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 36 / 104 页
- ICLR 2026FakeXplain: AI-Generated Image Detection via Human-Aligned Grounded Reasoning
- ICLR 2026Falcon: Fast Proximal Linearization of Normalized Cuts for Unsupervised Image Segmentation
- ICLR 2026Fantastic Tractor-Dogs and How Not to Find Them With Open-Vocabulary Detectors
- ICLR 2026FASA: FREQUENCY-AWARE SPARSE ATTENTION
- ICLR 2026Fast Data Mixture Optimization via Gradient Descent
- ICLR 2026FaSTA*: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing
- ICLR 2026Fastcar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge
- ICLR 2026Faster Vision Transformers with Adaptive Patches
- ICLR 2026FASTer: Toward Powerful and Efficient Autoregressive Vision–Language–Action Models with Learnable Action Tokenizer and Block-wise Decoding
- ICLR 2026Fed-Duet: Dual Expert-Orchestrated Framework for Continual Federated Vision-Language Learning
- ICLR 2026FETAL-GAUGE: A BENCHMARK FOR ASSESSING VISION-LANGUAGE MODELS IN FETAL ULTRASOUND
- ICLR 2026Figma2Code: Automating Multimodal Design to Code in the Wild
- ICLR 2026Fine-Grained Activation Steering: Steering Less, Achieving More
- ICLR 2026Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning
- ICLR 2026FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding
- ICLR 2026FlashRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models
- ICLR 2026FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
- ICLR 2026Flatness Guided Test-Time Adaptation for Vision-Language Models
- ICLR 2026Flatter Tokens are More Valuable for Speculative Draft Model Training
- ICLR 2026FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding
- ICLR 2026Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets
- ICLR 2026FlowAD: Ego-Scene Interactive Modeling for Autonomous Driving
- ICLR 2026FlowGen: Synthesizing Diverse Flowcharts to Enhance and Benchmark MLLM Reasoning
- ICLR 2026FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models
- ICLR 2026Fluent Alignment with Disfluent Judges: Post-training for lower-resource languages
- ICLR 2026FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark
- ICLR 2026FOCUS: Efficient Keyframe Selection for Long Video Understanding
- ICLR 2026Following the Navigation: Enhancing Small Language Models Contextual Reasoning with LLM Guidance
- ICLR 2026FoNE: Precise Single-Token Number Embeddings via Fourier Features
- ICLR 2026Fostering Video Reasoning via Next-Event Prediction
- ICLR 2026Foundation Models for Causal Inference via Prior-Data Fitted Networks
- ICLR 2026Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains
- ICLR 2026FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting
- ICLR 2026FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMs
- ICLR 2026Free Energy Mixer
- ICLR 2026FreeViS: Training-free Video Stylization with Inconsistent References
- ICLR 2026FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension
- ICLR 2026FRIEDA: Benchmarking Multi-Step Cartographic Reasoning in Vision-Language Models
- ICLR 2026From ``Sure" to ``Sorry": Detecting Jailbreak in Large Vision Language Model via JailNeurons
- ICLR 2026From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics
- ICLR 2026From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization
- ICLR 2026From Evaluation to Defense: Advancing Safety in Video Large Language Models
- ICLR 2026From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones
- ICLR 2026From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
- ICLR 2026From Natural Alignment to Conditional Controllability in Multimodal Dialogue
- ICLR 2026From Pixels to Words -- Towards Native Vision-Language Primitives at Scale
- ICLR 2026From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation
- ICLR 2026From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors
- ICLR 2026From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training
- ICLR 2026From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
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。