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 55 / 225 页
- ICLR 2026Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
- ICLR 2026Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
- ICLR 2026VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
- ICLR 2026VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
- ICLR 2026VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations
- ICLR 2026Visual Jigsaw Post-Training Improves MLLMs
- ICLR 2026Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsing
- ICLR 2026Visual symbolic mechanisms: Emergent symbol processing in Vision Language Models
- ICLR 2026VisualPRM400K: An Effective Dataset for Training Multimodal Process Reward Models
- ICLR 2026VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models
- ICLR 2026VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning
- ICLR 2026VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision–Language Models
- ICLR 2026Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration
- ICLR 2026VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
- ICLR 2026Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning
- ICLR 2026VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation
- ICLR 2026VLM-Guided Adaptive Negative Prompting for Creative Generation
- ICLR 2026VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?
- ICLR 2026VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models
- ICLR 2026VLMgineer: Vision-Language Models as Robotic Toolsmiths
- ICLR 2026VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety
- ICLR 2026VOGUE: Unified Understanding, Generation, and Editing for Videos
- ICLR 2026VoMP: Predicting Volumetric Mechanical Property Fields
- ICLR 2026VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use
- ICLR 2026VUDG: A Dataset for Video Understanding Domain Generalization
- ICLR 2026Vulcan: Crafting Compact Class-Specific Vision Transformers For Edge Intelligence
- ICLR 2026WAFT: Warping-Alone Field Transforms for Optical Flow
- ICLR 2026WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM
- ICLR 2026WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
- ICLR 2026WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
- ICLR 2026WebWatcher: Breaking New Frontiers of Vision-Language Deep Research Agent
- ICLR 2026Weight Decay may matter more than µP for Learning Rate Transfer in Practice
- ICLR 2026WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction
- ICLR 2026What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging
- ICLR 2026What Layers When: Learning to Skip Compute in LLMs with Residual Gates
- ICLR 2026What Scales in Cross-Entropy Scaling Law?
- ICLR 2026What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation
- ICLR 2026Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity
- ICLR 2026When Foundation Models are One-Liners: Limitations and Future Directions for Time Series Anomaly Detection
- ICLR 2026When Language Models Lose Their Mind: The Consequences of Brain Misalignment
- ICLR 2026When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations
- ICLR 2026When LLMs get significantly worse: A statistical approach to detect model degradations
- ICLR 2026When MLLMs Meets Compression Distortion: A Coding Paradigm Tailored to MLLMs
- ICLR 2026When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models
- ICLR 2026When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling
- ICLR 2026When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger
- ICLR 2026When would Vision-Proprioception Policies Fail in Robotic Manipulation?
- ICLR 2026Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation
- ICLR 2026WholeBodyVLA: Towards Unified Latent VLA for Whole-body Loco-manipulation Control
- ICLR 2026Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis
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。