视听学习论文趋势 2023–2026

音视频联合建模

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 790 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

视听学习论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202348201278158
202433192088160
202556301094190
2026693932142282

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

全部视听学习论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 789 篇，第 2 / 16 页

  1. CVPR 2026FVAR Next-Focus Prediction for Visual Autoregressive Modeling
  2. CVPR 2026Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction
  3. CVPR 2026Geometry-Guided 3D Visual Token Pruning for Video-Language Models
  4. CVPR 2026GroundVTS Visual Token Sampling in Multimodal Large Language Models for
  5. CVPR 2026Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation
  6. CVPR 2026HAVE-Bench Hierarchical Audio-Visual Evaluation from Perception to Interaction
  7. CVPR 2026HAWK Head Importance-Aware Visual Token Pruning in Multimodal Models
  8. CVPR 2026HOLO Homography-Guided Pose Estimator Network for Fine-Grained Visual Localization on
  9. CVPR 2026How Far Can We Go With Synthetic Data for Audio-Visual
  10. CVPR 2026HypeVPR Exploring Hyperbolic Space for Perspective to Equirectangular Visual Place
  11. CVPR 2026IBISAgent Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical
  12. CVPR 2026Illuminating Visual Identity in Universal Multimodal Embeddings
  13. CVPR 2026In Pursuit of Pixel Supervision for Visual Pre-training
  14. CVPR 2026InfinityHuman Towards Long-Term Audio-Driven Human Animation
  15. CVPR 2026Investigating Self-Supervised Representations for Audio-Visual Deepfake Detection
  16. CVPR 2026JUMP-Hand Learning Joint-wise Uncertainty to Gate Mixture of View Experts
  17. CVPR 2026Language Models Can Explain Visual Features via Steering
  18. CVPR 2026Learning to See Through a Babys Eyes Early Visual Diets
  19. CVPR 2026Learning to Select Visual Tools from Experience
  20. CVPR 2026LLaDA-V Large Language Diffusion Models with Visual Instruction Tuning
  21. CVPR 2026Locate-then-Sparsify Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
  22. CVPR 2026LongStream Long-Sequence Streaming Autoregressive Visual Geometry
  23. CVPR 2026Merge3D Efficient 3D Multimodal LLMs via Joint 2D-3D Token Merging
  24. CVPR 2026Modeling the Visual Ambiguity of Human Sketches
  25. CVPR 2026MoRE 3D Visual Geometry Reconstruction Meets Mixture-of-Experts
  26. CVPR 2026NeuroFlow Toward Unified Visual Encoding and Decoding from Neural Activity
  27. CVPR 2026OmniVGGT Omni-Modality Driven Visual Geometry Grounded Transformer
  28. CVPR 2026OmniZip Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language
  29. CVPR 2026One Layers Trash is Another Layers Treasure Adaptive Layer-wise Visual
  30. CVPR 2026OpenVision 2 A Family of Generative Pretrained Visual Encoders for
  31. CVPR 2026OpenVO Open-World Visual Odometry with Temporal Dynamics Awareness
  32. CVPR 2026ORD Object-Relation Decoupling for Generalized 3D Visual Grounding
  33. CVPR 2026ParallelVLM Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative
  34. CVPR 2026PAVAS Physics-Aware Video-to-Audio Synthesis
  35. CVPR 2026PECCVAI Overcoming the Brittleness of AI Image Watermarking Under Visual
  36. CVPR 2026PET-DINO Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training
  37. CVPR 2026PHANTOM Physics-Infused Video Generation via Joint Modeling of Visual and
  38. CVPR 2026Pixel2Phys Distilling Governing Laws from Visual Dynamics
  39. CVPR 2026Progressive Supernet Training for Efficient Visual Autoregressive Modeling
  40. CVPR 2026Prompt Yourself Awakening Textual Semantics in 1D Visual Tokenizers
  41. CVPR 2026Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding
  42. CVPR 2026QVGGT Post-Training Quantized Visual Geometry Grounded Transformer
  43. CVPR 2026Relational Visual Similarity
  44. CVPR 2026Rethinking Visual Rearrangement from A Diffusion Perspective
  45. CVPR 2026Retrieving Counterfactuals Improves Visual In-Context Learning
  46. CVPR 2026Revisiting Visual Corruptions in LVLMs A Shape-Texture Perspective on Model
  47. CVPR 2026RT-Splatting Joint Reflection-Transmission Modeling with Gaussian Splatting
  48. CVPR 2026RxnCaption Reformulating Reaction Diagram Parsing as Visual Prompt Guided Captioning
  49. CVPR 2026Same Attention Different Truths Put Logit-Lens over Visual Attention to
  50. CVPR 2026SEA Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question

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 查视听学习在 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-learning"}

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学习论文？
共 790 篇，按年份分别是 2023 年 158 篇、2024 年 160 篇、2025 年 190 篇、2026 年 282 篇。
NeurIPS 2026 有多少篇视听学习论文？
NeurIPS 2026 有 69 篇视听学习论文，上一届是 56 篇。
ICLR 2026 有多少篇视听学习论文？
ICLR 2026 有 39 篇视听学习论文，上一届是 30 篇。
ICML 2026 有多少篇视听学习论文？
ICML 2026 有 32 篇视听学习论文，上一届是 10 篇。
CVPR 2026 有多少篇视听学习论文？
CVPR 2026 有 142 篇视听学习论文，上一届是 94 篇。
哪个会议的视听学习论文最多？
CVPR，2023–2026 年共 402 篇。

「语音与音频」下的其他主题