多模态大模型论文趋势 2023–2026

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。

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 1,074 篇，第 1 / 22 页

1. NeurIPS 2025$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
2. NeurIPS 2025$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection
3. NeurIPS 20253D Visual Illusion Depth Estimation
4. NeurIPS 20253D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks
5. NeurIPS 20253DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
6. NeurIPS 20253EED: Ground Everything Everywhere in 3D
7. NeurIPS 20254D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration
8. NeurIPS 20254DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
9. NeurIPS 20254KAgent: Agentic Any Image to 4K Super-Resolution
10. NeurIPS 2025A Circular Argument: Does RoPE need to be Equivariant for Vision?
11. NeurIPS 2025A compressive-expressive communication framework for compositional representations
12. NeurIPS 2025A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
13. NeurIPS 2025A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
14. NeurIPS 2025A Minimalistic Unified Framework for Incremental Learning across Image Restoration Tasks
15. NeurIPS 2025A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detection
16. NeurIPS 2025A Multimodal BiMamba Network with Test-Time Adaptation for Emotion Recognition Based on Physiological Signals
17. NeurIPS 2025A Standardized Benchmark for Multilabel Antimicrobial Peptide Classification
18. NeurIPS 2025A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
19. NeurIPS 2025A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity
20. NeurIPS 2025A unified framework for establishing the universal approximation of transformer-type architectures
21. NeurIPS 2025A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis
22. NeurIPS 2025A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking
23. NeurIPS 2025A$^3$E: Towards Compositional Model Editing
24. NeurIPS 2025A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding
25. NeurIPS 2025AC-LoRA: (Almost) Training-Free Access Control Aware Multi-Modal LLMs
26. NeurIPS 2025Accelerating Diffusion LLMs via Adaptive Parallel Decoding
27. NeurIPS 2025Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings
28. NeurIPS 2025ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking
29. NeurIPS 2025Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models
30. NeurIPS 2025Activated LoRA: Fine-tuned LLMs for Intrinsics
31. NeurIPS 2025Active Test-time Vision-Language Navigation
32. NeurIPS 2025ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning
33. NeurIPS 2025AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining
34. NeurIPS 2025Adaptive Gradient Masking for Balancing ID and MLLM-based Representations in Recommendation
35. NeurIPS 2025Adaptive Re-calibration Learning for Balanced Multimodal Intention Recognition
36. NeurIPS 2025AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
37. NeurIPS 2025AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding
38. NeurIPS 2025ADMN: A Layer-Wise Adaptive Multimodal Network for Dynamic Input Noise and Compute Resources
39. NeurIPS 2025Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning
40. NeurIPS 2025AdvEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents
41. NeurIPS 2025Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
42. NeurIPS 2025AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models
43. NeurIPS 2025AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark
44. NeurIPS 2025Aha! - Predicting What Matters Next: Online Highlight Detection Without Looking Ahead
45. NeurIPS 2025AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs
46. NeurIPS 2025AI Testing Should Account for Sophisticated Strategic Behaviour
47. NeurIPS 2025AION-1: Omnimodal Foundation Model for Astronomical Sciences
48. NeurIPS 2025ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering
49. NeurIPS 2025Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment
50. NeurIPS 2025AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

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。