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 336 篇，第 5 / 7 页

  1. ICLR 2026SketchingReality: From Freehand Scene Sketches to Photorealistic Images
  2. ICLR 2026SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Model
  3. ICLR 2026SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation
  4. ICLR 2026SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generation
  5. ICLR 2026Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
  6. ICLR 2026Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers
  7. ICLR 2026Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs
  8. ICLR 2026UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
  9. ICLR 2026ViPO: Visual Preference Optimization at Scale
  10. ICLR 2026VisualPrompter: Semantic-Aware Prompt Optimization with Visual Feedback for Text-to-Image Synthesis
  11. ICLR 2026VMDiff: Visual Mixing Diffusion for Limitless Cross-Object Synthesis
  12. ICLR 2026WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM
  13. ICLR 2026WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction
  14. ICML 2026A Progressive Evidence Localization Framework Based on Wasserstein Gradient Flows for Document Visual Question Answering
  15. ICML 2026Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis
  16. ICML 2026Agentic Model Predictive Questioning Control in Visual Design
  17. ICML 2026AutoVSR: Automatic Visual-to-Symbolic Reasoning for Symbolic Expression Generation from Circuit Schematic
  18. ICML 2026AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
  19. ICML 2026AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs
  20. ICML 2026Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation
  21. ICML 2026Beyond Unidirectional Bias: Reciprocal Perspective Calibration in Scene Graph Generation
  22. ICML 2026Boost the Identity-Preserving Embedding for Consistent Visual Generation
  23. ICML 2026Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual Reasoners
  24. ICML 2026Deep Ensemble Clustering for Visual Representation Learning
  25. ICML 2026Direct 3D-Aware Object Insertion via Decomposed Visual Proxies
  26. ICML 2026Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
  27. ICML 2026Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs
  28. ICML 2026DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation
  29. ICML 2026EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
  30. ICML 2026End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
  31. ICML 2026EntRAG: Entity-Centric Retrieval-Augmented Generation for Knowledge-based Visual Question Answering
  32. ICML 2026Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy
  33. ICML 2026From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection
  34. ICML 2026Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation
  35. ICML 2026HSGG: Training-Free Hierarchical Scene Graph Generation with Geometry-Guided Relation Reasoning
  36. ICML 2026iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework
  37. ICML 2026JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments
  38. ICML 2026LightAVSeg: Lightweight Audio-Visual Segmentation
  39. ICML 2026ModernVBERT: Towards Smaller Visual Document Retrievers
  40. ICML 2026MotiMotion: Motion-Controlled Video Generation with Visual Reasoning
  41. ICML 2026MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
  42. ICML 2026NAVIGATE: Evaluating Visual-Guided Search Decision-Making on the Open Web
  43. ICML 2026Prism-MoE: Efficient Dense-to-MoE Conversion for Visual Autoregressive Generation
  44. ICML 2026Probing Cross-modal Information Hubs in Audio-Visual LLMs
  45. ICML 2026ProtoVAR: Efficient Dataset Distillation via Prototype-Guided Visual Autoregressive Modeling
  46. ICML 2026Scaling Transformers for End-to-End Discrete Audio Tokenization
  47. ICML 2026Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
  48. ICML 2026SpikeCLR: Self-Supervised Contrastive Learning for Visual Representations with Spiking Neural Networks
  49. ICML 2026Synergistic Space-Vision Processing for Predicate Inference
  50. ICML 2026VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing

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