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 1,051 篇，第 18 / 22 页
- ICML 2026STD-Former: Image-Conditioned Texture Dictionary Encoding with Sparse Topological Supervision for Texture Recognition
- ICML 2026Steal the Patch Size: Adversarially Manipulate Vision Language Models
- ICML 2026Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation
- ICML 2026Step-Resolved Data Attribution for Looped Transformers
- ICML 2026STORM: Segment, Track, and Object Re-Localization from a Single Image
- ICML 2026StructMamPose: From Sequential Perception to Structural Reasoning for 3D Human Pose Estimation
- ICML 2026STT-LLM: Structural-Temporal Tokenization for Adapting LLMs to Longitudinal Clinical Profiles
- ICML 2026Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
- ICML 2026Suppress and Diversify: Refining Robust Pathways for Corruption Robustness
- ICML 2026SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding
- ICML 2026SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?
- ICML 2026Symbal: Detecting Systematic Misalignments in Model-Generated Captions
- ICML 2026Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization
- ICML 2026Synergistic Space-Vision Processing for Predicate Inference
- ICML 2026SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment
- ICML 2026Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code
- ICML 2026T-Edit: Triple-Branch Diffusion Anchoring for Consistent Editing
- ICML 2026Tabero: Learning Gentle Manipulation with Closed-Loop Force Feedback from Vision, Touch, and Language
- ICML 2026TabMGP: Martingale Posterior with TabPFN
- ICML 2026Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework
- ICML 2026Task-and-Model-Aware Fractal-Consistency for Efficient LLM Reasoning
- ICML 2026Task-Aware Mechanism: Hybrid MoE Vision Tower Towards Holistic Video Understanding
- ICML 2026Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning
- ICML 2026TCAP: Tri-Component Attention Profiling for Unsupervised Backdoor Detection in MLLM Fine-Tuning
- ICML 2026Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
- ICML 2026Temporal-Aware Reasoning Optimization for Video Temporal Grounding
- ICML 2026Test-Time Debiasing with Probabilistic Prompts via Wasserstein Distance in Vision-Language Models
- ICML 2026Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding
- ICML 2026Text-Conditional JEPA for Learning Semantically Rich Visual Representations
- ICML 2026Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space
- ICML 2026TextME: Bridging Unseen Modalities Through Text Descriptions
- ICML 2026Textual Supervision Enhances Geospatial Representations in Vision-Language Models
- ICML 2026TGV-KV: Text-Grounded KV Eviction for Vision-Language Models
- ICML 2026The Abstraction Gap in Vision-Language Causal Reasoning
- ICML 2026The Convergent Representation of Contrastive Vision-Language Models: Geometry, Modality Gap and Shared Space Alignment
- ICML 2026The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path
- ICML 2026The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-Modal Divergence
- ICML 2026The Geometry of Representational Failures in Vision Language Models
- ICML 2026The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding
- ICML 2026The Hidden Risk: Membership Inference Attacks on Multimodal Federated Learning via Modality Imbalance
- ICML 2026The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space
- ICML 2026The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
- ICML 2026The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
- ICML 2026The Power of Power Law: Asymmetry Enables Compositional Reasoning
- ICML 2026The Realignment Problem: When Right becomes Wrong in LLMs
- ICML 2026The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs
- ICML 2026The Signal is in the Steps: Local Scoring for Reasoning Data Selection
- ICML 2026The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity
- ICML 2026The Tell-Tale Norm: $\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models
- ICML 2026Think in Cloud, Look at Edges: Semantic-Driven Query Decomposition for Efficient Video Reasoning
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。