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 1,401 篇，第 23 / 29 页
- ICLR 2026Sparsity-promoting Fine-tuning for Equivariant Materials Foundation Model
- ICLR 2026Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine Differentiation
- ICLR 2026Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
- ICLR 2026Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes
- ICLR 2026Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models
- ICLR 2026SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
- ICLR 2026Spatially Guided Training for Vision-Language-Action Model
- ICLR 2026SpatialViz-Bench: A Cognitively-Grounded Benchmark for Diagnosing Spatial Visualization in MLLMs
- ICLR 2026SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
- ICLR 2026SpectraLLM: Uncovering the Ability of LLMs for Molecule Structure Elucidation from Multi-Spectra
- ICLR 2026Speculative Speculative Decoding
- ICLR 2026Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences
- ICLR 2026SPICE: Submodular Penalized Information–Conflict Selection for Efficient Large Language Model Training
- ICLR 2026SPIKE-RL: Video-LLMs meet Bayesian Surprise
- ICLR 2026SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike Streams
- ICLR 2026SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs
- ICLR 2026SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus
- ICLR 2026SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports
- ICLR 2026Spotlight on Token Perception for Multimodal Reinforcement Learning
- ICLR 2026SPR$^2$Q: Static Priority-based Rectifier Routing Quantization for Image Super-Resolution
- ICLR 2026SPRIG: Improving Large Language Model Performance by System Prompt Optimization
- ICLR 2026SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
- ICLR 2026SRT: Super-Resolution for Time Series via Disentangled Rectified Flow
- ICLR 2026ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning
- ICLR 2026ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMs
- ICLR 2026StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
- ICLR 2026STAT: Skill-Targeted Adaptive Training
- ICLR 2026Steering and Rectifying Latent representation manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection
- ICLR 2026Steering Autoregressive Music Generation with Recursive Feature Machines
- ICLR 2026Steering Embedding Models with Geometric Rotation: Mapping Semantic Relationships Across Languages and Models
- ICLR 2026Steering MoE LLMs via Expert (De)Activation
- ICLR 2026Steering the Herd: A Framework for LLM-based Control of Social Learning
- ICLR 2026STEM: SCALING TRANSFORMERS WITH EMBEDDING MODULES
- ICLR 2026Stochastic Neural Networks for Causal Inference with Missing Confounders
- ICLR 2026StochasTok: Improving Fine-Grained Subword Understanding in LLMs
- ICLR 2026Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs
- ICLR 2026StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning
- ICLR 2026Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
- ICLR 2026Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters
- ICLR 2026StreamingThinker: Large Language Models Can Think While Reading
- ICLR 2026StreamingVLM: Real-Time Understanding for Infinite Video Streams
- ICLR 2026String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation
- ICLR 2026Structural Prognostic Event Modeling for Multimodal Cancer Survival Analysis
- ICLR 2026Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNs
- ICLR 2026STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning
- ICLR 2026SuperF: Neural Implicit Fields for Multi-Image Super-Resolution
- ICLR 2026Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking
- ICLR 2026Supporting Multimodal Intermediate Fusion with Informatic Constraint and Distribution Coherence
- ICLR 2026SURGE: Surprise-Guided Token Reduction for Efficient Video Understanding with VLMs
- ICLR 2026SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
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。