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 5,190 篇，第 52 / 104 页
- ICLR 2026Test-Time Scaling with Reflective Generative Model
- ICLR 2026Text summarization via global structure awareness
- ICLR 2026The Achilles’ Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities
- ICLR 2026The Art of Scaling Reinforcement Learning Compute for LLMs
- ICLR 2026The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
- ICLR 2026THE END OF MANUAL DECODING: TOWARDS TRULY END-TO-END LANGUAGE MODELS
- ICLR 2026The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm
- ICLR 2026The Geometry of Reasoning: Flowing Logics in Representation Space
- ICLR 2026The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
- ICLR 2026The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
- ICLR 2026The Lattice Representation Hypothesis and Concept Algebra in LLMs
- ICLR 2026THE PATH OF LEAST RESISTANCE: GUIDING LLM REASONING TRAJECTORIES WITH PREFIX CONSENSUS
- ICLR 2026The Pensieve Paradigm: Stateful Language Models with Learned Memory Management
- ICLR 2026The Softmax Bottleneck Does Not Limit the Probabilities of the Most Likely Tokens
- ICLR 2026The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss
- ICLR 2026The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM
- ICLR 2026THEMIS: Towards Holistic Evaluation of MLLMs for Scientific Paper Fraud Forensics
- ICLR 2026Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
- ICLR 2026Thicker and Quicker: The Jumbo Token for Fast Plain Vision Transformers
- ICLR 2026Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning
- ICLR 2026Think Then Embed: Generative Context Improves Multimodal Embedding
- ICLR 2026Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
- ICLR 2026ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
- ICLR 2026Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
- ICLR 2026Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs
- ICLR 2026TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D Alignment
- ICLR 2026TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning
- ICLR 2026Time Optimal Execution of Action Chunk Policies Beyond Demonstration Speed
- ICLR 2026TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
- ICLR 2026TimeSeriesExamAgent: Creating TimeSeries Reasoning Benchmarks at Scale
- ICLR 2026TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICES
- ICLR 2026TNT: Improving Chunkwise Training for Test-Time Memorization
- ICLR 2026To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration
- ICLR 2026To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
- ICLR 2026Tokenisation over Bounded Alphabets is Hard
- ICLR 2026TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
- ICLR 2026ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models
- ICLR 2026Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
- ICLR 2026Towards a Foundation Model for Crowdsourced Label Aggregation
- ICLR 2026Towards All-Atom Foundation Models for Biomolecular Binding Affinity Prediction
- ICLR 2026Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models
- ICLR 2026Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interaction
- ICLR 2026Towards Quantization-Aware Training for Ultra-Low-Bit Reasoning LLMs
- ICLR 2026Towards Sampling Data Structures for Tensor Products in Turnstile Streams
- ICLR 2026Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO
- ICLR 2026Towards Spatial Supersensing in Video
- ICLR 2026Towards Text-Mask Consistency in Medical Image Segmentation
- ICLR 2026Towards True Speech-to-Speech Models Without Text Guidance
- ICLR 2026Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
- ICLR 2026Towards Understanding Valuable Preference Data for Large Language Model Alignment
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。