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 8 / 16 页

  1. CVPR 2025SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling
  2. CVPR 2025Sound Bridge: Associating Egocentric and Exocentric Videos via Audio Cues
  3. CVPR 2025SoundVista: Novel-View Ambient Sound Synthesis via Visual-Acoustic Binding
  4. CVPR 2025Spectral State Space Model for Rotation-Invariant Visual Representation Learning
  5. CVPR 2025SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking
  6. CVPR 2025Stop Learning it all to Mitigate Visual Hallucination, Focus on the Hallucination Target.
  7. CVPR 2025Supervising Sound Localization by In-the-wild Egomotion
  8. CVPR 2025Synthetic Visual Genome
  9. CVPR 2025Test-Time Visual In-Context Tuning
  10. CVPR 2025Towards Open-Vocabulary Audio-Visual Event Localization
  11. CVPR 2025TSAM: Temporal SAM Augmented with Multimodal Prompts for Referring Audio-Visual Segmentation
  12. CVPR 2025Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video
  13. CVPR 2025UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection
  14. CVPR 2025Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach
  15. CVPR 2025UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing
  16. CVPR 2025VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification
  17. CVPR 2025VGGT: Visual Geometry Grounded Transformer
  18. CVPR 2025VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling
  19. CVPR 2025VISTREAM: Improving Computation Efficiency of Visual Streaming Perception via Law-of-Charge-Conservation Inspired Spiking Neural Network
  20. CVPR 2025Visual Consensus Prompting for Co-Salient Object Detection
  21. CVPR 2025Visual Prompting for One-shot Controllable Video Editing without Inversion
  22. CVPR 2025ViUniT: Visual Unit Tests for More Robust Visual Programming
  23. CVPR 2025VSNet: Focusing on the Linguistic Characteristics of Sign Language
  24. CVPR 2025World-consistent Video Diffusion with Explicit 3D Modeling
  25. CVPR 2025ZeroVO: Visual Odometry with Minimal Assumptions
  26. ICLR 2025Aligned Better, Listen Better for Audio-Visual Large Language Models
  27. ICLR 2025AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models
  28. ICLR 2025Beyond single neurons: population response geometry in digital twins of mouse visual cortex
  29. ICLR 2025ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension
  30. ICLR 2025Denoising with a Joint-Embedding Predictive Architecture
  31. ICLR 2025Endowing Visual Reprogramming with Adversarial Robustness
  32. ICLR 2025Exploring the Design Space of Visual Context Representation in Video MLLMs
  33. ICLR 2025From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities
  34. ICLR 2025KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models
  35. ICLR 2025LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
  36. ICLR 2025LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior
  37. ICLR 2025Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive Transformer
  38. ICLR 2025Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions
  39. ICLR 2025LongVILA: Scaling Long-Context Visual Language Models for Long Videos
  40. ICLR 2025MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
  41. ICLR 2025MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation
  42. ICLR 2025Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation
  43. ICLR 2025OMG: Opacity Matters in Material Modeling with Gaussian Splatting
  44. ICLR 2025PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
  45. ICLR 2025Reconstructive Visual Instruction Tuning
  46. ICLR 2025Representational Similarity via Interpretable Visual Concepts
  47. ICLR 2025Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
  48. ICLR 2025Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion
  49. ICLR 2025TopoGaussian: Inferring Internal Topology Structures from Visual Clues
  50. ICLR 2025Toward Generalizing Visual Brain Decoding to Unseen Subjects

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