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 23 / 225 页
- CVPR 2026Stay in your Lane Role Specific Queries with Overlap Suppression
- CVPR 2026STiTch Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot
- CVPR 2026Streaming Video Crime Anticipation with Spatio-Temporal Causal Reasoning
- CVPR 2026Streaming Video Instruction Tuning
- CVPR 2026StreamingTOM Streaming Token Compression for Efficient Video Understanding
- CVPR 2026Streamlined Open-Vocabulary Human-Object Interaction Detection
- CVPR 2026Structural Graph Probing of Vision-Language Models
- CVPR 2026StructXLIP Enhancing Vision-language Models with Multimodal Structural Cues
- CVPR 2026Style-GRPO Semantic-Aware Preference Optimization for Image Style Transfer Guided by
- CVPR 2026Subspace Alignment for CLIP-based Continual Learning via Canonical Correlation Analysis
- CVPR 2026SubspaceAD Training-Free Few-Shot Anomaly Detection via Subspace Modeling
- CVPR 2026Superman Unifying Skeleton and Vision for Human Motion Perception and
- CVPR 2026SVBench Evaluation of Video Generation Models on Social Reasoning
- CVPR 2026SWIFT Sliding Window Reconstruction for Few-Shot Training-Free Generated Video Attribution
- CVPR 2026SwiftTailor Efficient 3D Garment Generation with Geometry Image Representation
- CVPR 2026SwiftVLA Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal
- CVPR 2026Symphony A Cognitively-Inspired Multi-Agent System for Long-Video Understanding
- CVPR 2026SynCLIP Synonym-Coherent Language-Image Pretraining for Robust Open-Vocabulary Dense Perception
- CVPR 2026Synthesizing Visual Concepts as Vision-Language Programs
- CVPR 2026SynthRGB-T Language-Vision Guided Image Translation for Diversity Synthesis
- CVPR 2026T2SGrid Temporal-to-Spatial Gridification for Video Temporal Grounding
- CVPR 2026TableMix Enhancing Multimodal Table Reasoning in MLLMs from a Data-Centric
- CVPR 2026TALO Pushing 3D Vision Foundation Models Towards Globally Consistent Online
- CVPR 2026TANGO Learning Distribution-wise Foundation Prior Consistency and Instance-wise Style Calibration
- CVPR 2026TANGO Text-Anchored Guided Optimization for Robust Fine-tuning Vision-Language Models under
- CVPR 2026Task-Aware Image Signal Processor for Advanced Visual Perception
- CVPR 2026Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal
- CVPR 2026TDATR Improving End-to-End Table Recognition via Table Detail-Aware Learning and
- CVPR 2026Teacher-Guided Routing for Sparse Vision Mixture-of-Experts
- CVPR 2026TEAR Temporal-aware Automated Red-teaming for Text-to-Video Models
- CVPR 2026Temporal Inversion for Learning Interval Change in Chest X-Rays
- CVPR 2026TerraScope Pixel-Grounded Visual Reasoning for Earth Observation
- CVPR 2026TESSERA Temporal Embeddings of Surface Spectra for Earth Representation and
- CVPR 2026Test-Time Attention Purification for Backdoored Large Vision Language Models
- CVPR 2026Test-Time Multi-Prompt Adaptation for Open-Vocabulary Remote Sensing Image Segmentation
- CVPR 2026Test-Time Perturbation Tuning with Delayed Feedback for Vision-Language-Action Models
- CVPR 2026Text-guided Feature Disentanglement for Cross-modal Gait Recognition
- CVPR 2026Text-Image Conditioned 3D Generation
- CVPR 2026Text-Printed Image Bridging the Image-Text Modality Gap for Text-centric Training
- CVPR 2026TextFM Robust Semi-dense Feature Matching with Language Guidance
- CVPR 2026TF-SSD A Strong Pipeline via Synergic Mask Filter for Training-free
- CVPR 2026The Blind Spot of Adaptation Quantifying and Mitigating Forgetting in
- CVPR 2026The Consistency Critic Correcting Inconsistencies in Generated Images via Reference-Guided
- CVPR 2026The Geometry of Robustness Optimizing Loss Landscape Curvature and Feature
- CVPR 2026The LLM Bottleneck Why Open-Source Vision LLMs Struggle with Hierarchical
- CVPR 2026The Midas Touch for Metric Depth
- CVPR 2026The Missing Point in Vision Transformers for Universal Image Segmentation
- CVPR 2026THE MORE THE MERRIER CONTRASTIVE FUSION FOR HIGHER-ORDER MULTIMODAL ALIGNMENT
- CVPR 2026The Road Less Seen Segment Exploration for Weakly Supervised Video
- CVPR 2026The SA-FARI Dataset Segment Anything in Footage of Animals for
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。