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 1,131 篇，第 8 / 23 页

351. ICML 2026Fast and Accurate Causal Parallel Decoding using Jacobi Forcing
352. ICML 2026Fast Byte Latent Transformer
353. ICML 2026Fast KV Compaction via Attention Matching
354. ICML 2026Feature-Aware (Hyper)graph Generation via Next-Scale Prediction
355. ICML 2026Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs
356. ICML 2026Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
357. ICML 2026FedPissa: Towards Federated Personalized Adaptation of Foundation Models via LoRA Subspace Mapping
358. ICML 2026FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA
359. ICML 2026FedSDR: Federated Self-Distillation with Rectification
360. ICML 2026FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment
361. ICML 2026Float8@2bits: Entropy Coding Enables Data-Free Model Compression
362. ICML 2026FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
363. ICML 2026FOAM: Blocked State Folding for Memory-Efficient LLM Training
364. ICML 2026FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation
365. ICML 2026FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance For Pruned Large Language Models
366. ICML 2026FOCUS: DLLMs Know How to Tame Their Compute Bound
367. ICML 2026FormulaCode: Evaluating Agentic Optimization on Large Codebases
368. ICML 2026FPTQuant: Function-Preserving Transforms for LLM Quantization
369. ICML 2026From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning
370. ICML 2026From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing
371. ICML 2026From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models
372. ICML 2026From Drift to Coherence: Stabilizing Beliefs in LLMs
373. ICML 2026From Extraction to Deduction: Resolving Functional Misalignment in RAG via a Collaborative Critic-Reasoner Framework
374. ICML 2026From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity
375. ICML 2026From Growing to Looping: A Unified View of Iterative Computation in LLMs
376. ICML 2026From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair
377. ICML 2026From Interactions to Principles: Experience-Driven Self-Distillation for Evolving LLM Agents
378. ICML 2026From LLM-Generated Conjectures to Lean Formalizations: Automated Polynomial Inequality Proving via Sum-of-Squares Certificates
379. ICML 2026From Out-of-Distribution Detection to Hallucination Detection: A Geometric View
380. ICML 2026From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training
381. ICML 2026From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
382. ICML 2026From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory
383. ICML 2026From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models
384. ICML 2026From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal Reasoning
385. ICML 2026From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
386. ICML 2026From Retrieval to Translation: Translating Query into Graph-level Clues for Retrieval-Augmented Generation
387. ICML 2026From Winning to Understanding: A Diagnostic Long-Horizon RTS Benchmark for LLMs
388. ICML 2026FrontierCS: Evolving Challenges for Evolving Intelligence
389. ICML 2026Future-Gain Guided Test-Time Learning for Large Language Models
390. ICML 2026FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
391. ICML 2026G$^2$RPO: Geometric GRPO; Escaping LLM's Reasoning Rut to Break Accuracy--Entropy Trade-off
392. ICML 2026GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation
393. ICML 2026GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
394. ICML 2026GEM: Geometric Entropy Mixing for Optimal LLM Data Curation
395. ICML 2026GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
396. ICML 2026Generalized Correctness Models: Learning Calibrated and Cross-Model Correctness Predictors from Historical Patterns
397. ICML 2026GeoAlign: Geometric Rollout Curation for Robust LLM Reinforcement Learning
398. ICML 2026Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models
399. ICML 2026GLARE: Scalable Neuro-Symbolic Reward Shaping for LLM Agents via Group-Level Automata
400. ICML 2026Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

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。