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 1,051 篇，第 15 / 22 页
- ICML 2026Reflex: Real-Time Vision-Language-Action Control through Streaming Inference
- ICML 2026Regression Language Models for Code
- ICML 2026Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis
- ICML 2026Remove the Ambiguity: Few-shot Multimodal Anomaly Detection Using Crossmodal Feature Replacers
- ICML 2026RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress
- ICML 2026Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models
- ICML 2026Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
- ICML 2026Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models
- ICML 2026Rethinking Calibration for Early-Exit Neural Networks
- ICML 2026Rethinking Federated Prompt Learning for Medical Images: From Textual Tuning to Visual Manifold Anchoring
- ICML 2026Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate
- ICML 2026Rethinking Genomic Modeling Through Optical Character Recognition
- ICML 2026Rethinking Instruction Drift as a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning
- ICML 2026Rethinking Low-Confidence Pseudo Labels: Influence-Aware Semi-Supervised Fine-Tuning for Hyperspectral Change Detection
- ICML 2026Rethinking Multimodal Time-Series Forecasting Evaluation
- ICML 2026Rethinking Pretraining Data Detection for LLMs: From Local to Global
- ICML 2026Rethinking Video Generation Model for the Embodied World
- ICML 2026REVIS: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
- ICML 2026Revisiting the Role of Pretrained Weights in Model Merging: On Near-Optimality within the Core Subspace
- ICML 2026Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval
- ICML 2026REViT: Roto-reflection Equivariant Convolutional Vision Transformer
- ICML 2026ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
- ICML 2026Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility
- ICML 2026RLSF-V: Mitigating Hallucinations in MLLMs via Fuzzy Semantic Self-Feedback
- ICML 2026ROAMM: A Benchmark Dataset for Multimodal Human Attention Decoding and EEG-to-Text Modeling During Naturalistic Reading
- ICML 2026RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
- ICML 2026RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
- ICML 2026RoboOmni: Actions Are Just Another Modality for Vision-Language Models
- ICML 2026RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- ICML 2026Robust Cross-Modal Retrieval via Generative Semantic Refinement and Exclusion-Guided Adaptation
- ICML 2026Robust Multi-View Fusion via Prototype-Anchored Unbalanced Optimal Transport
- ICML 2026Robust Vision-Language Models via Manifold-Adversarial Adapters
- ICML 2026Robustifying Vision-Language Models via Test-Time Prompt Adaptation
- ICML 2026Rotary Position Encodings for Graphs
- ICML 2026RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning
- ICML 2026RVAS: Referring Video Active Exploration and Segmentation
- ICML 2026S2M-Net: Spectral-Spatial Mixing with Morphology-Aware Adaptive Loss for Medical Image Segmentation
- ICML 2026Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
- ICML 2026SAGE: A Dataflow-Native Framework for Modular, Controllable, and Transparent LLM-Augmented Reasoning
- ICML 2026SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs
- ICML 2026SALSA-V: Shortcut-Augmented Long-form Synchronized Audio from Videos
- ICML 2026SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning
- ICML 2026Sampling and Identity-Testing Without Approximate Tensorization of Entropy
- ICML 2026SARSteer: Safeguarding Large Audio Language Models via Safe-Ablated Refusal Steering
- ICML 2026SAW-Bench: Learning Situated Awareness in the Real World
- ICML 2026Scalable Kronecker-Factored Fisher Approximation for Neural Network Parameter Sensitivity
- ICML 2026Scalable Medical Multimodal Fusion via Symmetric Consistency Modeling
- ICML 2026Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
- ICML 2026SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models
- ICML 2026ScaleErasure: Inference-Time Minimal Intervention for Precise Concept Erasure in Next-Scale Autoregressive Image Generation
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。