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 66 / 104 页
- ICML 2026Learning with Admissibility: Robust Fuzzy Hashing for Cross-Modal Retrieval with Noisy Labels
- ICML 2026Left–Right Symmetry Breaking in CLIP-Style Vision-Language Models Trained on Synthetic Spatial-Relation Data
- ICML 2026Less Is More in Federated Continual Learning: RieSelect for Conflict-Aware Layer Selection in LLMs
- ICML 2026Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure
- ICML 2026Less Precise Can Be More Reliable: A Systematic Evaluation of Quantization’s Impact on VLMs Beyond Accuracy
- ICML 2026Let Language Constrain Geometry: Vision–Language Models as Semantic and Spatial Critics for 3D Generation
- ICML 2026Leveraging Evidence Priors for Robust Prompt Learning under Noisy Supervision in Vision-Language Models
- ICML 2026LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs
- ICML 2026LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning
- ICML 2026LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
- ICML 2026LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations
- ICML 2026Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
- ICML 2026Linearizing Vision Transformer with Test-Time Training
- ICML 2026Linguistic Relative Policy Optimization for Video Anomaly Reasoning
- ICML 2026LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment
- ICML 2026LiveFigure: Generating Editable Scientific Illustration with VLM Agents
- ICML 2026LLM-Guided Diagnostic Evidence Alignment for Medical Vision–Language Pretraining under Limited Pairing
- ICML 2026LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs
- ICML 2026LLMInertia: Adaptive Counter-Inertial Reasoning to Improve Evidence Faithfulness in Large Language Models
- ICML 2026LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws
- ICML 2026LLMs Lean on Priors, Not Programming Language Semantics
- ICML 2026LMM4-IC4K: A Large Multimodal Model Powered Integrated Circuit Footprint Geometry Understanding
- ICML 2026Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
- ICML 2026Localize and Neutralize: Gradient-Guided Token Suppression Against Visual Prompt Injection Attack
- ICML 2026LogicSAGE: Neuro-Symbolic Reasoning with Socratic-Guided Enhancement
- ICML 2026Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration
- ICML 2026Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
- ICML 2026Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference
- ICML 2026Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning
- ICML 2026Lookahead-GCG: Improving Universal Multi-Model Optimization-Based Jailbreaking Attacks via Stochastic Nesterov Optimization
- ICML 2026Looking Locally: Object-Centric Vision Transformers as Foundation Models for Efficient Segmentation
- ICML 2026Low-cost Full Fine-tuning: Learning What to Update for LLMs
- ICML 2026M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation Model
- ICML 2026MACD: Model-Aware Contrastive Decoding via Counterfactual Data for Video-LLMs
- ICML 2026MADA-Attack: Transferable Multi-modal Attention Distraction Adversarial Attack against Vision Language Models
- ICML 2026MAGIC: Multi-Granularity Language-Informed Image Clustering
- ICML 2026Making Expert Reasoning Learnable with Self-Distillation
- ICML 2026ManiSoft: Towards Vision-Language Manipulation for Soft Continuum Robotics
- ICML 2026Mantis: Lightweight Foundation Model for Time Series Classification
- ICML 2026MapDream: Task-Driven Map Learning for Vision-Language Navigation
- ICML 2026MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics
- ICML 2026MDN: Parallelizing Stepwise Momentum for Delta Linear Attention
- ICML 2026Measuring Meta-Cultural Competency: A Spectral Framework for LLM Knowledge Structures
- ICML 2026MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding
- ICML 2026Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Training
- ICML 2026MEDA: Medical-Oriented Activation Editing for Hallucination Mitigation in Medical Large Vision-Language Model
- ICML 2026MedCRP-CL: Continual Medical Image Segmentation via Bayesian Nonparametric Semantic Modality Discovery
- ICML 2026MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio
- ICML 2026MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts
- ICML 2026MedScope: Incentivizing "Think with Videos" for Clinical Reasoning via Coarse-to-Fine Tool Calling
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。