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 149 篇，第 1 / 3 页

1. CVPR 2026Adaptive Capacity Autoregressive Visual Tracking
2. CVPR 2026AffordMatcher Affordance Learning in 3D Scenes from Visual Signifiers
3. CVPR 2026AnyID Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual References
4. CVPR 2026Archon A Unified Multimodal Model for Holistic Digital Human Generation
5. CVPR 2026Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner
6. CVPR 2026AudioStory Generating Long-Form Narrative Audio with Large Language Models
7. CVPR 2026AVA-Bench Atomic Visual Ability Benchmark for Vision Foundation Models
8. CVPR 2026Benchmarking Single-Factor Physical Video-to-Audio Generation
9. CVPR 2026Cinematic Audio Source Separation Using Visual Cues
10. CVPR 2026ClusterMark Towards Robust Watermarking for Autoregressive Image Generators with Visual
11. CVPR 2026Co-Me Confidence Guided Token Merging for Visual Geometric Transformers
12. CVPR 2026CodePercept Code-Grounded Visual STEM Perception for MLLMs
13. CVPR 2026Cross-Modal Guided Visual Synthesis for Data-Efficient Multimodal Depression Recognition
14. CVPR 2026Cubic Discrete Diffusion Discrete Visual Generation on High-Dimensional Representation Tokens
15. CVPR 2026DialogueVPR Towards Conversational Visual Place Recognition
16. CVPR 2026DiverseGRPO Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO
17. CVPR 2026DocSeeker Structured Visual Reasoning with Evidence Grounding for Long Document
18. CVPR 2026DPAR Dynamic Patchification for Efficient Autoregressive Visual Generation
19. CVPR 2026Drift-Resilient Temporal Priors for Visual Tracking
20. CVPR 2026Dual-Granularity Memory for Efficient Video Generation
21. CVPR 2026DuetSVG Unified Multimodal SVG Generation with Internal Visual Guidance
22. CVPR 2026Echoes Over Time Unlocking Length Generalization in Video-to-Audio Generation Models
23. CVPR 2026EffectMaker Unifying Reasoning and Generation for Customized Visual Effect Creation
24. CVPR 2026EgoAVU Egocentric Audio-Visual Understanding
25. CVPR 2026Emergent Outlier View Rejection in Visual Geometry Grounded Transformers
26. CVPR 2026Enhancing the Security of Visual Speaker Authentication Based on Dynamic
27. CVPR 2026EVATok Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
28. CVPR 2026Event-based Visual Deformation Measurement
29. CVPR 2026Fast Spatial Tracking with Visual Geometry Transformer
30. CVPR 2026FAVE A Structured Benchmark for Fine-Grained Audio-Visual Temporal Evaluation in
31. CVPR 2026First Logit Boosting Visual Grounding Method to Mitigate Object Hallucination
32. CVPR 2026FlashMotion Few-Step Controllable Video Generation with Trajectory Guidance
33. CVPR 2026FlowFixer Towards Detail-Preserving Subject-Driven Generation
34. CVPR 2026FoleyDirector Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts
35. CVPR 2026FontCrafter High-Fidelity Element-Driven Artistic Font Creation with Visual In-Context Generation
36. CVPR 2026ForeAct Steering Your VLA with Efficient Visual Foresight Planning
37. CVPR 2026Gloria Consistent Character Video Generation via Content Anchors
38. CVPR 2026GroundingME Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional
39. CVPR 2026Harmony Harmonizing Audio and Video Generation through Cross-Task Synergy
40. CVPR 2026HAVE-Bench Hierarchical Audio-Visual Evaluation from Perception to Interaction
41. CVPR 2026Hear What Matters Text-conditioned Selective Video-to-Audio Generation
42. CVPR 2026Hidden Dangers of Compositional Generation Diagnosing Semantic Safety Failures in
43. CVPR 2026Hierarchical Codec Diffusion for Video-to-Speech Generation
44. CVPR 2026HOLO Homography-Guided Pose Estimator Network for Fine-Grained Visual Localization on
45. CVPR 2026How Far Can We Go With Synthetic Data for Audio-Visual
46. CVPR 2026HypeVPR Exploring Hyperbolic Space for Perspective to Equirectangular Visual Place
47. CVPR 2026Illuminating Visual Identity in Universal Multimodal Embeddings
48. CVPR 2026InfiniBench Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene
49. CVPR 2026Investigating Self-Supervised Representations for Audio-Visual Deepfake Detection
50. CVPR 2026LacTokGen Latent Consistency Tokenizer for 1024-pixel Image Generation by 256

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。