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 1,366 篇，第 23 / 28 页
- NeurIPS 2026Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation
- NeurIPS 2026Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models
- NeurIPS 2026SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
- NeurIPS 2026SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization
- NeurIPS 2026Spectral Rank Calibration for Continual LoRA Merging in Multimodal Large Language Models
- NeurIPS 2026Spectral Unlearning: Transformer Structure-Preserving Updates for Language Model
- NeurIPS 2026SPEXT: A Decoupled Multi-Spectral Foundation Model for Earth Observation and Vision-Language Grounding
- NeurIPS 2026SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
- NeurIPS 2026SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera
- NeurIPS 2026SPHQuant: Efficient extreme low bit weight quantization for Vision-Language Models
- NeurIPS 2026Split Then Select: Moment-Preserving Density Control for Generalized Primitive Splatting
- NeurIPS 2026SpRePE: A Spherical Geometry-Aware Position Embedding scheme for Vision Transformers
- NeurIPS 2026SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation
- NeurIPS 2026SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs
- NeurIPS 2026Stability-Aware Self-Training for CLIP under Cross-Modal Anchoring Mismatch
- NeurIPS 2026Stable and Scalable Probabilistic Numerical Solvers for Stiff and High-Dimensional ODEs
- NeurIPS 2026StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training
- NeurIPS 2026Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
- NeurIPS 2026Static-Dynamic Disentanglement for Efficient Multi-Frame Vision-Language-Action Models
- NeurIPS 2026Statistical Query Lower Bounds for Smoothed Agnostic Learning
- NeurIPS 2026STEER: Route-Aware Adaptive Reasoning for Autonomous Driving
- NeurIPS 2026Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
- NeurIPS 2026Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
- NeurIPS 2026Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
- NeurIPS 2026Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
- NeurIPS 2026StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
- NeurIPS 2026Stitched Value Model for Diffusion Alignment
- NeurIPS 2026Stranger Things: When Objects Appear Without Their Typical Neighbours
- NeurIPS 2026StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
- NeurIPS 2026Streaming Interventions: Can Video LLMs Correct Mistakes as They Occur?
- NeurIPS 2026StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
- NeurIPS 2026StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
- NeurIPS 2026Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs
- NeurIPS 2026StructLens: A Structural Lens for Language Models via Maximum Spanning Trees
- NeurIPS 2026Structural Self-Teaching for Compositional Generation in Unified Multimodal Models
- NeurIPS 2026Structure Over Scale: Learning Visual Reasoning from Pedagogical Video
- NeurIPS 2026Structure-Prompted Multimodal Protein Language Model for Preference-Aligned Fitness Prediction
- NeurIPS 2026Structure, Subspace and System: Push the Real Limit of Extremely Low-Bit Quantization for MoE-LLMs
- NeurIPS 2026Structured Sparse Memory for Recurrent Reasoning
- NeurIPS 2026Structured State-Space Regularization for Generation-Friendly Image Tokenization
- NeurIPS 2026Subcritical Signal Propagation at Initialization in Normalization-Free Transformers
- NeurIPS 2026Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging
- NeurIPS 2026Subset-Conditioned Boundary Compensation for Missing-Modality Multimodal Classification
- NeurIPS 2026SUPERVISE: A Unified Framework for Standardized and Reproducible Superpixel Evaluation
- NeurIPS 2026Surface Recovery Is Not State Recovery: Pressure–Recovery–Relapse in Multi-turn LLMs
- NeurIPS 2026Susceptibilities for Neural Networks Learning from Physical Data
- NeurIPS 2026SWE-Pro: A Benchmark for Evaluating LLMs on Performance-Oriented Repository-Level Optimization
- NeurIPS 2026SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions
- NeurIPS 2026SynGeo: Synergizing Seeing and Proving through Revisable Geometric States
- NeurIPS 2026SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning
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。