多模态大模型论文趋势 2023–2026
视觉语言模型、图像/视频理解与生成式多模态基础模型
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 11,209 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 433 | 138 | 146 | 509 | 1,226 |
| 2024 | 446 | 321 | 323 | 626 | 1,716 |
| 2025 | 1,074 | 816 | 390 | 795 | 3,075 |
| 2026 | 1,366 | 1,401 | 1,051 | 1,374 | 5,192 |
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 3,319 篇，第 43 / 67 页
- NeurIPS 2025REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving
- NeurIPS 2025Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling
- NeurIPS 2025Reasoning Planning for Language Models
- NeurIPS 2025Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
- NeurIPS 2025Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
- NeurIPS 2025Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems
- NeurIPS 2025REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing
- NeurIPS 2025Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding
- NeurIPS 2025Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
- NeurIPS 2025Reliable Lifelong Multimodal Editing: Conflict-Aware Retrieval Meets Multi-Level Guidance
- NeurIPS 2025Remarkable Robustness of LLMs: Stages of Inference?
- NeurIPS 2025Rendering-Aware Reinforcement Learning for Vector Graphics Generation
- NeurIPS 2025REOBench: Benchmarking Robustness of Earth Observation Foundation Models
- NeurIPS 2025REOrdering Patches Improves Vision Models
- NeurIPS 2025ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
- NeurIPS 2025Representation Consistency for Accurate and Coherent LLM Answer Aggregation
- NeurIPS 2025Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition
- NeurIPS 2025ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code
- NeurIPS 2025Restoring Pruned Large Language Models via Lost Component Compensation
- NeurIPS 2025Restricted Spectral Gap Decomposition for Simulated Tempering Targeting Mixture Distributions
- NeurIPS 2025Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion
- NeurIPS 2025Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval
- NeurIPS 2025Revealing Multimodal Causality with Large Language Models
- NeurIPS 2025Revisiting Logit Distributions for Reliable Out-of-Distribution Detection
- NeurIPS 2025Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
- NeurIPS 2025Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks
- NeurIPS 2025Revisiting Semi-Supervised Learning in the Era of Foundation Models
- NeurIPS 2025Revitalizing SVD for Global Covariance Pooling: Halley’s Method to Overcome Over-Flattening
- NeurIPS 2025RGB-to-Polarization Estimation: A New Task and Benchmark Study
- NeurIPS 2025RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility
- NeurIPS 2025Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI
- NeurIPS 2025RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
- NeurIPS 2025Robo2VLM: Improving Visual Question Answering using Large-Scale Robot Manipulation Data
- NeurIPS 2025RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation
- NeurIPS 2025Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models
- NeurIPS 2025RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
- NeurIPS 2025Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
- NeurIPS 2025RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills
- NeurIPS 2025Robust Cross-modal Alignment Learning for Cross-Scene Spatial Reasoning and Grounding
- NeurIPS 2025Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention
- NeurIPS 2025Robust Hallucination Detection in LLMs via Adaptive Token Selection
- NeurIPS 2025Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
- NeurIPS 2025Robustness in Both Domains: CLIP Needs a Robust Text Encoder
- NeurIPS 2025RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing
- NeurIPS 2025ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks
- NeurIPS 2025RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
- NeurIPS 2025RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models
- NeurIPS 2025RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events
- NeurIPS 2025RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video
- NeurIPS 2025Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查多模态大模型在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "multimodal-llms"}
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。