强化学习论文趋势 2023–2026

主要结论

• 强化学习论文从 2023 年的 1,070 篇增长到 2026 年的 2,985 篇，三年间扩大到约 2.8 倍。
• NeurIPS 是发强化学习论文最多的会议，2023–2026 年共 2,494 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是推理模型：同时属于两个主题的论文从 2023 年的 9 篇增至 2026 年的 437 篇。

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

• NeurIPS 2026\texttt{FEROM}: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs
• ICML 2026$\text{DT}^\text{2}$: Decision-Targeted Digital Twins
• ICLR 2026$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Textual Space
• CVPR 2026A Causal Marriage between VLM and IRM from Understanding to
• NeurIPS 2025$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning
• ICML 2025A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
• ICLR 2025$\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee
• CVPR 2025All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising
• NeurIPS 2024A Critical Evaluation of AI Feedback for Aligning Large Language Models
• ICML 2024${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
• ICLR 2024A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
• CVPR 2024DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning
• NeurIPS 2023“Why Not Looking backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization
• ICML 2023A Connection between One-Step RL and Critic Regularization in Reinforcement Learning
• ICLR 2023$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games
• CVPR 2023"Seeing" Electric Network Frequency From Events
• NeurIPS 2026$\varphi$TD: Distributional Reinforcement Learning using Characteristic Functions
• ICML 2026$\textit{S}$-SPPO: Semantic-Calibrated Self-Play Preference Optimization
• ICLR 2026$AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-Tuning
• CVPR 2026AdaptVision Efficient Vision-Language Models via Adaptive Visual Acquisition

全部强化学习论文

共 1,190 篇，第 1 / 24 页

1. CVPR 20243DToonify: Creating Your High-Fidelity 3D Stylized Avatar Easily from 2D Portrait Images
2. CVPR 2024Active Object Detection with Knowledge Aggregation and Distillation from Large Models
3. CVPR 2024Activity-Biometrics: Person Identification from Daily Activities
4. CVPR 2024AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
5. CVPR 2024An Interactive Navigation Method with Effect-oriented Affordance
6. CVPR 2024Are Conventional SNNs Really Efficient? A Perspective from Network Quantization
7. CVPR 2024Authentic Hand Avatar from a Phone Scan via Universal Hand Model
8. CVPR 2024Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft
9. CVPR 2024Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch
10. CVPR 2024Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning
11. CVPR 2024ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles
12. CVPR 2024Detector-Free Structure from Motion
13. CVPR 2024Diffusion Model Alignment Using Direct Preference Optimization
14. CVPR 2024DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning
15. CVPR 2024Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes
16. CVPR 2024DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback
17. CVPR 2024Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification
18. CVPR 2024Dynamic Prompt Optimizing for Text-to-Image Generation
19. CVPR 2024EgoGen: An Egocentric Synthetic Data Generator
20. CVPR 2024Ensemble Diversity Facilitates Adversarial Transferability
21. CVPR 2024Event-based Structure-from-Orbit
22. CVPR 2024From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation
23. CVPR 2024From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers
24. CVPR 2024Gated Fields: Learning Scene Reconstruction from Gated Videos
25. CVPR 2024GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction
26. CVPR 2024Hybrid Proposal Refiner: Revisiting DETR Series from the Faster R-CNN Perspective
27. CVPR 2024Improving Unsupervised Hierarchical Representation with Reinforcement Learning
28. CVPR 2024Insights from the Use of Previously Unseen Neural Architecture Search Datasets
29. CVPR 2024IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing
30. CVPR 2024Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment
31. CVPR 2024Lane2Seq: Towards Unified Lane Detection via Sequence Generation
32. CVPR 2024Learning from Observer Gaze: Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition
33. CVPR 2024Learning to Control Camera Exposure via Reinforcement Learning
34. CVPR 2024Learning to Select Views for Efficient Multi-View Understanding
35. CVPR 2024Learning to Transform Dynamically for Better Adversarial Transferability
36. CVPR 2024Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels
37. CVPR 2024LEMON: Learning 3D Human-Object Interaction Relation from 2D Images
38. CVPR 2024Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving
39. CVPR 2024Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences
40. CVPR 2024MonoNPHM: Dynamic Head Reconstruction from Monocular Videos
41. CVPR 2024MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild
42. CVPR 2024NARUTO: Neural Active Reconstruction from Uncertain Target Observations
43. CVPR 2024OmniLocalRF: Omnidirectional Local Radiance Fields from Dynamic Videos
44. CVPR 2024PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns
45. CVPR 2024POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning
46. CVPR 2024Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds
47. CVPR 2024PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models
48. CVPR 2024Previously on ... From Recaps to Story Summarization
49. CVPR 2024Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion
50. CVPR 2024Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences

常见问题

2023–2026 年四大会议一共有多少篇强化学习论文？

共 6,885 篇，按年份分别是 2023 年 1,070 篇、2024 年 1,190 篇、2025 年 1,640 篇、2026 年 2,985 篇。

NeurIPS 2026 有多少篇强化学习论文？

NeurIPS 2026 有 760 篇强化学习论文，上一届是 784 篇。

ICLR 2026 有多少篇强化学习论文？

ICLR 2026 有 911 篇强化学习论文，上一届是 379 篇。

ICML 2026 有多少篇强化学习论文？

ICML 2026 有 1,021 篇强化学习论文，上一届是 405 篇。

CVPR 2026 有多少篇强化学习论文？

CVPR 2026 有 293 篇强化学习论文，上一届是 72 篇。

哪个会议的强化学习论文最多？

NeurIPS，2023–2026 年共 2,494 篇。