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 1,401 篇，第 18 / 29 页
- ICLR 2026Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
- ICLR 2026Pay Less Attention to Function Words for Free Robustness of Vision-Language Models
- ICLR 2026PCB-Bench: Benchmarking LLMs for Printed Circuit Board Placement and Routing
- ICLR 2026PCLR: Progressively Compressed LoRA for Multimodal Continual Instruction Tuning
- ICLR 2026Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation
- ICLR 2026Perception-Aware Policy Optimization for Multimodal Reasoning
- ICLR 2026Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward
- ICLR 2026PERK: Long-Context Reasoning as Parameter-Efficient Test-Time Learning
- ICLR 2026Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
- ICLR 2026Personalized Reasoning: Just-in-time Personalization and Why LLMs Fail at It
- ICLR 2026PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits
- ICLR 2026PerSpectra: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments
- ICLR 2026PETRI: Learning Unified Cell Embeddings from Unpaired Modalities via Early-Fusion Joint Reconstruction
- ICLR 2026pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models
- ICLR 2026Phantom-Data: Towards a General Subject-Consistent Video Generation Dataset
- ICLR 2026Photon: Speedup Volume Understanding with Efficient Multimodal Large Language Models
- ICLR 2026PHyCLIP: $\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning
- ICLR 2026PhysLLM: Harnessing Large Language Models for Cross-Modal Remote Physiological Sensing
- ICLR 2026Pi-CCA: Prompt-Invariant CCA Certificates for Replay-Free Continual Multimodal Learning
- ICLR 2026PICABench: How Far are We from Physical Realistic Image Editing?
- ICLR 2026Pitfalls in Evaluating Language Model Forecasters
- ICLR 2026PixelCraft: A Multi-Agent system for High-Fidelity Visual Reasoning on Structured Images
- ICLR 2026PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model
- ICLR 2026Plan then Act: Bi-level CAD Command Sequence Generation
- ICLR 2026Plan-Answer-Refine-on-Graph: Structured Planning and Self-Refinement for Large Language Model Reasoning on Knowledge Graphs
- ICLR 2026Planning with an Embodied Learnable Memory
- ICLR 2026Plug-and-Play Compositionality for Boosting Continual Learning with Foundation Models
- ICLR 2026Plug, Play, and Fortify: A Low-Cost Module for Robust Multimodal Image Understanding Models
- ICLR 2026PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs
- ICLR 2026PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives
- ICLR 2026Policy Contrastive Decoding for Robotic Foundation Models
- ICLR 2026PonderLM: Pretraining Language Models to Ponder in Continuous Space
- ICLR 2026Pose-RFT: Aligning MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning
- ICLR 2026PoSh: Using Scene Graphs to Guide LLMs-as-a-Judge for Detailed Image Descriptions
- ICLR 2026Post-hoc Probabilistic Vision-Language Models
- ICLR 2026Post-Training Quantization for Video Matting
- ICLR 2026PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs
- ICLR 2026PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models
- ICLR 2026PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
- ICLR 2026Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
- ICLR 2026Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning
- ICLR 2026Pre-training under infinite compute
- ICLR 2026Predicting LLM Reasoning Performance with Small Proxy Model
- ICLR 2026Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs
- ICLR 2026PreferThinker: Reasoning-based Personalized Image Preference Assessment
- ICLR 2026PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention
- ICLR 2026Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning
- ICLR 2026Pretraining Scaling Laws for Generative Evaluations of Language Models
- ICLR 2026Pretraining with hierarchical memories: separating long-tail and common knowledge
- ICLR 2026Prior-based Noisy Text Data Filtering: Fast and Strong Alternative For Perplexity
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。