视听生成论文趋势 2023–2026

联合生成

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 780 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

视听生成论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023151066192
202427251960131
2025573219113221
2026846439149336

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

全部视听生成论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 221 篇，第 4 / 5 页

  1. ICML 2025OmniAudio: Generating Spatial Audio from 360-Degree Video
  2. ICML 2025Probing Visual Language Priors in VLMs
  3. ICML 2025SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation
  4. ICML 2025Sounding that Object: Interactive Object-Aware Image to Audio Generation
  5. ICML 2025TabNAT: A Continuous-Discrete Joint Generative Framework for Tabular Data
  6. ICML 2025Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
  7. ICML 2025The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering
  8. ICML 2025Token Coordinated Prompt Attention is Needed for Visual Prompting
  9. ICML 2025Understanding Complexity in VideoQA via Visual Program Generation
  10. ICML 2025Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision
  11. ICML 2025video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model
  12. ICML 2025Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models
  13. ICML 2025Visual Generation Without Guidance
  14. ICML 2025ZipAR: Parallel Autoregressive Image Generation through Spatial Locality
  15. NeurIPS 2025🎧MOSPA: Human Motion Generation Driven by Spatial Audio
  16. NeurIPS 2025$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
  17. NeurIPS 2025Aligning What Matters: Masked Latent Adaptation for Text-to-Audio-Video Generation
  18. NeurIPS 2025ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation
  19. NeurIPS 2025Audio Super-Resolution with Latent Bridge Models
  20. NeurIPS 2025Audio-Sync Video Generation with Multi-Stream Temporal Control
  21. NeurIPS 2025AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding
  22. NeurIPS 2025BNMusic: Blending Environmental Noises into Personalized Music
  23. NeurIPS 2025Bridging the gap to real-world language-grounded visual concept learning
  24. NeurIPS 2025CoFFT: Chain of Foresight-Focus Thought for Visual Language Models
  25. NeurIPS 2025DAVE: Diagnostic benchmark for Audio Visual Evaluation
  26. NeurIPS 2025Differentiable Hierarchical Visual Tokenization
  27. NeurIPS 2025DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images
  28. NeurIPS 2025Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention
  29. NeurIPS 2025FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction
  30. NeurIPS 2025FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance
  31. NeurIPS 2025Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning
  32. NeurIPS 2025Imagine360: Immersive 360 Video Generation from Perspective Anchor
  33. NeurIPS 2025InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation
  34. NeurIPS 2025Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
  35. NeurIPS 2025Joint Relational Database Generation via Graph-Conditional Diffusion Models
  36. NeurIPS 2025Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
  37. NeurIPS 2025Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials
  38. NeurIPS 2025MagCache: Fast Video Generation with Magnitude-Aware Cache
  39. NeurIPS 2025MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation
  40. NeurIPS 2025Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression
  41. NeurIPS 2025Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation
  42. NeurIPS 2025Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
  43. NeurIPS 2025OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data
  44. NeurIPS 2025OmniGen-AR: AutoRegressive Any-to-Image Generation
  45. NeurIPS 2025OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
  46. NeurIPS 2025OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers
  47. NeurIPS 2025OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking
  48. NeurIPS 2025On the rankability of visual embeddings
  49. NeurIPS 2025OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation
  50. NeurIPS 2025PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models

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 查视听生成在 CVPR 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": "audio-visual-generation"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「多模态生成」下的其他主题