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 11,207 篇，第 64 / 225 页
- ICML 2026h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning
- ICML 2026HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning
- ICML 2026HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models
- ICML 2026Hamiltonian Asymmetric Fusion: One-Way Safe Directed Refinement under Modality Imbalance
- ICML 2026Harnessing Non-Adversarial Robustness in Large Language Models
- ICML 2026Harnessing Spectrum Video for Subject-Level Few-Shot and Cross-Montage EEG Generalization
- ICML 2026HECTOR: Hybrid Editable Compositional Object References for Video Generation
- ICML 2026Hierarchical Image Tokenization for Multi-Scale Image Super Resolution
- ICML 2026Hierarchical Procedural Meta-Reasoning for Generalizable Multimodal Agents
- ICML 2026HieRD: Hierarchical Relational Distillation for Vision-Language Embedding Models
- ICML 2026HilbertA: Hilbert-Curve–Aligned Sparse Attention for 2D Structured Data
- ICML 2026HiMe: Hierarchical Embodied Memory for Long-Horizon Vision-Language-Action Control
- ICML 2026HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?
- ICML 2026Hölder++: Improving Quality-Coherence Trade-off in Multimodal VAEs
- ICML 2026Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
- ICML 2026How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
- ICML 2026How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
- ICML 2026How much can language models memorize?
- ICML 2026How Powerful are LLMs in Generating Formal Program Specifications?
- ICML 2026How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
- ICML 2026How2Everything: Mining the Web for How-to Procedures to Evaluate and Improve LLMs
- ICML 2026HSGG: Training-Free Hierarchical Scene Graph Generation with Geometry-Guided Relation Reasoning
- ICML 2026Hybrid Policy Distillation for LLMs
- ICML 2026HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
- ICML 2026Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning
- ICML 2026HypCL: Adapting CLIP in Hyperbolic Space for Continual Learning
- ICML 2026Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning
- ICML 2026Hyper-LLaVA: Hyperbolic Uncertainty-aware Modality-Balanced Routing for Multimodal Continual Instruction Tuning
- ICML 2026Hyperbolic Hierarchical Alignment for Video-Based Visible-Infrared Person Re-Identification
- ICML 2026Hyperbolic Multimodal Continual Learning
- ICML 2026Hyperspectral Image Fusion with Spectral-Band and Fusion-Scale Agnosticism
- ICML 2026IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning
- ICML 2026IBMA: Information Bottleneck-Based Multimodal Alignment
- ICML 2026Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Models
- ICML 2026Imagination Helps Visual Reasoning, But Not Yet in Latent Space
- ICML 2026Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthiness
- ICML 2026ImpQuant: Fine-Grained Importance-Aware Quantization for Large Vision-Language Models
- ICML 2026Improved Dynamic Algorithm for Non-monotone Submodular Maximization under Cardinality Constraint
- ICML 2026Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
- ICML 2026Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM Inference
- ICML 2026ImpText: A Benchmark and Tool-Augmented Framework for Implicit Text Reasoning
- ICML 2026Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models
- ICML 2026InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context
- ICML 2026Inner-layer Token Self-modulation as Another Scaling Axis for LLMs
- ICML 2026Innovation: An Almost Characterization of Hallucination
- ICML 2026Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers
- ICML 2026Instruction Decomposition and Action Alignment for Vision-Language Navigation
- ICML 2026Instruction Lens Score: Your Instruction Contributes a Powerful Object Hallucination Detector for Multimodal Large Language Models
- ICML 2026Interactive Person Retrieval via Multi-Turn Multimodal Conversation
- ICML 2026Interpretability Transfer from Language to Vision via Sparse Autoencoders
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。