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 1,051 篇，第 1 / 22 页

1. ICML 2026“very likely” Means “uncertain”? How LLMs Diverge from Humans in Linguistic Uncertainty Quantification
2. ICML 2026[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation
3. ICML 2026$\mathcal{O}(\log N)$ Latent Dimension Suffices for Universal Approximation of Permutation-invariant Function
4. ICML 2026$\sigma$: Sigmoid Modulation for Ultra High Resolution Diffusion
5. ICML 2026$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data
6. ICML 2026$G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA
7. ICML 20263D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding
8. ICML 20263ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models
9. ICML 2026A Bayesian Approach to Quantify the Uncertainty of Human Ratings in a Single-Instance Multimodal Framework
10. ICML 2026A Close Look at Negative Label Guided Out-of-distribution Detection in Pre-trained Vision-Language Models
11. ICML 2026A Computational Framework for Evaluating Human-likeness in LLMs' Open-ended Human Behaviors
12. ICML 2026A Generalist Pair-wise Progress Critic Model for Vision-Language-Action Robots
13. ICML 2026A Progressive Evidence Localization Framework Based on Wasserstein Gradient Flows for Document Visual Question Answering
14. ICML 2026A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention
15. ICML 2026A Robust Optimization Guided Pruning Framework for Vision and Large Language Models
16. ICML 2026A robust PPG foundation model using multimodal physiological supervision
17. ICML 2026A Very Big Video Reasoning Suite
18. ICML 2026A²RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation
19. ICML 2026A3: an Analytical Low-Rank Approximation Framework for Attention
20. ICML 2026ABCD: All Biases Come Disguised
21. ICML 2026AC-ODM: Actor–Critic Online Data Mixing for Sample-Efficient LLM Pretraining
22. ICML 2026Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models
23. ICML 2026Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models
24. ICML 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
25. ICML 2026ActiveScope: Actively Seeking and Correcting Perception for MLLMs
26. ICML 2026AD-MIR: Bridging the Gap from Perception to Persuasion in Advertising Video Understanding via Structured Reasoning
27. ICML 2026AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments
28. ICML 2026AdaNav: Adaptive Reasoning with Uncertainty for Vision-Language Navigation
29. ICML 2026Adaptive Generation of Bias-Eliciting Questions for LLMs
30. ICML 2026Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision-Language Models
31. ICML 2026Adaptive Time Series Reasoning via Segment Selection
32. ICML 2026Adaptive Token Refinement in Long-Tailed Large Vision-Language Models Fine-Tuning
33. ICML 2026ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools — From Consensus Learning to Ambiguity-Driven Emotion Reasoning
34. ICML 2026Advancing Analytic Class-Incremental Learning through Vision-Language Calibration
35. ICML 2026Adversarial Training for Process Reward Models
36. ICML 2026AesFormer: Transform Everyday Photos into Beautiful Memories
37. ICML 2026AffIn-Space: Learning Affine-Invariant Representations for 3D Spatial Understanding with MLLMs
38. ICML 2026Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning
39. ICML 2026AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs
40. ICML 2026AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation
41. ICML 2026AIR: Post-training Data Selection for Reasoning via Attention Head Influence
42. ICML 2026AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models
43. ICML 2026AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs
44. ICML 2026AlignedNorm: Prompting Vision–Language Models via Coupled Prompt Field
45. ICML 2026Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs
46. ICML 2026AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in Unified Multimodal Models via Decompositional Verifiable Reward
47. ICML 2026Alterbute: Editing Intrinsic Attributes of Objects in Images
48. ICML 2026An In-Depth Study on Deep Learning Model Cloning
49. ICML 2026Anchor-Final Self-Supervision Drives Hallucination-Aware Optimization in Large Vision-Language Models
50. ICML 2026ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models

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。