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 5 / 21 页

  1. ICML 2026Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad
  2. ICML 2026Can Muon Fine-tune Adam-Pretrained Models?
  3. ICML 2026CARE: Adaptive Calibration for Reliable Recommendations
  4. ICML 2026CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
  5. ICML 2026Cold-Start Personalization via Bayesian Adaptive Questioning
  6. ICML 2026Constrained Adaptive Rejection Sampling
  7. ICML 2026Contrastive Symbolic Regression: Aligned Representations, Adaptive Prediction, and Diverse Ensembles
  8. ICML 2026Data-Source Adaptive Online Learning under Heteroscedastic Noise
  9. ICML 2026Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization
  10. ICML 2026Delving into Muon and Beyond: Deep Analysis and Extensions
  11. ICML 2026DistMatch: Adaptive Binning via Distribution Matching for Robust Sequential Conformal Prediction
  12. ICML 2026dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
  13. ICML 2026Domain Adaptive Object Detection via Dynamic Causal Refinement
  14. ICML 2026DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting
  15. ICML 2026Dual-channel Dynamic Graph Neural Networks with Adaptive Adjacency Learning and Multi-scale Representation Fusion
  16. ICML 2026DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing
  17. ICML 2026Entropic Mirror Monte Carlo
  18. ICML 2026Entropy-informed Decoding: Adaptive Information-Driven Branching
  19. ICML 2026FedVeer: Self-Adaptive Skew Estimation for Robust Federated Learning
  20. ICML 2026FOAM: Frequency and Operator-Error Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
  21. ICML 2026Geometric Convergence of Gauss–Newton for Neural Networks: Riemannian Geometry and Adaptive Damping
  22. ICML 2026Geometry-Misalignment in Distributional Learning
  23. ICML 2026Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation
  24. ICML 2026GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks
  25. ICML 2026GradientStabilizer: Fix the Norm, Not the Gradient
  26. ICML 2026HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression
  27. ICML 2026HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
  28. ICML 2026Identifiable Nonlinear Differentiable Causal Discovery via Independence and Adaptive Group Sparsity
  29. ICML 2026IO-Adam: Rethinking Memory-Efficient Adaptive Optimizers from Gradient Computation
  30. ICML 2026JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference
  31. ICML 2026KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
  32. ICML 2026LDARNet: DNA Adaptive Representation Network with Learnable Tokenization for Genomic Modeling
  33. ICML 2026Learning Adaptive Perturbation-Conditioned Contexts for Robust Transcriptional Response Prediction
  34. ICML 2026Learning Adaptive Topology with FiLM-Guided Distillation for Tertiary Structure-Based RNA Design
  35. ICML 2026LoRe: Adaptive Interaction-Evaluation Routing with Per-step Interaction Budgets for Iterative Graph Solvers
  36. ICML 2026M+Adam: Low-Precision Training via Additive–Multiplicative Optimization
  37. ICML 2026Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
  38. ICML 2026MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification
  39. ICML 2026MixFP4: Enhancing NVFP4 with Adaptive FP4/INT4 Block Representations
  40. ICML 2026Model-Preserving Adaptive Rounding
  41. ICML 2026Multi-Objective Bayesian Optimization via Adaptive $\varepsilon$-Constraint Decomposition
  42. ICML 2026Navigating the Flatlands: Dual Adaptive Sharpness-Aware Minimization for Domain Generalization
  43. ICML 2026Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models
  44. ICML 2026Not All Frequencies Are Equal: Energy-Adaptive Diffusion for Time Series Forecasting
  45. ICML 2026OmniFit: Bridging Modalities via Layer-Adaptive Token Compression for Omnimodal Large Language Models
  46. ICML 2026PACEAttention: Principled and Adaptive Feature Compression-Expansion Grounded in the Geometry of $\text{MCR}^2$
  47. ICML 2026PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement Learning
  48. ICML 2026Preconditioning Neural Tangent Kernel for Adaptive Optimization
  49. ICML 2026Prediction-Powered Adaptive Inference with Pretrained AI Models for Contextual Bandits
  50. ICML 2026PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training

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