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 2,334 篇，第 26 / 47 页

1251. ICML 2025Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving
1252. ICML 2025Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
1253. ICML 2025EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration
1254. ICML 2025Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
1255. ICML 2025EvoPress: Accurate Dynamic Model Compression via Evolutionary Search
1256. ICML 2025Explicit Preference Optimization: No Need for an Implicit Reward Model
1257. ICML 2025Exploiting Presentative Feature Distributions for Parameter-Efficient Continual Learning of Large Language Models
1258. ICML 2025FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees
1259. ICML 2025Fast Large Language Model Collaborative Decoding via Speculation
1260. ICML 2025Federated In-Context Learning: Iterative Refinement for Improved Answer Quality
1261. ICML 2025FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation
1262. ICML 2025Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models
1263. ICML 2025FlatQuant: Flatness Matters for LLM Quantization
1264. ICML 2025FlipAttack: Jailbreak LLMs via Flipping
1265. ICML 2025FloE: On-the-Fly MoE Inference on Memory-constrained GPU
1266. ICML 2025Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options
1267. ICML 2025Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
1268. ICML 2025Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
1269. ICML 2025Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization
1270. ICML 2025Fragments to Facts: Partial-Information Fragment Inference from LLMs
1271. ICML 2025Free Process Rewards without Process Labels
1272. ICML 2025From Debate to Equilibrium: Belief‑Driven Multi‑Agent LLM Reasoning via Bayesian Nash Equilibrium
1273. ICML 2025From Language Models over Tokens to Language Models over Characters
1274. ICML 2025From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
1275. ICML 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
1276. ICML 2025FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
1277. ICML 2025Function-to-Style Guidance of LLMs for Code Translation
1278. ICML 2025GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models
1279. ICML 2025Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks
1280. ICML 2025Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
1281. ICML 2025GRAM: A Generative Foundation Reward Model for Reward Generalization
1282. ICML 2025Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models
1283. ICML 2025Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for Agents
1284. ICML 2025Great Models Think Alike and this Undermines AI Oversight
1285. ICML 2025Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
1286. ICML 2025GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs
1287. ICML 2025GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning
1288. ICML 2025Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents
1289. ICML 2025GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
1290. ICML 2025Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
1291. ICML 2025HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding
1292. ICML 2025Heads up! Large Language Models Can Perform Tasks Without Your Instruction via Selective Attention Head Masking
1293. ICML 2025Hidden No More: Attacking and Defending Private Third-Party LLM Inference
1294. ICML 2025How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence
1295. ICML 2025How Much Can We Forget about Data Contamination?
1296. ICML 2025HPS: Hard Preference Sampling for Human Preference Alignment
1297. ICML 2025Hyperband-based Bayesian Optimization for Black-box Prompt Selection
1298. ICML 2025HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking
1299. ICML 2025Hypo3D: Exploring Hypothetical Reasoning in 3D
1300. ICML 2025IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck

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。