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 281 篇，第 5 / 6 页

  1. ICML 2026OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention
  2. ICML 2026PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs
  3. ICML 2026PRIM：Cooperative Dynamic Token Compression for Efficient Large Multimodal Models
  4. ICML 2026Probing Cross-modal Information Hubs in Audio-Visual LLMs
  5. ICML 2026Rethinking Attention in Spiking Transformers: Overcoming Density Bias with Set Similarity
  6. ICML 2026Return-Critic: Bridging Goal Discrepancy for Efficient Visual Reinforcement Learning
  7. ICML 2026SpaceVista: All-Scale Visual Spatial Reasoning from mm to km
  8. ICML 2026Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
  9. ICML 2026Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation
  10. ICML 2026TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learning
  11. ICML 2026TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
  12. ICML 2026video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
  13. NeurIPS 2026A Quantitative Visual Taxonomy of Worldwide Writing Systems
  14. NeurIPS 2026A Training-Free Video Moment Retrieval Framework via Selection from Multiple Visual Prompts
  15. NeurIPS 2026AdaCodec: A Predictive Visual Code for Video MLLMs
  16. NeurIPS 2026Asymmetric Hierarchical Anchoring for Robust Audio–Visual Cross-Modal Generalization
  17. NeurIPS 2026AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression
  18. NeurIPS 2026Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency
  19. NeurIPS 2026Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings
  20. NeurIPS 2026Binding Visual Features Point by Point
  21. NeurIPS 2026CCDiff: Inverse Canonical Correlation Analysis for Discovering Visual Differences in Natural Language
  22. NeurIPS 2026Do Diffusion Models Learn to Generalize Basic Visual Skills?
  23. NeurIPS 2026Do Joint Audio-Video Generation Models Understand Physics?
  24. NeurIPS 2026Do Pathology Foundation Models Encode Disease Progression? A Pseudotime Analysis of Visual Representations
  25. NeurIPS 2026Foveal-Mamba: Inside-Out Ring Scanning with Recurrent Offset Prediction for Visual State Space Models
  26. NeurIPS 2026From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation
  27. NeurIPS 2026GATE-AD: Graph Attention Network Encoding for Few-Shot Industrial Visual Anomaly Detection
  28. NeurIPS 2026Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
  29. NeurIPS 2026HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling
  30. NeurIPS 2026Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
  31. NeurIPS 2026IDEA: Unwrapping Visual Black-box Models by Interaction Decomposition
  32. NeurIPS 2026Internalize External Competence for Visual Instruction Editing
  33. NeurIPS 2026Language-Conditioned World Modeling for Visual Navigation
  34. NeurIPS 2026LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
  35. NeurIPS 2026Learning a Maximum Entropy Model for Visual Textures using Diffusion
  36. NeurIPS 2026Learning a Task-Adaptive Low-Dimensional Semantic Space for Improved Visual Classification
  37. NeurIPS 2026Learning Task-Centric World Models from Visual Foundations
  38. NeurIPS 2026Learning to See Through Language: An Exploration of Language Modeling's Effect on Visual Representations
  39. NeurIPS 2026Learning Visual Feature-Based World Models via Residual Latent Action
  40. NeurIPS 2026Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling
  41. NeurIPS 2026Learning When Visual Context Matters for Mouse Behavior Analysis
  42. NeurIPS 2026LiteNav: Lightweight Map-free Outdoor Visual Navigation
  43. NeurIPS 2026Localizing Concepts in Visual Autoregressive Models
  44. NeurIPS 2026MAEB: Massive Audio Embedding Benchmark
  45. NeurIPS 2026Masked Visual Actions for Unified World Modeling
  46. NeurIPS 2026Native Audio-Visual Alignment for Generation
  47. NeurIPS 2026Not Another Text Benchmark: Putting the “Visual" Back in Visual Question Answering for Large Video Models
  48. NeurIPS 2026OmniSE: Support-Faithful Optimization for Evidence-Centric Audio-Video Reasoning
  49. NeurIPS 2026Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
  50. NeurIPS 2026PanoWorld: Geometry-Consistent Panoramic Video World Modeling

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