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 1,366 篇，第 9 / 28 页
- NeurIPS 2026Efficient, Accurate and Stable Gradients for Neural ODEs
- NeurIPS 2026EgoBabyVLM: Benchmarking cross-modal learning from naturalistic egocentric video data
- NeurIPS 2026EgoStream: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision
- NeurIPS 2026EgoTac: In-the-wild Tactile Prediction from Egocentric Vision
- NeurIPS 2026Elastic Representations via Hyperbolic Geometry
- NeurIPS 2026ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
- NeurIPS 2026Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding
- NeurIPS 2026ELPAC: Endpoint-Anchored Latent Progression with Stage-Varying Multimodal Coordination
- NeurIPS 2026EM-NeSy: Expectation Maximization for Neurosymbolic Learning
- NeurIPS 2026Embedding Foundation Model Predictions in Discrete-Choice Models with Structural Guarantees
- NeurIPS 2026Emergent Biological Capabilities in a Foundation Model for Molecular Interactions
- NeurIPS 2026Empirical regularities in subjective decision-making by LLMs
- NeurIPS 2026Empowering Time Series Analysis with Large-Scale Multimodal Pretraining
- NeurIPS 2026Enabling VLA Action Self-Verification via VLM Token Probability Bucketing
- NeurIPS 2026EndoSCOP-V: A Multi-Turn Video Understanding Evaluation Framework for Multimodal Models in Endoscopy Reporting and Clinical Reasoning
- NeurIPS 2026Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following
- NeurIPS 2026Enhancing LLMs with Cognitive-Affective Personality Inference for Simulating Human Social-Psychological Behavior
- NeurIPS 2026EnvTrap: Revealing the Environment-Only Attack Surface in Embodied AI via Consequence-Blind Action Execution
- NeurIPS 2026EpiStream: Utility-Aware Temporal Abstraction for Dense-Action Streams
- NeurIPS 2026Escaping Reasoning Basins: Basin-Aware Search for Inference-Time LLM Reasoning
- NeurIPS 2026Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
- NeurIPS 2026Euler-Mamba: Learning Resolution-Invariant State Evolution on Polar Manifolds for Asymmetric Pansharpening
- NeurIPS 2026EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment
- NeurIPS 2026EVA: Evidence-seeking Visual Agent for Hallucination-Resistant Multimodal Reasoning
- NeurIPS 2026Evaluating Multimodal Narrative Understanding of Popular Hollywood Films
- NeurIPS 2026Evaluating Neural Data Tokenizers: A Framework for Assessing Learned Representations of Spiking Activity
- NeurIPS 2026Evaluating Spatiotemporal Reasoning of Vision-Language Models in Atari Gameplay
- NeurIPS 2026Even Sailors Need Calm Seas: Taming the Geometry of VLMs for Fast Adversarial Fine-Tuning
- NeurIPS 2026Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies
- NeurIPS 2026EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning
- NeurIPS 2026Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
- NeurIPS 2026EviSAM3: Evidence-Driven SAM3 for Referring Remote Sensing Image Segmentation
- NeurIPS 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
- NeurIPS 2026EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution
- NeurIPS 2026EvoGround: Self-Evolving Video Agents for Video Temporal Grounding
- NeurIPS 2026Example-Based Spatial Guidance for Training-Free Concept Erasure in Diffusion Models
- NeurIPS 2026Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs
- NeurIPS 2026Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving
- NeurIPS 2026Exploiting Textual Semantics for Robust Cross-View Object Correspondence
- NeurIPS 2026Exploring the Epipolar Consistency for Light Field Deraining
- NeurIPS 2026Exploring the Limits of Compositional Generalization in Vision-Language-Action Manipulation
- NeurIPS 2026Exposing Private Corpus Leakage in Multimodal RAG
- NeurIPS 2026Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons
- NeurIPS 2026Extraneous Cognitive Load in Large Language Models
- NeurIPS 2026Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models
- NeurIPS 2026FACETS: Cross-Granularity Vision--Language Modeling for 3D Anomaly Detection
- NeurIPS 2026Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models
- NeurIPS 2026Failure Profiling and Reachable Trajectory Selection for Reasoning Distillation
- NeurIPS 2026FairTune Market: A Fair and Trustworthy Marketplace for Fine-Tuned LLMs via Posted-Price & Proper-Scoring Mechanisms
- NeurIPS 2026Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEs
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。