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
- 视听学习论文从 2023 年的 158 篇增长到 2026 年的 282 篇，三年间扩大到约 1.8 倍。
- CVPR 是发视听学习论文最多的会议，2023–2026 年共 402 篇，占四个会议总量的 51%。
- 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 19 篇。
- 在「语音与音频」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的音频生成是 4.3 倍，视听学习是 1.8 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 48 | 20 | 12 | 78 | 158 |
| 2024 | 33 | 19 | 20 | 88 | 160 |
| 2025 | 56 | 30 | 10 | 94 | 190 |
| 2026 | 69 | 39 | 32 | 142 | 282 |
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
- NeurIPS 2026A Training-Free Video Moment Retrieval Framework via Selection from Multiple Visual Prompts
- ICML 2026AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs
- ICLR 2026AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
- CVPR 2026AVFakeBench A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMs
- NeurIPS 2025$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
- ICML 2025Token Coordinated Prompt Attention is Needed for Visual Prompting
- ICLR 2025AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models
- CVPR 2025A Distractor-Aware Memory for Visual Object Tracking with SAM2
- NeurIPS 2024Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex.
- ICML 2024EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
- ICLR 2024Can Transformers Capture Spatial Relations between Objects?
- CVPR 2024DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields
- NeurIPS 2023Are Vision Transformers More Data Hungry Than Newborn Visual Systems?
- ICML 2023A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition
- ICLR 2023A Control-Centric Benchmark for Video Prediction
- CVPR 2023An Empirical Study of End-to-End Video-Language Transformers With Masked Visual Modeling
- NeurIPS 2026AdaCodec: A Predictive Visual Code for Video MLLMs
- ICML 2026EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
- ICLR 2026Depth Anything 3: Recovering the Visual Space from Any Views
- CVPR 2026Co-Me Confidence Guided Token Merging for Visual Geometric Transformers
全部视听学习论文
共 281 篇，第 4 / 6 页
- ICLR 2026Enabling True Global Perception in State Space Models for Visual Tasks
- ICLR 2026Entropy-Monitored Kernelized Token Distillation for Audio-Visual Compression
- ICLR 2026FARTrack: Fast Autoregressive Visual Tracking with High Performance
- ICLR 2026FastVGGT: Fast Visual Geometry Transformer
- ICLR 2026FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
- ICLR 2026FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding
- ICLR 2026From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training
- ICLR 2026HierLoc: Hyperbolic Entity Embeddings for Hierarchical Visual Geolocation
- ICLR 2026JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization
- ICLR 2026JointAVBench: A Benchmark for Joint Audio-Visual Reasoning Evaluation
- ICLR 2026MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites
- ICLR 2026Model-Guided Microstimulation Steers Primate Visual Behavior
- ICLR 2026OmniCVR: A Benchmark for Omni-Composed Video Retrieval with Vision, Audio, and Text
- ICLR 2026OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs
- ICLR 2026Procedural Mistake Detection via Action Effect Modeling
- ICLR 2026Query-Guided Spatial–Temporal–Frequency Interaction for Music Audio–Visual Question Answering
- ICLR 2026RAR: Reversing Visual Attention Re-Sinking for Unlocking Potential in Multimodal Large Language Models
- ICLR 2026reAR: Rethinking Visual Autoregressive Models via Token-wise Consistency Regularization
- ICLR 2026Seeing Through the Brain: New Insights from Decoding Visual Stimuli with fMRI
- ICLR 2026Self-Improving Loops for Visual Robotic Planning
- ICLR 2026SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Model
- ICLR 2026SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation
- ICLR 2026The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss
- ICLR 2026Unified 3D Scene Understanding Through Physical World Modeling
- ICLR 2026VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning
- ICLR 2026Visual Autoregressive Modeling for Instruction-Guided Image Editing
- ICLR 2026Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow
- ICLR 2026Visual Planning: Let's Think Only with Images
- ICLR 2026Visual Prompt-Agnostic Evolution
- ICLR 2026WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM
- ICML 2026AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs
- ICML 2026AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes
- ICML 2026Bioacoustic Geolocation: Species Sounds as Geographic Signals
- ICML 2026CAST: Modeling Visual State Transitions for Consistent Video Retrieval
- ICML 2026Dual Latent Memory for Visual Multi-agent System
- ICML 2026DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics
- ICML 2026EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
- ICML 2026Emergent Visual Representations through Unsupervised Spiking Networks with Synaptic Pruning
- ICML 2026FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models
- ICML 2026From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping
- ICML 2026From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection
- ICML 2026Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM Inference
- ICML 2026INFER: Learning Implicit Neural Frequency Response Fields for Confined Acoustic Environments
- ICML 2026JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments
- ICML 2026Just Noticeable Difference Modeling for Deep Visual Features
- ICML 2026Learning Generalized Trackers with Elastic Token Budgets
- ICML 2026LightAVSeg: Lightweight Audio-Visual Segmentation
- ICML 2026ModernVBERT: Towards Smaller Visual Document Retrievers
- ICML 2026Multimodal Function Vectors for Visual Relations
- ICML 2026Neural-Inspired Modeling of Auditory Selection and Compensation for Audio-Visual Speech Separation
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"}
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。