自适应方法论文趋势 2023–2026

Adam 类与调度

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,012 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

自适应方法论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202354242243143
202464225146183
2025109476852276
20261388010983410

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

全部自适应方法论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,012 篇，第 12 / 21 页

  1. ICML 2025GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models
  2. ICML 2025Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes
  3. ICML 2025Graph Adaptive Autoregressive Moving Average Models
  4. ICML 2025Layer-wise Quantization for Quantized Optimistic Dual Averaging
  5. ICML 2025Learning Adaptive Lighting via Channel-Aware Guidance
  6. ICML 2025Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning
  7. ICML 2025Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
  8. ICML 2025MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning
  9. ICML 2025MARS: Unleashing the Power of Variance Reduction for Training Large Models
  10. ICML 2025Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing
  11. ICML 2025On Efficient Estimation of Distributional Treatment Effects under Covariate-Adaptive Randomization
  12. ICML 2025On the Learnability of Distribution Classes with Adaptive Adversaries
  13. ICML 2025Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect
  14. ICML 2025PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling
  15. ICML 2025Peripheral Memory for LLMs: Integration of Sequential Memory Banks with Adaptive Querying
  16. ICML 2025Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care
  17. ICML 2025Prediction-Powered Adaptive Shrinkage Estimation
  18. ICML 2025Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale
  19. ICML 2025Prompt-to-Leaderboard: Prompt-Adaptive LLM Evaluations
  20. ICML 2025Refining Adaptive Zeroth-Order Optimization at Ease
  21. ICML 2025Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs
  22. ICML 2025Sassha: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation
  23. ICML 2025Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling
  24. ICML 2025Stronger Neyman Regret Guarantees for Adaptive Experimental Design
  25. ICML 2025Structured Preconditioners in Adaptive Optimization: A Unified Analysis
  26. ICML 2025Tracking Most Significant Shifts in Infinite-Armed Bandits
  27. ICML 2025WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
  28. NeurIPS 2025A Driving-Style-Adaptive Framework for Vehicle Trajectory Prediction
  29. NeurIPS 2025Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency
  30. NeurIPS 2025AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
  31. NeurIPS 2025Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization
  32. NeurIPS 2025Accelerating Diffusion LLMs via Adaptive Parallel Decoding
  33. NeurIPS 2025AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking
  34. NeurIPS 2025Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
  35. NeurIPS 2025AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees
  36. NeurIPS 2025AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining
  37. NeurIPS 2025Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
  38. NeurIPS 2025AdaptGrad: Adaptive Sampling to Reduce Noise
  39. NeurIPS 2025Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization
  40. NeurIPS 2025Adaptive and Multi-scale Affinity Alignment for Hierarchical Contrastive Learning
  41. NeurIPS 2025Adaptive Cannistraci-Hebb Network Automata Modelling of Complex Networks for Path-based Link Prediction
  42. NeurIPS 2025Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking
  43. NeurIPS 2025Adaptive Data-Borrowing for Improving Treatment Effect Estimation using External Controls
  44. NeurIPS 2025Adaptive Discretization for Consistency Models
  45. NeurIPS 2025Adaptive Fission: Post-training Encoding for Low-latency Spike Neural Networks
  46. NeurIPS 2025Adaptive Inference-Time Scaling via Cyclic Diffusion Search
  47. NeurIPS 2025Adaptive Latent-Space Constraints in Personalized Federated Learning
  48. NeurIPS 2025Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
  49. NeurIPS 2025Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees
  50. NeurIPS 2025Adaptive Quantization in Generative Flow Networks for Probabilistic Sequential Prediction

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 查自适应方法在 NeurIPS 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": "adaptive-methods"}

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自适应方法论文？
共 1,012 篇，按年份分别是 2023 年 143 篇、2024 年 183 篇、2025 年 276 篇、2026 年 410 篇。
NeurIPS 2026 有多少篇自适应方法论文？
NeurIPS 2026 有 138 篇自适应方法论文，上一届是 109 篇。
ICLR 2026 有多少篇自适应方法论文？
ICLR 2026 有 80 篇自适应方法论文，上一届是 47 篇。
ICML 2026 有多少篇自适应方法论文？
ICML 2026 有 109 篇自适应方法论文，上一届是 68 篇。
CVPR 2026 有多少篇自适应方法论文？
CVPR 2026 有 83 篇自适应方法论文，上一届是 52 篇。
哪个会议的自适应方法论文最多？
NeurIPS，2023–2026 年共 365 篇。

「优化与缩放」下的其他主题