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 38 / 67 页
- NeurIPS 2025Linguini: A benchmark for language-agnostic linguistic reasoning
- NeurIPS 2025LISAt: Language-Instructed Segmentation Assistant for Satellite Imagery
- NeurIPS 2025LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
- NeurIPS 2025LiveStar: Live Streaming Assistant for Real-World Online Video Understanding
- NeurIPS 2025LLM Query Scheduling with Prefix Reuse and Latency Constraints
- NeurIPS 2025LLMs Encode Harmfulness and Refusal Separately
- NeurIPS 2025LMFusion: Adapting Pretrained Language Models for Multimodal Generation
- NeurIPS 2025Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding
- NeurIPS 2025Logic.py: Bridging the Gap between LLMs and Constraint Solvers
- NeurIPS 2025LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data
- NeurIPS 2025LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language Models
- NeurIPS 2025LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation
- NeurIPS 2025Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
- NeurIPS 2025LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
- NeurIPS 2025LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?
- NeurIPS 2025Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation
- NeurIPS 2025Lookahead Routing for Large Language Models
- NeurIPS 2025LoRO: Real-Time on-Device Secure Inference for LLMs via TEE-Based Low Rank Obfuscation
- NeurIPS 2025Lost in Transmission: When and Why LLMs Fail to Reason Globally
- NeurIPS 2025LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning
- NeurIPS 2025LVLM-Driven Attribute-Aware Modeling for Visible-Infrared Person Re-Identification
- NeurIPS 2025Lyapunov-Stable Adaptive Control for Multimodal Concept Drift
- NeurIPS 2025Machine Unlearning via Task Simplex Arithmetic
- NeurIPS 2025MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series
- NeurIPS 2025Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation
- NeurIPS 2025Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection
- NeurIPS 2025MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
- NeurIPS 2025MAPLE: Multi-scale Attribute-enhanced Prompt Learning for Few-shot Whole Slide Image Classification
- NeurIPS 2025Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks
- NeurIPS 2025Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
- NeurIPS 2025Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences
- NeurIPS 2025MathArena: Evaluating LLMs on Uncontaminated Math Competitions
- NeurIPS 2025Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
- NeurIPS 2025Mechanism Design for LLM Fine-tuning with Multiple Reward Models
- NeurIPS 2025MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives
- NeurIPS 2025MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants
- NeurIPS 2025MedSG-Bench: A Benchmark for Medical Image Sequences Grounding
- NeurIPS 2025MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation
- NeurIPS 2025Mellow: a small audio language model for reasoning
- NeurIPS 2025MemEIC: A Step Toward Continual and Compositional Knowledge Editing
- NeurIPS 2025MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs
- NeurIPS 2025MergeBench: A Benchmark for Merging Domain-Specialized LLMs
- NeurIPS 2025Meta CLIP 2: A Worldwide Scaling Recipe
- NeurIPS 2025MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
- NeurIPS 2025MIDAS: Misalignment-based Data Augmentation Strategy for Imbalanced Multimodal Learning
- NeurIPS 2025MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models
- NeurIPS 2025Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
- NeurIPS 2025MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
- NeurIPS 2025MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?
- NeurIPS 2025MindJourney: Test-Time Scaling with World Models for Spatial 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。