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 2,676 篇，第 12 / 54 页
- ICLR 2026InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models
- ICLR 2026Inoculation Prompting: Eliciting traits from LLMs during training can reduce trait expression at test-time
- ICLR 2026InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search
- ICLR 2026Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved Instructions
- ICLR 2026Interleaving Reasoning for Better Text-to-Image Generation
- ICLR 2026InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models
- ICLR 2026InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models
- ICLR 2026Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
- ICLR 2026Intrinsic Entropy of Context Length Scaling in LLMs
- ICLR 2026Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?
- ICLR 2026Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders
- ICLR 2026Is Finer Better? The Limits of Microscaling Formats in Large Language Models
- ICLR 2026Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility
- ICLR 2026It's All Just Vectorization: einx, a Universal Notation for Tensor Operations
- ICLR 2026IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs
- ICLR 2026IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning
- ICLR 2026IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment
- ICLR 2026IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?
- ICLR 2026Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion
- ICLR 2026JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence
- ICLR 2026JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation
- ICLR 2026Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation
- ICLR 2026JointAVBench: A Benchmark for Joint Audio-Visual Reasoning Evaluation
- ICLR 2026Journey to the Centre of Cluster: Harnessing Interior Nodes for A/B Testing under Network Interference
- ICLR 2026Judo: A Juxtaposed Domain-oriented Multimodal Reasoner for Industrial Anomaly QA
- ICLR 2026Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
- ICLR 2026K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge
- ICLR 2026K²-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control
- ICLR 2026Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation
- ICLR 2026KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
- ICLR 2026KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
- ICLR 2026KeepLoRA: Continual Learning with Residual Gradient Adaptation
- ICLR 2026Know When to Abstain: Optimal Selective Classification with Likelihood Ratios
- ICLR 2026KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning
- ICLR 2026Knowledge Exchange with Confidence: Cost-Effective LLM Integration for Reliable and Efficient Visual Question Answering
- ICLR 2026Knowledge Externalization: Reversible Unlearning and Modular Retrieval in Multimodal Large Language Models
- ICLR 2026Knowledge Fusion of Large Language Models via Modular SkillPacks
- ICLR 2026Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning
- ICLR 2026KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning
- ICLR 2026KV-Cache Transform Coding for Compact Storage in LLM Inference
- ICLR 2026LABEL-FREE MITIGATION OF SPURIOUS CORRELATIONS IN VLMS USING SPARSE AUTOENCODERS
- ICLR 2026LadderSym: A Multimodal Interleaved Transformer for Music Practice Error Detection
- ICLR 2026LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
- ICLR 2026Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models
- ICLR 2026Language Confusion Gate: Language-Aware Decoding Through Model Self-Distillation
- ICLR 2026Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative
- ICLR 2026Language Models are Injective and Hence Invertible
- ICLR 2026Language-guided Open-world Video Anomaly Detection under Weak Supervision
- ICLR 2026Language-Instructed Vision Embeddings for Controllable and Generalizable Perception
- ICLR 2026LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel
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。