic to optimize time-space tradeoff for large models
78. NeurIPS 2023A Path to Simpler Models Starts With Noise
79. NeurIPS 2023A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints
80. NeurIPS 2023A Scalable Neural Network for DSIC Affine Maximizer Auction Design
81. NeurIPS 2023Active Learning-Based Species Range Estimation
82. NeurIPS 2023AdANNS: A Framework for Adaptive Semantic Search
83. NeurIPS 2023ADGym: Design Choices for Deep Anomaly Detection
84. NeurIPS 2023Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
85. NeurIPS 2023Agnostically Learning Single-Index Models using Omnipredictors
86. NeurIPS 2023AI for Interpretable Chemistry: Predicting Radical Mechanistic Pathways via Contrastive Learning
87. NeurIPS 2023AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs
88. NeurIPS 2023ALGO: Synthesizing Algorithmic Programs with Generated Oracle Verifiers
89. NeurIPS 2023Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization
90. NeurIPS 2023Aligning Language Models with Human Preferences via a Bayesian Approach
91. NeurIPS 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
92. NeurIPS 2023AmadeusGPT: a natural language interface for interactive animal behavioral analysis
93. NeurIPS 2023American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers
94. NeurIPS 2023An Empirical Investigation of the Role of Pre-training in Lifelong Learning
95. NeurIPS 2023An Information-Theoretic Evaluation of Generative Models in Learning Multi-modal Distributions
96. NeurIPS 2023ANPL: Towards Natural Programming with Interactive Decomposition
97. NeurIPS 2023Are aligned neural networks adversarially aligned?
98. NeurIPS 2023Are Emergent Abilities of Large Language Models a Mirage?
99. NeurIPS 2023ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training
100. NeurIPS 2023ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

常见问题

2023–2026 年四大会议一共有多少篇深度学习 · large language models论文？

共 2,334 篇，按年份分别是 2023 年 488 篇、2024 年 298 篇、2025 年 417 篇、2026 年 1,131 篇。

NeurIPS 2024 有多少篇深度学习 · large language models论文？

NeurIPS 2024 有 298 篇深度学习 · large language models论文，上一届是 415 篇。

ICLR 2025 有多少篇深度学习 · large language models论文？

ICLR 2025 有 13 篇深度学习 · large language models论文。

ICML 2026 有多少篇深度学习 · large language models论文？

ICML 2026 有 1,131 篇深度学习 · large language models论文，上一届是 404 篇。

哪个会议的深度学习 · large language models论文最多？

ICML，2023–2026 年共 1,608 篇。