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 70 篇，第 1 / 2 页

1. CVPR 20253D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
2. CVPR 2025Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
3. CVPR 2025Associative Transformer
4. CVPR 2025Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence
5. CVPR 2025CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
6. CVPR 2025Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model
7. CVPR 2025CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification
8. CVPR 2025Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning
9. CVPR 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
10. CVPR 2025CRISP: Object Pose and Shape Estimation with Test-Time Adaptation
11. CVPR 2025D^3CTTA: Domain-Dependent Decorrelation for Continual Test-Time Adaption of 3D LiDAR Segmentation
12. CVPR 2025DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding
13. CVPR 2025DrVideo: Document Retrieval Based Long Video Understanding
14. CVPR 2025Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning
15. CVPR 2025Effortless Active Labeling for Long-Term Test-Time Adaptation
16. CVPR 2025F-LMM: Grounding Frozen Large Multimodal Models
17. CVPR 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement
18. CVPR 2025FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute
19. CVPR 2025Functionality Understanding and Segmentation in 3D Scenes
20. CVPR 2025GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks
21. CVPR 2025GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation
22. CVPR 2025Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels
23. CVPR 2025How to Merge Your Multimodal Models Over Time?
24. CVPR 2025ImagineFSL: Self-Supervised Pretraining Matters on Imagined Base Set for VLM-based Few-shot Learning
25. CVPR 2025Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
26. CVPR 2025Interleaved-Modal Chain-of-Thought
27. CVPR 2025Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising
28. CVPR 2025Let's Verify and Reinforce Image Generation Step by Step
29. CVPR 2025Maintaining Consistent Inter-Class Topology in Continual Test-Time Adaptation
30. CVPR 2025MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research
31. CVPR 2025MLLM-as-a-Judge for Image Safety without Human Labeling
32. CVPR 2025Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level
33. CVPR 2025MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts
34. CVPR 2025Notes-guided MLLM Reasoning: Enhancing MLLM with Knowledge and Visual Notes for Visual Question Answering
35. CVPR 2025OffsetOPT: Explicit Surface Reconstruction without Normals
36. CVPR 2025OmniGen: Unified Image Generation
37. CVPR 2025OmniStereo: Real-time Omnidireactional Depth Estimation with Multiview Fisheye Cameras
38. CVPR 2025OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary
39. CVPR 2025Open Set Label Shift with Test Time Out-of-Distribution Reference
40. CVPR 2025Opportunistic Single-Photon Time of Flight
41. CVPR 2025Perception Tokens Enhance Visual Reasoning in Multimodal Language Models
42. CVPR 2025PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
43. CVPR 2025POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation
44. CVPR 2025PURA: Parameter Update-Recovery Test-Time Adaption for RGB-T Tracking
45. CVPR 2025Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression
46. CVPR 2025R2C: Mapping Room to Chessboard to Unlock LLM As Low-Level Action Planner
47. CVPR 2025Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
48. CVPR 2025Reasoning in Visual Navigation of End-to-end Trained Agents: A Dynamical Systems Approach
49. CVPR 2025Reasoning Mamba: Hypergraph-Guided Region Relation Calculating for Weakly Supervised Affordance Grounding
50. CVPR 2025ROD-MLLM: Towards More Reliable Object Detection in Multimodal Large Language Models

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。