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 3,319 篇，第 28 / 67 页
- NeurIPS 2026Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have
- NeurIPS 2026Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs
- NeurIPS 2026Why Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention
- NeurIPS 2026Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space
- NeurIPS 2026Why Heavy-Tailed Weights Predict Model Quality
- NeurIPS 2026Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It
- NeurIPS 2026Winfree Oscillatory Neural Network
- NeurIPS 2026Witness Overlap: Directional Provenance Inside Open-Weight Model Families
- NeurIPS 2026Words Before Pixels: Selective Modality Routing for Vision-Language Model Unlearning
- NeurIPS 2026Words That Make Language Models Perceive
- NeurIPS 2026World–Value–Action Model: Implicit Planning for Vision–Language–Action Systems
- NeurIPS 2026WorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution
- NeurIPS 2026WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation
- NeurIPS 2026WovenAnchor Matcher: Specialized Intra- and Inter-Image Context Modeling for Feature Matching
- NeurIPS 2026XMNoise2Clean: Cross-Modal Denoising Under Sparse Data
- NeurIPS 2026Z0-Inf: Zeroth Order Approximation for Data Influence
- NeurIPS 2025$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
- NeurIPS 2025$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection
- NeurIPS 20253D Visual Illusion Depth Estimation
- NeurIPS 20253D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks
- NeurIPS 20253DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
- NeurIPS 20253EED: Ground Everything Everywhere in 3D
- NeurIPS 20254D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration
- NeurIPS 20254DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
- NeurIPS 20254KAgent: Agentic Any Image to 4K Super-Resolution
- NeurIPS 2025A Circular Argument: Does RoPE need to be Equivariant for Vision?
- NeurIPS 2025A compressive-expressive communication framework for compositional representations
- NeurIPS 2025A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
- NeurIPS 2025A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
- NeurIPS 2025A Minimalistic Unified Framework for Incremental Learning across Image Restoration Tasks
- NeurIPS 2025A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detection
- NeurIPS 2025A Multimodal BiMamba Network with Test-Time Adaptation for Emotion Recognition Based on Physiological Signals
- NeurIPS 2025A Standardized Benchmark for Multilabel Antimicrobial Peptide Classification
- NeurIPS 2025A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
- NeurIPS 2025A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity
- NeurIPS 2025A unified framework for establishing the universal approximation of transformer-type architectures
- NeurIPS 2025A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis
- NeurIPS 2025A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking
- NeurIPS 2025A$^3$E: Towards Compositional Model Editing
- NeurIPS 2025A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding
- NeurIPS 2025AC-LoRA: (Almost) Training-Free Access Control Aware Multi-Modal LLMs
- NeurIPS 2025Accelerating Diffusion LLMs via Adaptive Parallel Decoding
- NeurIPS 2025Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings
- NeurIPS 2025ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking
- NeurIPS 2025Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models
- NeurIPS 2025Activated LoRA: Fine-tuned LLMs for Intrinsics
- NeurIPS 2025Active Test-time Vision-Language Navigation
- NeurIPS 2025ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning
- NeurIPS 2025AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining
- NeurIPS 2025Adaptive Gradient Masking for Balancing ID and MLLM-based Representations in Recommendation
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。