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 1,640 篇，第 1 / 33 页

1. CVPR 2025All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising
2. CVPR 2025AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos
3. CVPR 2025AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward
4. CVPR 2025Automated Proof of Polynomial Inequalities via Reinforcement Learning
5. CVPR 2025AutoPresent: Designing Structured Visuals from Scratch
6. CVPR 2025Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries
7. CVPR 2025CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-Scale Reinforcement Learning in Autonomous Driving
8. CVPR 2025CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
9. CVPR 2025Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models
10. CVPR 2025Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
11. CVPR 2025Curriculum Direct Preference Optimization for Diffusion and Consistency Models
12. CVPR 2025CustAny: Customizing Anything from A Single Example
13. CVPR 2025Decision SpikeFormer: Spike-Driven Transformer for Decision Making
14. CVPR 2025Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
15. CVPR 2025Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera
16. CVPR 2025EventFly: Event Camera Perception from Ground to the Sky
17. CVPR 2025Focal Split: Untethered Snapshot Depth from Differential Defocus
18. CVPR 2025Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportions
19. CVPR 2025FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images
20. CVPR 2025From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
21. CVPR 2025From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization
22. CVPR 2025Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging
23. CVPR 2025GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks
24. CVPR 2025GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill
25. CVPR 2025Hand-held Object Reconstruction from RGB Video with Dynamic Interaction
26. CVPR 2025HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos
27. CVPR 2025Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes
28. CVPR 2025High-Fidelity Lightweight Mesh Reconstruction from Point Clouds
29. CVPR 2025Homogeneous Dynamics Space for Heterogeneous Humans
30. CVPR 2025LATTE-MV: Learning to Anticipate Table Tennis Hits from Monocular Videos
31. CVPR 2025Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation
32. CVPR 2025Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model
33. CVPR 2025Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation
34. CVPR 2025Let Humanoids Hike! Integrative Skill Development on Complex Trails
35. CVPR 2025Leveraging Global Stereo Consistency for Category-Level Shape and 6D Pose Estimation from Stereo Images
36. CVPR 2025ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning
37. CVPR 2025MultiMorph: On-demand Atlas Construction
38. CVPR 2025Neural Motion Simulator Pushing the Limit of World Models in Reinforcement Learning
39. CVPR 2025PICO: Reconstructing 3D People In Contact with Objects
40. CVPR 2025Plug-and-Play PPO: An Adaptive Point Prompt Optimizer Making SAM Greater
41. CVPR 2025Pose Priors from Language Models
42. CVPR 2025Practical Solutions to the Relative Pose of Three Calibrated Cameras
43. CVPR 2025Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning
44. CVPR 2025RaSS: Improving Denoising Diffusion Samplers with Reinforced Active Sampling Scheduler
45. CVPR 2025Removing Reflections from RAW Photos
46. CVPR 2025Revisiting Fairness in Multitask Learning: A Performance-Driven Approach for Variance Reduction
47. CVPR 2025Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward
48. CVPR 2025RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression
49. CVPR 2025Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments
50. CVPR 2025Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation

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。