推理模型论文趋势 2023–2026

主要结论

• 推理模型论文从 2023 年的 470 篇增长到 2026 年的 1,799 篇，三年间扩大到约 3.8 倍。
• NeurIPS 是发推理模型论文最多的会议，2023–2026 年共 1,253 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是强化学习：同时属于两个主题的论文从 2023 年的 9 篇增至 2026 年的 437 篇。
• 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 3；同组增长最快的AI 智能体是 12 倍，推理模型是 3.8 倍。

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 2026A Mechanistic Analysis of Looped Reasoning Language Models
• ICML 2026A Formal Comparison Between Chain of Thought and Latent Thought
• ICLR 2026A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
• CVPR 2026Asking like Socrates Socrates helps VLMs understand remote sensing images
• NeurIPS 2025A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
• ICML 2025A Reasoning-Based Approach to Cryptic Crossword Clue Solving
• ICLR 2025A Formal Framework for Understanding Length Generalization in Transformers
• CVPR 2025Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
• NeurIPS 2024Are Large Language Models Good Statisticians?
• ICML 2024Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
• ICLR 2024Amortizing intractable inference in large language models
• CVPR 2024Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts
• NeurIPS 2023A benchmark of categorical encoders for binary classification
• ICML 2023Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?
• ICLR 2023Automatic Chain of Thought Prompting in Large Language Models
• CVPR 2023ActMAD: Activation Matching To Align Distributions for Test-Time-Training
• NeurIPS 2026A Solvable Model of Chain-of-Thought in In-Context Learning
• ICML 2026A Narrowing Geometry in Contaminated Reasoning
• ICLR 2026A State-Transition Framework for Efficient LLM Reasoning
• CVPR 2026Beyond Weak Supervision MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged

全部推理模型论文

共 43 篇，第 1 / 1 页

1. CVPR 2024A Versatile Framework for Continual Test-Time Domain Adaptation: Balancing Discriminability and Generalizability
2. CVPR 2024AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation
3. CVPR 2024Backdoor Defense via Test-Time Detecting and Repairing
4. CVPR 2024Backpropagation-free Network for 3D Test-time Adaptation
5. CVPR 2024Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM
6. CVPR 2024CoG-DQA: Chain-of-Guiding Learning with Large Language Models for Diagram Question Answering
7. CVPR 2024Compositional Chain-of-Thought Prompting for Large Multimodal Models
8. CVPR 2024Depth-aware Test-Time Training for Zero-shot Video Object Segmentation
9. CVPR 2024Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation
10. CVPR 2024EventPS: Real-Time Photometric Stereo Using an Event Camera
11. CVPR 2024ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More
12. CVPR 2024Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts
13. CVPR 2024Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal
14. CVPR 2024GRAM: Global Reasoning for Multi-Page VQA
15. CVPR 2024Higher-order Relational Reasoning for Pedestrian Trajectory Prediction
16. CVPR 2024Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras
17. CVPR 2024HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses
18. CVPR 2024iKUN: Speak to Trackers without Retraining
19. CVPR 2024IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing
20. CVPR 2024Language Model Guided Interpretable Video Action Reasoning
21. CVPR 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
22. CVPR 2024Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation
23. CVPR 2024LISA: Reasoning Segmentation via Large Language Model
24. CVPR 2024LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation
25. CVPR 2024MedBN: Robust Test-Time Adaptation against Malicious Test Samples
26. CVPR 2024Mind Artist: Creating Artistic Snapshots with Human Thought
27. CVPR 2024Modality-Collaborative Test-Time Adaptation for Action Recognition
28. CVPR 2024MoReVQA: Exploring Modular Reasoning Models for Video Question Answering
29. CVPR 2024NC-TTT: A Noise Constrastive Approach for Test-Time Training
30. CVPR 2024PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought
31. CVPR 2024Real-Time Simulated Avatar from Head-Mounted Sensors
32. CVPR 2024Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM
33. CVPR 2024Situational Awareness Matters in 3D Vision Language Reasoning
34. CVPR 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
35. CVPR 2024Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA
36. CVPR 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory
37. CVPR 2024TEA: Test-time Energy Adaptation
38. CVPR 2024Test-Time Adaptation for Depth Completion
39. CVPR 2024Test-Time Domain Generalization for Face Anti-Spoofing
40. CVPR 2024Test-Time Linear Out-of-Distribution Detection
41. CVPR 2024TTA-EVF: Test-Time Adaptation for Event-based Video Frame Interpolation via Reliable Pixel and Sample Estimation
42. CVPR 2024Unified Entropy Optimization for Open-Set Test-Time Adaptation
43. CVPR 2024What How and When Should Object Detectors Update in Continually Changing Test Domains?

常见问题

2023–2026 年四大会议一共有多少篇推理模型论文？

共 3,512 篇，按年份分别是 2023 年 470 篇、2024 年 311 篇、2025 年 932 篇、2026 年 1,799 篇。

NeurIPS 2026 有多少篇推理模型论文？

NeurIPS 2026 有 361 篇推理模型论文，上一届是 500 篇。

ICLR 2026 有多少篇推理模型论文？

ICLR 2026 有 652 篇推理模型论文，上一届是 203 篇。

ICML 2026 有多少篇推理模型论文？

ICML 2026 有 582 篇推理模型论文，上一届是 159 篇。

CVPR 2026 有多少篇推理模型论文？

CVPR 2026 有 204 篇推理模型论文，上一届是 70 篇。

哪个会议的推理模型论文最多？

NeurIPS，2023–2026 年共 1,253 篇。