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 336 篇，第 2 / 7 页

51. CVPR 2026Language Models Can Explain Visual Features via Steering
52. CVPR 2026LazyVAR Accelerating Visual Autoregressive Models via Scale-wise Token Pruning and
53. CVPR 2026Learning to See Through a Babys Eyes Early Visual Diets
54. CVPR 2026Learning to Select Visual Tools from Experience
55. CVPR 2026Learning What to Trust Bayesian Prior-Guided Optimization for Visual Generation
56. CVPR 2026LiveGesture Streamable Co-Speech Gesture Generation Model
57. CVPR 2026LLaDA-V Large Language Diffusion Models with Visual Instruction Tuning
58. CVPR 2026LottieGPT Tokenizing Vector Animation for Autoregressive Generation
59. CVPR 2026Machine Mental Imagery Empower Multimodal Reasoning with Latent Visual Tokens
60. CVPR 2026MacTok Robust Continuous Tokenization for Image Generation
61. CVPR 2026MagicFuse Single Image Fusion for Visual and Semantic Reinforcement
62. CVPR 2026Markovian Scale Prediction A New Era of Visual Autoregressive Generation
63. CVPR 2026Mirai Autoregressive Visual Generation Needs Foresight
64. CVPR 2026MoRE 3D Visual Geometry Reconstruction Meets Mixture-of-Experts
65. CVPR 2026MR-RAG Multimodal Relevance-Aware Retrieval-Augmented Generation for Medical Visual Question Answering
66. CVPR 2026Narrative Weaver Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning
67. CVPR 2026Omni-Attribute Open-vocabulary Attribute Encoder for Visual Concept Personalization
68. CVPR 2026OmniLottie Generating Vector Animations via Parameterized Lottie Tokens
69. CVPR 2026OmniSonic Towards Universal and Holistic Audio Generation from Video and
70. CVPR 2026OmniZip Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language
71. CVPR 2026One Algorithm to Align Them All
72. CVPR 2026P-Flow Prompting Visual Effects Generation
73. CVPR 2026Pantheon360 Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusion
74. CVPR 2026PC-Talk Precise Facial Animation Control for Audio-Driven Talking Face Generation
75. CVPR 2026PerpetualWonder Long-horizon Action-conditioned 4D Scene Generation
76. CVPR 2026PET-DINO Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training
77. CVPR 2026PHANTOM Physics-Infused Video Generation via Joint Modeling of Visual and
78. CVPR 2026PhysGen Physically Grounded 3D Shape Generation for Industrial Design
79. CVPR 2026Pixel2Phys Distilling Governing Laws from Visual Dynamics
80. CVPR 2026PixelRush Ultra-Fast Training-Free High-Resolution Image Generation via One-step Diffusion
81. CVPR 2026Plenoptic Video Generation
82. CVPR 2026POCA Pareto-Optimal Curriculum Alignment for Visual Text Generation
83. CVPR 2026POINTS-Long Adaptive Dual-Mode Visual Reasoning in MLLMs
84. CVPR 2026Predictive Regularization Against Visual Representation Degradation in Multimodal Large Language
85. CVPR 2026Progressive Supernet Training for Efficient Visual Autoregressive Modeling
86. CVPR 2026Prompt Yourself Awakening Textual Semantics in 1D Visual Tokenizers
87. CVPR 2026QVGGT Post-Training Quantized Visual Geometry Grounded Transformer
88. CVPR 2026ReAG Reasoning-Augmented Generation for Knowledge-based Visual Question Answering
89. CVPR 2026ReaGEN Adaptive Generation of Structured Chains-of-Thought for Efficient Multimodal Reasoning
90. CVPR 2026RebRL Reinforcing Discrete Visual Diffusion Models with Rebalanced Timestep Credits
91. CVPR 2026Relational Visual Similarity
92. CVPR 2026Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation
93. CVPR 2026Rethinking UMM Visual Generation Masked Modeling for Efficient Image-Only Pre-training
94. CVPR 2026Rethinking Visual Rearrangement from A Diffusion Perspective
95. CVPR 2026RobustVisRAG Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations
96. CVPR 2026RxnCaption Reformulating Reaction Diagram Parsing as Visual Prompt Guided Captioning
97. CVPR 2026Same Attention Different Truths Put Logit-Lens over Visual Attention to
98. CVPR 2026SEA Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question
99. CVPR 2026Seeing is Improving Visual Feedback for Iterative Text Layout Refinement
100. CVPR 2026Seeing What Matters Visual Preference Policy Optimization for Visual Generation

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。