Adaptive Methods papers, 2023–2026

Key findings

• Adaptive Methods went from 143 papers in 2023 to 410 in 2026, roughly 2.9x in three years.
• NeurIPS publishes the most Adaptive Methods work: 365 papers from 2023 to 2026, 36% of the four-venue total.
• The fastest-growing overlap is with Theory · optimization: papers tagged with both rose from 1 in 2023 to 29 in 2026.
• Among the 5 topics under Optimization and Scaling, it ranks #3 by 2026 paper count; the fastest grower in the group, Scaling Laws, is up 4.1x versus 2.9x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026AcceleGrad#: Adaptive Geometry-Aware Acceleration
• ICML 2026Adaptive Bandit Algorithms for Contextual Matching Markets
• ICLR 2026Adaptive Width Neural Networks
• CVPR 2026Active Inference for Micro-Gesture Recognition EFE-Guided Temporal Sampling and Adaptive
• NeurIPS 2025AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
• ICML 2025Adaptive Data Collection for Robust Learning Across Multiple Distributions
• ICLR 2025Adaptive Length Image Tokenization via Recurrent Allocation
• CVPR 2025A Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse Artifacts
• NeurIPS 2024Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization
• ICML 2024A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
• ICLR 2024Learning Adaptive Multiresolution Transforms via Meta-Framelet-based Graph Convolutional Network
• CVPR 2024HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces
• NeurIPS 2023A Bounded Ability Estimation for Computerized Adaptive Testing
• ICML 2023A/B Testing in Network Data with Covariate-Adaptive Randomization
• ICLR 2023An Adaptive Policy to Employ Sharpness-Aware Minimization
• CVPR 2023Adaptive Annealing for Robust Geometric Estimation
• NeurIPS 2026AdapMatch: Adaptive Bias Decoupling for Semi-Supervised Partial Label Learning under Unknown Class Distributions
• ICML 2026Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
• ICLR 2026ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
• CVPR 2026Adaptive Learned Image Compression with Graph Neural Networks

All Adaptive Methods papers

109 papers, page 1 of 3

1. ICML 2026A KL-regularization framework for learning to plan with adaptive priors
2. ICML 2026Achieving Structurally Robust Gromov Wasserstein Distance via Adaptive Dual-Mask
3. ICML 2026Active Attacks: Red-teaming LLMs via Adaptive Environments
4. ICML 2026AD-BTS: Adaptive Dual-Branch Token Sparsification via Spatial Information Density
5. ICML 2026AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping
6. ICML 2026AdaHC: Accelerating Multi-Token Prediction with Adaptive Head Chunking with Pipeline Parallelism
7. ICML 2026Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond
8. ICML 2026Adaptive Bandit Algorithms for Contextual Matching Markets
9. ICML 2026Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
10. ICML 2026Adaptive Coding Emerges in Stabilized Supralinear Networks Trained with Local Plasticity
11. ICML 2026Adaptive Contracts for Cost-Effective AI Delegation
12. ICML 2026Adaptive DNA Sequence Modeling via Synergistic Plasticity Units
13. ICML 2026Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman Orthogonality
14. ICML 2026Adaptive Momentum and Nonlinear Damping for Neural Network Training
15. ICML 2026Adaptive Multi-Round Allocation with Stochastic Arrivals
16. ICML 2026Adaptive Multiscale Binary Expansion Tests for Independence
17. ICML 2026Adaptive Node Feature Selection for Graph Neural Networks
18. ICML 2026Adaptive Physics Transformer with Fused Global-Local Attention for Subsurface Energy Systems
19. ICML 2026Adaptive Policy Backbone via Shared Network
20. ICML 2026Adaptive Preconditioners Trigger Loss Spikes in Adam
21. ICML 2026Adaptive Probe-based Steering for Robust LLM Jailbreaking
22. ICML 2026Adaptive Protein Tokenization
23. ICML 2026Adaptive Quasimetric Mapping : Principled Topological Abstraction for Robust Offline Goal-Conditioned Navigation
24. ICML 2026Adaptive Querying with AI Persona Priors
25. ICML 2026Adaptive Reinforcement Learning for Unobservable Random Delays
26. ICML 2026Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
27. ICML 2026Adaptive Symmetry Discovery for Dynamical System Identification
28. ICML 2026Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis
29. ICML 2026AdaS: Adaptive Gradient Descent for Spiking Transformers
30. ICML 2026AdaSCALE: Adaptive Scaling for OOD Detection
31. ICML 2026Adversarially Robust Approximate Furthest Neighbor
32. ICML 2026ANTiC: Adaptive Neural Temporal In Situ Compressor
33. ICML 2026AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
34. ICML 2026API: Adaptive Prototype Imputation for Incomplete Multimodal Sentiment Analysis
35. ICML 2026BAS: Bridging Adam and SignSGD for Memory-Efficient LLM Training
36. ICML 2026BASIL: Scalable Bayesian Semi-supervised Clustering with Feature Selection and Adaptive Constraint Weighting
37. ICML 2026Bootstrapped Exploration with Causal Reasoning: A Training Paradigm for Adaptive Forecasting Agent
38. ICML 2026Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad
39. ICML 2026Can Muon Fine-tune Adam-Pretrained Models?
40. ICML 2026CARE: Adaptive Calibration for Reliable Recommendations
41. ICML 2026CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
42. ICML 2026Cold-Start Personalization via Bayesian Adaptive Questioning
43. ICML 2026Constrained Adaptive Rejection Sampling
44. ICML 2026Contrastive Symbolic Regression: Aligned Representations, Adaptive Prediction, and Diverse Ensembles
45. ICML 2026Data-Source Adaptive Online Learning under Heteroscedastic Noise
46. ICML 2026Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization
47. ICML 2026Delving into Muon and Beyond: Deep Analysis and Extensions
48. ICML 2026DistMatch: Adaptive Binning via Distribution Matching for Robust Sequential Conformal Prediction
49. ICML 2026dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
50. ICML 2026Domain Adaptive Object Detection via Dynamic Causal Refinement

FAQ

How many Adaptive Methods papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,012 in total: 143 in 2023, 183 in 2024, 276 in 2025, 410 in 2026.

How many Adaptive Methods papers are at NeurIPS 2026?

NeurIPS 2026 has 138 Adaptive Methods papers, versus 109 the year before.

How many Adaptive Methods papers are at ICLR 2026?

ICLR 2026 has 80 Adaptive Methods papers, versus 47 the year before.

How many Adaptive Methods papers are at ICML 2026?

ICML 2026 has 109 Adaptive Methods papers, versus 68 the year before.

How many Adaptive Methods papers are at CVPR 2026?

CVPR 2026 has 83 Adaptive Methods papers, versus 52 the year before.

Which conference publishes the most Adaptive Methods papers?

NeurIPS, with 365 papers from 2023 to 2026.