多模态大模型论文趋势 2023–2026

主要结论

• 多模态大模型论文从 2023 年的 1,226 篇增长到 2026 年的 5,192 篇，三年间扩大到约 4.2 倍。
• NeurIPS 是发多模态大模型论文最多的会议，2023–2026 年共 3,319 篇，占四个会议总量的 30%。
• 交叉方向里涨得最快的是应用 · computer vision：同时属于两个主题的论文从 2023 年的 35 篇增至 2026 年的 596 篇。
• 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 1；同组增长最快的AI 智能体是 12 倍，多模态大模型是 4.2 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 2026$\text{A}^3$-VLA: Automatic Perception-Guided Attention Alignment for Robot Manipulation
• ICML 2026[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation
• ICLR 2026A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic
• CVPR 20263D Space as a Scratchpad for Editable Text-to-Image Generation
• NeurIPS 2025$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
• ICML 2025Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation
• ICLR 2025$\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models
• CVPR 20252DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification
• NeurIPS 2024A Concept-Based Explainability Framework for Large Multimodal Models
• ICML 2024A Multimodal Automated Interpretability Agent
• ICLR 2024Alt-Text with Context: Improving Accessibility for Images on Twitter
• CVPR 2024Data-Efficient Multimodal Fusion on a Single GPU
• NeurIPS 20234M: Massively Multimodal Masked Modeling
• ICML 2023$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
• ICLR 2023A Primal-Dual Framework for Transformers and Neural Networks
• CVPR 20233D Concept Learning and Reasoning From Multi-View Images
• NeurIPS 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
• ICML 2026$G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA
• ICLR 2026A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models
• CVPR 20263D-IDE 3D Implicit Depth Emergent

全部多模态大模型论文

共 11,207 篇，第 1 / 225 页

1. CVPR 2026240FPS Stereo Vision from Monocular Mixed Spikes
2. CVPR 20263D Space as a Scratchpad for Editable Text-to-Image Generation
3. CVPR 20263D-IDE 3D Implicit Depth Emergent
4. CVPR 20264D Primitive-Mache Glueing Primitives for Persistent 4D Scene Reconstruction
5. CVPR 20264DEquine Disentangling Motion and Appearance for 4D Equine Reconstruction from
6. CVPR 20264DP-QA Scalable QA for 4D Perception in Vision Language Models
7. CVPR 2026A Causal Marriage between VLM and IRM from Understanding to
8. CVPR 2026A Closed-Form Solution for Debiasing Vision-Language Models with Utility Guarantees
9. CVPR 2026A Mixed Diet Makes DINO An Omnivorous Vision Encoder
10. CVPR 2026A More Word-like Image Tokenization for MLLMs
11. CVPR 2026A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning
12. CVPR 2026A2GC Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors
13. CVPR 2026Abstract 3D Perception for Spatial Intelligence in Vision-Language Models
14. CVPR 2026AceTone Bridging Words and Colors for Conditional Image Grading
15. CVPR 2026ACoT-VLA Action Chain-of-Thought for Vision-Language-Action Models
16. CVPR 2026Act Like a Pathologist Tissue-Aware Whole Slide Image Reasoning
17. CVPR 2026Act2See Emergent Active Visual Perception for Video Reasoning
18. CVPR 2026Action-Sketcher From Reasoning to Action via Visual Sketches for Robotic
19. CVPR 2026ActiveVLA Injecting Active Perception into Vision-Language-Action Models for Precise 3D
20. CVPR 2026AD-GBC Anisotropic Granular-Ball Skip-Connection Refiner for UNet-Based Medical Image Segmentation
21. CVPR 2026AdaCluster Adaptive Query-Key Clustering for Sparse Attention in Video Generation
22. CVPR 2026AdaIAT Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations
23. CVPR 2026Adapting In-context Generation for Enhanced Composed Image Retrieval
24. CVPR 2026Adapting Lightweight Image-based Counting Models for Video Crowd Counting
25. CVPR 2026Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning
26. CVPR 2026Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
27. CVPR 2026Adaptive Confidence Regularization for Multimodal Failure Detection
28. CVPR 2026AdaptVision Efficient Vision-Language Models via Adaptive Visual Acquisition
29. CVPR 2026AdaSpark Adaptive Sparsity for Efficient Long-Video Understanding
30. CVPR 2026AdaSpot Spend Resolution Where It Matters for Precise Event Spotting
31. CVPR 2026AdaSVD Singular Value Decomposition with Adaptive Mechanisms for Large Multimodal
32. CVPR 2026Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning
33. CVPR 2026ADSeeker A Knowledge-Grounded Reasoning Framework for Industry Anomaly Detection and
34. CVPR 2026Advancing Cancer Prognosis with Hierarchical Fusion of Genomic Proteomic and
35. CVPR 2026Adversarial Style Optimization Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers
36. CVPR 2026AE2VID Event-based Video Reconstruction via Aperture Modulation
37. CVPR 2026Affordance Field Intervention Enabling VLAs to Escape Memory Traps in
38. CVPR 2026Affordance-First Decomposition for Continual Learning in Video-Language Understanding
39. CVPR 2026AG-VAS Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
40. CVPR 2026AgentDet A Shared-Blackboard Multi-Agent Framework for Zero-Few-Shot Object Detection
41. CVPR 2026Agentic Retoucher for Text-To-Image Generation
42. CVPR 2026AGENTSAFE Benchmarking the Safety of Embodied Agents on Hazardous Instructions
43. CVPR 2026AGFT Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models
44. CVPR 2026AIMDepth Asymmetric Image-Event Mamba for Monocular Depth Estimation
45. CVPR 2026Air-Know Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval
46. CVPR 2026Alert-CLIP Abnormality-aware Latent-Enhanced Representation Tuning of CLIP for Video Anomaly
47. CVPR 2026Align Once to Explain Feature Alignment for Scalable B-cosification of
48. CVPR 2026Aligning What Vision-Language Models See and Perceive with Adaptive Information
49. CVPR 2026All Roads Lead to Rome Incentivizing Divergent Thinking in Vision-Language
50. CVPR 2026An Empirical Study on How Video-LLMs Answer Video Questions

常见问题

2023–2026 年四大会议一共有多少篇多模态大模型论文？

共 11,209 篇，按年份分别是 2023 年 1,226 篇、2024 年 1,716 篇、2025 年 3,075 篇、2026 年 5,192 篇。

NeurIPS 2026 有多少篇多模态大模型论文？

NeurIPS 2026 有 1,366 篇多模态大模型论文，上一届是 1,074 篇。

ICLR 2026 有多少篇多模态大模型论文？

ICLR 2026 有 1,401 篇多模态大模型论文，上一届是 816 篇。

ICML 2026 有多少篇多模态大模型论文？

ICML 2026 有 1,051 篇多模态大模型论文，上一届是 390 篇。

CVPR 2026 有多少篇多模态大模型论文？

CVPR 2026 有 1,374 篇多模态大模型论文，上一届是 795 篇。

哪个会议的多模态大模型论文最多？

NeurIPS，2023–2026 年共 3,319 篇。