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 417 篇，第 8 / 9 页

351. ICML 2025Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
352. ICML 2025SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
353. ICML 2025Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
354. ICML 2025SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
355. ICML 2025Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
356. ICML 2025Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
357. ICML 2025Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models
358. ICML 2025Steer LLM Latents for Hallucination Detection
359. ICML 2025Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMM
360. ICML 2025Structure-Guided Large Language Models for Text-to-SQL Generation
361. ICML 2025Synthetic Text Generation for Training Large Language Models via Gradient Matching
362. ICML 2025Taming Knowledge Conflicts in Language Models
363. ICML 2025Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision
364. ICML 2025Teaching Language Models to Critique via Reinforcement Learning
365. ICML 2025Teaching Physical Awareness to LLMs through Sounds
366. ICML 2025Teaching Transformers Causal Reasoning through Axiomatic Training
367. ICML 2025Test-Time Learning for Large Language Models
368. ICML 2025Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
369. ICML 2025TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
370. ICML 2025The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models
371. ICML 2025The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph
372. ICML 2025The Canary’s Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
373. ICML 2025The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination
374. ICML 2025The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
375. ICML 2025The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
376. ICML 2025The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
377. ICML 2025The Missing Alignment Link of In-context Learning on Sequences
378. ICML 2025The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
379. ICML 2025The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
380. ICML 2025Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization
381. ICML 2025Thinking LLMs: General Instruction Following with Thought Generation
382. ICML 2025To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
383. ICML 2025Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
384. ICML 2025Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
385. ICML 2025Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models
386. ICML 2025TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation
387. ICML 2025Towards Cost-Effective Reward Guided Text Generation
388. ICML 2025Towards Lifelong Model Editing via Simulating Ideal Editor
389. ICML 2025Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
390. ICML 2025Training a Generally Curious Agent
391. ICML 2025Training Software Engineering Agents and Verifiers with SWE-Gym
392. ICML 2025TruthFlow: Truthful LLM Generation via Representation Flow Correction
393. ICML 2025TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
394. ICML 2025Tuning LLM Judge Design Decisions for 1/1000 of the Cost
395. ICML 2025UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
396. ICML 2025Unbiased Evaluation of Large Language Models from a Causal Perspective
397. ICML 2025Understanding Bias Reinforcement in LLM Agents Debate
398. ICML 2025Understanding Chain-of-Thought in LLMs through Information Theory
399. ICML 2025Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
400. ICML 2025Understanding Synthetic Context Extension via Retrieval Heads

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。