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 816 篇，第 7 / 17 页
- ICLR 2025HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment
- ICLR 2025HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging
- ICLR 2025Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models
- ICLR 2025Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging
- ICLR 2025High-Quality Joint Image and Video Tokenization with Causal VAE
- ICLR 2025How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension
- ICLR 2025How Does Critical Batch Size Scale in Pre-training?
- ICLR 2025How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
- ICLR 2025How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations
- ICLR 2025HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
- ICLR 2025HShare: Fast LLM Decoding by Hierarchical Key-Value Sharing
- ICLR 2025Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment
- ICLR 2025Hymba: A Hybrid-head Architecture for Small Language Models
- ICLR 2025Hyper-Connections
- ICLR 2025IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model
- ICLR 2025Image and Video Tokenization with Binary Spherical Quantization
- ICLR 2025ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination
- ICLR 2025Implicit In-context Learning
- ICLR 2025Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization Approach
- ICLR 2025Improving Instruction-Following in Language Models through Activation Steering
- ICLR 2025Improving Pretraining Data Using Perplexity Correlations
- ICLR 2025Improving Reasoning Performance in Large Language Models via Representation Engineering
- ICLR 2025In Search of Forgotten Domain Generalization
- ICLR 2025In vivo cell-type and brain region classification via multimodal contrastive learning
- ICLR 2025INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph
- ICLR 2025Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
- ICLR 2025Information Theoretic Text-to-Image Alignment
- ICLR 2025Injecting Universal Jailbreak Backdoors into LLMs in Minutes
- ICLR 2025Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
- ICLR 2025Intelligence at the Edge of Chaos
- ICLR 2025Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention
- ICLR 2025Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment
- ICLR 2025Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks
- ICLR 2025Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology
- ICLR 2025Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
- ICLR 2025Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs
- ICLR 2025Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations
- ICLR 2025IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities
- ICLR 2025Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
- ICLR 2025Is In-Context Learning Sufficient for Instruction Following in LLMs?
- ICLR 2025Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist
- ICLR 2025Is Your Multimodal Language Model Oversensitive to Safe Queries?
- ICLR 2025Is Your Video Language Model a Reliable Judge?
- ICLR 2025It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation
- ICLR 2025Jamba: Hybrid Transformer-Mamba Language Models
- ICLR 2025JetFormer: An autoregressive generative model of raw images and text
- ICLR 2025K-HALU: Multiple Answer Korean Hallucination Benchmark for Large Language Models
- ICLR 2025KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models
- ICLR 2025KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI
- ICLR 2025kNN Attention Demystified: A Theoretical Exploration for Scalable Transformers
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。