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 11,207 篇，第 134 / 225 页
- ICLR 2025STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
- ICLR 2025Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo
- ICLR 2025Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs
- ICLR 2025Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
- ICLR 2025Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
- ICLR 2025Streamlining Redundant Layers to Compress Large Language Models
- ICLR 2025StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
- ICLR 2025SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
- ICLR 2025SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding
- ICLR 2025SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding
- ICLR 2025SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression
- ICLR 2025SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?
- ICLR 2025SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
- ICLR 2025Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning
- ICLR 2025SysBench: Can LLMs Follow System Message?
- ICLR 2025SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems
- ICLR 2025System 1.x: Learning to Balance Fast and Slow Planning with Language Models
- ICLR 2025TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
- ICLR 2025Tamper-Resistant Safeguards for Open-Weight LLMs
- ICLR 2025TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types
- ICLR 2025TAU-106K: A New Dataset for Comprehensive Understanding of Traffic Accident
- ICLR 2025Teaching Human Behavior Improves Content Understanding Abilities Of VLMs
- ICLR 2025Teaching LLMs How to Learn with Contextual Fine-Tuning
- ICLR 2025TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction
- ICLR 2025TeaserGen: Generating Teasers for Long Documentaries
- ICLR 2025Tell me about yourself: LLMs are aware of their learned behaviors
- ICLR 2025TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
- ICLR 2025Temporal Reasoning Transfer from Text to Video
- ICLR 2025TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data
- ICLR 2025Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning
- ICLR 2025Test-time Adaptation for Image Compression with Distribution Regularization
- ICLR 2025Text4Seg: Reimagining Image Segmentation as Text Generation
- ICLR 2025The 3D-PC: a benchmark for visual perspective taking in humans and machines
- ICLR 2025The AdEMAMix Optimizer: Better, Faster, Older
- ICLR 2025The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation
- ICLR 2025The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs
- ICLR 2025The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model
- ICLR 2025The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities
- ICLR 2025The Unreasonable Ineffectiveness of the Deeper Layers
- ICLR 2025Theory, Analysis, and Best Practices for Sigmoid Self-Attention
- ICLR 2025ThinK: Thinner Key Cache by Query-Driven Pruning
- ICLR 2025TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
- ICLR 2025TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models
- ICLR 2025Tight Clusters Make Specialized Experts
- ICLR 2025Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
- ICLR 2025Time-to-Event Pretraining for 3D Medical Imaging
- ICLR 2025TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
- ICLR 2025TIPS: Text-Image Pretraining with Spatial awareness
- ICLR 2025TLDR: Token-Level Detective Reward Model for Large Vision Language Models
- ICLR 2025To Code or Not To Code? Exploring Impact of Code in Pre-training
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。