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 5,190 篇，第 65 / 104 页
- ICML 2026Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow
- ICML 2026Intrinsic Gradient Suppression for Label-Noise Prompt Tuning in Vision–Language Models
- ICML 2026IPMark: A Sentence-Level Watermark for LLMs with Hierarchical Personalization and Efficient Detection
- ICML 2026IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring
- ICML 2026IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination
- ICML 2026Is Code Better Than Language for Algorithmic Reasoning?
- ICML 2026Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives
- ICML 2026IVQA-LD: Inclusive Multimodal Understanding for Population with Limb Deficiency
- ICML 2026Jailbreaking Vision-Language Models Through the Visual Modality
- ICML 2026Joint Navigation and Manipulation Planning with 3D Interaction Chains
- ICML 2026Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streams
- ICML 2026Know Thyself, Know Thy User: Intrinsic Dual-Perspective Reasoning for Role-Playing LLMs
- ICML 2026KODA: Contrastive Representation Comparison and Alignment for Vision-Language Foundation Models
- ICML 2026KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls
- ICML 2026KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices
- ICML 2026Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency
- ICML 2026LAGEA: Language Guided Embodied Agents for Robotic Manipulation
- ICML 2026Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies
- ICML 2026LALM-as-a-Judge: Benchmarking Large Audio-Language Models for Safety Evaluation in Multi-Turn Spoken Dialogues
- ICML 2026LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
- ICML 2026LangPrecip: Language-Aware Multimodal Precipitation Nowcasting
- ICML 2026LaRA-Fusion: Latent-Robust Adaptation via Dual-Loop Constraints for Infrared and Visible Image Fusion
- ICML 2026LARA: Latent Action Representation Alignment for Vision-Language-Action Models
- ICML 2026Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge
- ICML 2026Large Language Models as Topological Thinkers: A Benchmark on Graph Persistent Homology
- ICML 2026Large Vision-Language Models Get Lost in Attention
- ICML 2026LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment
- ICML 2026LaST$_{0}$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
- ICML 2026Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
- ICML 2026LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs
- ICML 2026LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs
- ICML 2026LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer
- ICML 2026LAVA: A Unified Framework for Finetuning Language and Vision Models
- ICML 2026Lavida-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models
- ICML 2026Layer-Centric Factors of Variation Disentanglement for Task- and Model-Agnostic Generalization
- ICML 2026LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
- ICML 2026Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
- ICML 2026Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training
- ICML 2026Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs
- ICML 2026Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization
- ICML 2026Learning GUI Grounding with Spatial Reasoning from Visual Feedback
- ICML 2026Learning More from Less: Unlocking Internal Representations for Benchmark Compression
- ICML 2026Learning Rewrite-Invariant Reasoning with Targeted Alternation Training
- ICML 2026Learning Self-Correction in Vision–Language Models via Rollout Augmentation
- ICML 2026Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models
- ICML 2026Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
- ICML 2026Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models
- ICML 2026Learning to Memorize with Attributive and Associative Memory for Online Test-Time Adaptation of Vision-Language Models
- ICML 2026Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
- ICML 2026Learning When to Attend: Conditional Memory Access for Long-Context 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。