视听生成论文趋势 2023–2026

主要结论

• 视听生成论文从 2023 年的 92 篇增长到 2026 年的 336 篇，三年间扩大到约 3.7 倍。
• CVPR 是发视听生成论文最多的会议，2023–2026 年共 383 篇，占四个会议总量的 49%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 6 篇增至 2026 年的 79 篇。
• 在「多模态生成」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的叙事生成是 15 倍，视听生成是 3.7 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 2026Binding Visual Features Point by Point
• ICML 2026AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs
• ICLR 2026AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
• CVPR 2026Benchmarking Single-Factor Physical Video-to-Audio Generation
• NeurIPS 2025$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
• ICML 2025Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities
• ICLR 2025AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models
• CVPR 2025Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding
• NeurIPS 2024Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming
• ICML 2024CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process
• ICLR 2024Can Transformers Capture Spatial Relations between Objects?
• CVPR 2024EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning
• NeurIPS 20234D Panoptic Scene Graph Generation
• ICML 2023A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition
• ICLR 2023Learning to reason over visual objects
• CVPR 2023Autoregressive Visual Tracking
• NeurIPS 2026From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation
• ICML 2026Deep Ensemble Clustering for Visual Representation Learning
• ICLR 2026AQuA: Toward Strategic Response Generation for Ambiguous Visual Questions
• CVPR 2026Co-Me Confidence Guided Token Merging for Visual Geometric Transformers

全部视听生成论文

共 131 篇，第 2 / 3 页

51. ICLR 2026Shift-and-Sum Quantization for Visual Autoregressive Models
52. ICLR 2026SketchingReality: From Freehand Scene Sketches to Photorealistic Images
53. ICLR 2026SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Model
54. ICLR 2026SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation
55. ICLR 2026SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generation
56. ICLR 2026Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
57. ICLR 2026Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers
58. ICLR 2026Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs
59. ICLR 2026UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
60. ICLR 2026ViPO: Visual Preference Optimization at Scale
61. ICLR 2026VisualPrompter: Semantic-Aware Prompt Optimization with Visual Feedback for Text-to-Image Synthesis
62. ICLR 2026VMDiff: Visual Mixing Diffusion for Limitless Cross-Object Synthesis
63. ICLR 2026WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM
64. ICLR 2026WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction
65. ICLR 2025Aligned Better, Listen Better for Audio-Visual Large Language Models
66. ICLR 2025Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception
67. ICLR 2025AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models
68. ICLR 2025Beyond single neurons: population response geometry in digital twins of mouse visual cortex
69. ICLR 2025BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities
70. ICLR 2025ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension
71. ICLR 2025CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation
72. ICLR 2025DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation
73. ICLR 2025DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation
74. ICLR 2025ECHOPulse: ECG Controlled Echocardio-gram Video Generation
75. ICLR 2025EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face Generation
76. ICLR 2025Exploring the Design Space of Visual Context Representation in Video MLLMs
77. ICLR 2025GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEs
78. ICLR 2025GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation
79. ICLR 2025HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
80. ICLR 2025Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation
81. ICLR 2025Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On
82. ICLR 2025LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
83. ICLR 2025LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior
84. ICLR 2025Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection
85. ICLR 2025Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation
86. ICLR 2025MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation
87. ICLR 2025MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation
88. ICLR 2025MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences
89. ICLR 2025Personalized Visual Instruction Tuning
90. ICLR 2025PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions
91. ICLR 2025Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
92. ICLR 2025StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces
93. ICLR 2025TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation
94. ICLR 2025Toward Generalizing Visual Brain Decoding to Unseen Subjects
95. ICLR 2025Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment
96. ICLR 2025ViSAGe: Video-to-Spatial Audio Generation
97. ICLR 2024Adapting to Distribution Shift by Visual Domain Prompt Generation
98. ICLR 2024Adaptive Self-training Framework for Fine-grained Scene Graph Generation
99. ICLR 2024AnyText: Multilingual Visual Text Generation and Editing
100. ICLR 2024AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation

常见问题

2023–2026 年四大会议一共有多少篇视听生成论文？

共 780 篇，按年份分别是 2023 年 92 篇、2024 年 131 篇、2025 年 221 篇、2026 年 336 篇。

NeurIPS 2026 有多少篇视听生成论文？

NeurIPS 2026 有 84 篇视听生成论文，上一届是 57 篇。

ICLR 2026 有多少篇视听生成论文？

ICLR 2026 有 64 篇视听生成论文，上一届是 32 篇。

ICML 2026 有多少篇视听生成论文？

ICML 2026 有 39 篇视听生成论文，上一届是 19 篇。

CVPR 2026 有多少篇视听生成论文？

CVPR 2026 有 149 篇视听生成论文，上一届是 113 篇。

哪个会议的视听生成论文最多？

CVPR，2023–2026 年共 383 篇。