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 47 / 225 页
- ICLR 2026QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture
- ICLR 2026Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
- ICLR 2026QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification
- ICLR 2026Query-Guided Spatial–Temporal–Frequency Interaction for Music Audio–Visual Question Answering
- ICLR 2026QueryStream: Advancing Streaming Video Understanding with Query-Aware Pruning and Proactive Response
- ICLR 2026QUEST: A robust attention formulation using query-modulated spherical attention
- ICLR 2026QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
- ICLR 2026QuoKA: Query-Oriented KV Selection for Efficient LLM Prefill
- ICLR 2026QuRL: Low-Precision Reinforcement Learning for Efficient Reasoning
- ICLR 2026R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning
- ICLR 2026R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
- ICLR 2026RACE Attention: A Strictly Linear-Time Attention for Long-Sequence Training
- ICLR 2026RAG4DMC: Retrieval-Augmented Generation for Data-Level Modality Completion
- ICLR 2026Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
- ICLR 2026Random Anchors with Low-rank Decorrelated Learning: A Minimalist Pipeline for Class-Incremental Medical Image Classification
- ICLR 2026Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
- ICLR 2026RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty
- ICLR 2026RAR: Reversing Visual Attention Re-Sinking for Unlocking Potential in Multimodal Large Language Models
- ICLR 2026RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
- ICLR 2026RCPU: Rotation-Constrained Error Compensation for Structured Pruning of a Large Language Model
- ICLR 2026Read the Room: Video Social Reasoning with Mental-Physical Causal Chains
- ICLR 2026Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models
- ICLR 2026REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
- ICLR 2026Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment
- ICLR 2026Reasoning Boosts Opinion Alignment in LLMs
- ICLR 2026Reasoning on Time-Series for Financial Technical Analysis
- ICLR 2026Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning
- ICLR 2026Reasoning-Driven Multimodal LLM for Domain Generalization
- ICLR 2026Reassessing Layer Pruning in LLMs: New Insights and Methods
- ICLR 2026ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
- ICLR 2026ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
- ICLR 2026Reconstructing KV Caches with Cross-Layer Fusion for Enhanced Transformers
- ICLR 2026Reconstruction Alignment Improves Unified Multimodal Models
- ICLR 2026Reducing Semantic Mismatch in Brain-to-Text Decoding Through Personalized Multimodal Masking
- ICLR 2026Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks
- ICLR 2026Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping
- ICLR 2026Reformulation for Pretraining Data Augmentation
- ICLR 2026RefTool: Reference-Guided Tool Creation for Knowledge-Intensive Reasoning
- ICLR 2026RegionReasoner: Region-Grounded Multi-Round Visual Reasoning
- ICLR 2026ReIn: Conversational Error Recovery with Reasoning Inception
- ICLR 2026Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
- ICLR 2026Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data
- ICLR 2026RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization
- ICLR 2026RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning
- ICLR 2026RepSpec: Structural Re-parameterized Draft Model Training for Speculative Decoding
- ICLR 2026Repurposing Foundation Model for Generalizable Medical Time Series Classification
- ICLR 2026RESA: Bringing Back What Sparse Attention Ignores with Residual Estimation
- ICLR 2026Reshaping Reasoning in LLMs: A Theoretical Analysis of RL Training Dynamics through Pattern Selection
- ICLR 2026Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis
- ICLR 2026Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures
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。