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 1,401 篇，第 14 / 29 页
- ICLR 2026LLMs Process Lists With General Filter Heads
- ICLR 2026LLMs Struggle to Balance Reasoning and World Knowledge in Causal Narrative Understanding
- ICLR 2026lmgame-Bench: How Good are LLMs at Playing Games?
- ICLR 2026Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression
- ICLR 2026Locality-Attending Vision Transformer
- ICLR 2026Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
- ICLR 2026Log-Linear Attention
- ICLR 2026LogiConBench: Benchmarking Logical Consistencies of LLMs
- ICLR 2026LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization
- ICLR 2026Long-range Modeling and Processing of Multimodal Event Sequences
- ICLR 2026Long-tailed Test-Time Adaptation for Vision-Language Models
- ICLR 2026LongHorizonUI: A Unified Framework for Robust long-horizon Task Automation of GUI Agent
- ICLR 2026Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation
- ICLR 2026LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation
- ICLR 2026Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs
- ICLR 2026LSA: Layer-wise Sparsity Allocation for Large Language Model Pruning Based on Minimal Linear Reconstruction Error
- ICLR 2026LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer
- ICLR 2026LVTINO: LAtent Video consisTency INverse sOlver for High Definition Video Restoration
- ICLR 2026LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
- ICLR 2026M$^2$-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data Mining
- ICLR 2026M$^3$E: Continual Vision-and-Language Navigation via Mixture of Macro and Micro Experts
- ICLR 2026M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding
- ICLR 2026Many-for-Many: Unify the Training of Multiple Video and Image Generation and Manipulation Tasks
- ICLR 2026MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
- ICLR 2026Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless Localization
- ICLR 2026Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
- ICLR 2026Mapping Post-Training Forgetting in Language Models at Scale
- ICLR 2026MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
- ICLR 2026MARS-Sep: Multimodal-Aligned Reinforced Sound Separation
- ICLR 2026MASAM: Multimodal Adaptive Sharpness-Aware Minimization for Heterogeneous Data Fusion
- ICLR 2026MaskInversion: Localized Embeddings via Optimization of Explainability Maps
- ICLR 2026MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs
- ICLR 2026MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning
- ICLR 2026Math Blind: Failures in Diagram Understanding Undermine Reasoning in MLLMs
- ICLR 2026MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task
- ICLR 2026Matting Anything 2: Towards Video Matting for Anything
- ICLR 2026MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains
- ICLR 2026MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
- ICLR 2026Measure Twice, Cut Once: A Semantic-Oriented Approach to Video Temporal Localization with Video LLMs
- ICLR 2026Medical thinking with multiple images
- ICLR 2026MedLesionVQA: A Multimodal Benchmark Emulating Clinical Visual Diagnosis for Body Surface Health
- ICLR 2026MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning
- ICLR 2026MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
- ICLR 2026Memento: Toward an All-Day Proactive Assistant for Ultra-Long Streaming Video
- ICLR 2026Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models
- ICLR 2026MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
- ICLR 2026MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
- ICLR 2026MergeTune: Continued Fine-Tuning of Vision-Language Models
- ICLR 2026MeSH: Memory-as-State-Highways for Recursive Transformers
- ICLR 2026Meta-Adaptive Prompt Distillation for Few-Shot Visual Question Answering
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。