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 62 / 225 页
- ICML 2026Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
- ICML 2026Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
- ICML 2026Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization
- ICML 2026Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment
- ICML 2026Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
- ICML 2026EnsembleVLA: Ensemble Learning for Vision-Language Action Models
- ICML 2026EntRAG: Entity-Centric Retrieval-Augmented Generation for Knowledge-based Visual Question Answering
- ICML 2026Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching
- ICML 2026ERGeoBench: A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models
- ICML 2026Escaping the Likelihood Trap: Geometric Diversity Optimization for Long-Form Image Captioning
- ICML 2026Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions
- ICML 2026Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals
- ICML 2026Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems
- ICML 2026Evaluating Sample Utility for Efficient Data Selection by Mimicking Model Weights
- ICML 2026EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization
- ICML 2026Evolving Interdependent Operators with Large Language Models for Multi-Objective Combinatorial Optimization
- ICML 2026ExpAlign: Expectation-Guided Vision–Language Alignment for Open-Vocabulary Grounding
- ICML 2026ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns
- ICML 2026Extracting alignment data in open models
- ICML 2026ExVerus: Verus Proof Repair via Counterexample Reasoning
- ICML 2026Failure is Feedback: History-Aware Backtracking for Agentic Traversal in Multimodal Graphs
- ICML 2026FairSSL: Fair Multimodal Self-Supervised Learning
- ICML 2026Faithful Mobile GUI Agents with Guided Advantage Estimator
- ICML 2026Faithful Relational Reasoning with Region-based Embeddings: Expressivity of Convex Coordinate-wise Models
- ICML 2026Fast and Accurate Causal Parallel Decoding using Jacobi Forcing
- ICML 2026Fast and Expressive Multi-Byte Prediction with Probabilistic Circuits
- ICML 2026Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs
- ICML 2026FedSSM: State Space Model-based Proactive Inference for Heterogeneous Multimodal Federated Learning
- ICML 2026FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
- ICML 2026Find, Fix, Reason: Context Repair for Video Reasoning
- ICML 2026Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy
- ICML 2026Fine-Tuning of Transformer models with Frames
- ICML 2026FiSeR: Fine-Grained Source Representations for Cross-Domain AI Image Detection
- ICML 2026FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences
- ICML 2026FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations
- ICML 2026FlowNar: Scalable Streaming Narration for Long-Form Videos
- ICML 2026FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation
- ICML 2026FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation
- ICML 2026Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain
- ICML 2026Foreground-Aware Token Routing Vision Transformer for Real-Time Satellite Video Tracking
- ICML 2026Forensic Prompting with Dual-Action Policy Optimization for Vision-Language Forgery Detection and Localization
- ICML 2026Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding
- ICML 2026Formalizing the Binding Problem
- ICML 2026FOVI: A biologically-inspired foveated interface for deep vision models
- ICML 2026FrameOracle: Learning What to See and How Much to See in Videos
- ICML 2026FreeRet: MLLMs as Training-Free Retrievers
- ICML 2026Frequency-Aware Perceptual Optimization for Low-Complexity Implicit Image Compression
- ICML 2026FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision–Language Models
- ICML 2026From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion
- ICML 2026From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model
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。