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

ICML/NeurIPS 深度学习方向：large_language_models

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,334 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

深度学习 · large language models论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20234150730488
2024298000298
20250134040417
2026001,13101,131

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

全部深度学习 · large language models论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 2,334 篇，第 23 / 47 页

  1. ICML 2026What LLMs Explain Is Not What They Believe: Evaluating Explanation Sufficiency Under Models' Own Input Beliefs
  2. ICML 2026What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis
  3. ICML 2026What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code
  4. ICML 2026When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems
  5. ICML 2026When Diffusion Language Models Hesitate: Detecting and Correcting Visual Hallucinations via Confidence Fluctuation
  6. ICML 2026When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models
  7. ICML 2026When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression
  8. ICML 2026When Does Sparsity Mitigate the Curse of Depth in LLMs
  9. ICML 2026When Drafts Evolve: Speculative Decoding Meets Online Learning
  10. ICML 2026When Labelers Stay Silent: The Power of Ties in Cost-Effective Preference Learning
  11. ICML 2026When LLMs Encounter Open-world Graph Learning: A Fresh View on Unlabeled Data Uncertainty
  12. ICML 2026When Model Merging Breaks Routing: Training-Free Calibration for MoE
  13. ICML 2026When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
  14. ICML 2026When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
  15. ICML 2026When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models
  16. ICML 2026When Simple Problems Wear Complex Costumes: Improving Efficiency in LRM's Adaptive Reasoning
  17. ICML 2026When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning
  18. ICML 2026Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
  19. ICML 2026Who can we trust? LLM-as-a-jury for Comparative Assessment
  20. ICML 2026Why Deep Jacobian Spectra Separate: Depth-Induced Scaling and Singular-Vector Alignment
  21. ICML 2026WinDeskGround: A Benchmark for Robust GUI Grounding in Complex Multi-Window Desktop Environments
  22. ICML 2026WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points
  23. ICML 2026Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation
  24. ICML 2026WorldTravel: A Realistic Multimodal Travel-Planning Benchmark with Tightly Coupled Constraints
  25. ICML 2026WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
  26. ICML 2026xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction
  27. ICML 2026XSkill: Continual Learning from Experience and Skills in Multimodal Agents
  28. ICML 2026XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding
  29. ICML 2026You Can Learn Tokenization End-to-End with Reinforcement Learning
  30. ICML 2026Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression
  31. ICML 2026ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling
  32. ICLR 2025AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models
  33. ICLR 2025Brain-inspired $L_p$-Convolution benefits large kernels and aligns better with visual cortex
  34. ICLR 2025DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback
  35. ICLR 2025Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning
  36. ICLR 2025Emergence of a High-Dimensional Abstraction Phase in Language Transformers
  37. ICLR 2025Holistically Evaluating the Environmental Impact of Creating Language Models
  38. ICLR 2025Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM
  39. ICLR 2025Multi-modal brain encoding models for multi-modal stimuli
  40. ICLR 2025Personality Alignment of Large Language Models
  41. ICLR 2025Physics-Informed Deep Inverse Operator Networks for Solving PDE Inverse Problems
  42. ICLR 2025Synthetic continued pretraining
  43. ICLR 2025Uni-Sign: Toward Unified Sign Language Understanding at Scale
  44. ICLR 2025Universal generalization guarantees for Wasserstein distributionally robust models
  45. ICML 2025(How) Do Language Models Track State?
  46. ICML 2025A Hitchhiker's Guide to Scaling Law Estimation
  47. ICML 2025A Tale of Two Structures: Do LLMs Capture the Fractal Complexity of Language?
  48. ICML 2025A Unified Approach to Routing and Cascading for LLMs
  49. ICML 2025Accelerating Large Language Model Reasoning via Speculative Search
  50. ICML 2025Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查深度学习 · large language models在 ICML 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "dl-large-language-models"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「深度学习」下的其他主题