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 190 篇，第 4 / 4 页

  1. NeurIPS 2025Learning to cluster neuronal function
  2. NeurIPS 2025Learning to Instruct for Visual Instruction Tuning
  3. NeurIPS 2025Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding
  4. NeurIPS 2025LoRATv2: Enabling Low-Cost Temporal Modeling in One-Stream Trackers
  5. NeurIPS 2025LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
  6. NeurIPS 2025MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks
  7. NeurIPS 2025MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs
  8. NeurIPS 2025Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors
  9. NeurIPS 2025MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence
  10. NeurIPS 2025On the rankability of visual embeddings
  11. NeurIPS 2025Perception Encoder: The best visual embeddings are not at the output of the network
  12. NeurIPS 2025Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection
  13. NeurIPS 2025PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling
  14. NeurIPS 2025Quantum Visual Fields with Neural Amplitude Encoding
  15. NeurIPS 2025Rethinking Joint Maximum Mean Discrepancy for Visual Domain Adaptation
  16. NeurIPS 2025SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing
  17. NeurIPS 2025SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs
  18. NeurIPS 2025Seg-VAR:Image Segmentation with Visual Autoregressive Modeling
  19. NeurIPS 2025Self-supervised Blending Structural Context of Visual Molecules for Robust Drug Interaction Prediction
  20. NeurIPS 2025Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
  21. NeurIPS 2025Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
  22. NeurIPS 2025STSBench: A Large-Scale Dataset for Modeling Neuronal Activity in the Dorsal Stream of Primate Visual Cortex
  23. NeurIPS 2025The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
  24. NeurIPS 2025Time-Evolving Dynamical System for Learning Latent Representations of Mouse Visual Neural Activity
  25. NeurIPS 2025Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task
  26. NeurIPS 2025Towards A Translative Model of Sperm Whale Vocalization
  27. NeurIPS 2025Towards Visualization-of-Thought Jailbreak Attack against Large Visual Language Models
  28. NeurIPS 2025Transformer brain encoders explain human high-level visual responses
  29. NeurIPS 2025TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
  30. NeurIPS 2025UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface
  31. NeurIPS 2025un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
  32. NeurIPS 2025Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations
  33. NeurIPS 2025Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks
  34. NeurIPS 2025Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations
  35. NeurIPS 2025Visual Instruction Bottleneck Tuning
  36. NeurIPS 2025Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting
  37. NeurIPS 2025Visual Sync: Multi‑Camera Synchronization via Cross‑View Object Motion
  38. NeurIPS 2025VisualLens: Personalization through Task-Agnostic Visual History
  39. NeurIPS 2025Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM
  40. NeurIPS 2025Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering

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