口语理解论文趋势 2023–2026

主要结论

• 口语理解论文从 2023 年的 40 篇增长到 2026 年的 61 篇，三年间扩大到约 1.5 倍。
• CVPR 是发口语理解论文最多的会议，2023–2026 年共 62 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 14 篇。
• 在「语音与音频」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的音频生成是 4.3 倍，口语理解是 1.5 倍。

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 2026Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering
• ICML 2026A Single Layer to Explain Them All: Understanding Massive Values in Large Language Models
• ICLR 2026Neuron-Level Analysis of Cultural Understanding in Large Language Models
• CVPR 2026Consistent Instance Field for Dynamic Scene Understanding
• NeurIPS 2025The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
• ICML 2025On Understanding Attention-Based In-Context Learning for Categorical Data
• ICLR 2025Toward Understanding In-context vs. In-weight Learning
• CVPR 2025HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics
• NeurIPS 2024SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
• ICML 2024Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
• ICLR 2024Understanding Addition in Transformers
• CVPR 2024SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field
• NeurIPS 2023ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
• ICML 2023How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding
• ICLR 2023Towards Understanding Why Mask Reconstruction Pretraining Helps in Downstream Tasks
• CVPR 2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
• NeurIPS 2026EmbodiedObject: All-in-One Object Understanding with SLAT
• ICML 2026Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions
• ICLR 2026Towards Understanding the Shape of Representations in Protein Language Models
• CVPR 2026Lifting Unlabeled Internet-level Data for 3D Scene Understanding

全部口语理解论文

共 189 篇，第 2 / 4 页

51. NeurIPS 2026Understanding axial attention in TSFMs through single location regression
52. NeurIPS 2026Understanding Circulant Permutation to Extend the CMinHash Estimator
53. NeurIPS 2026Understanding Double Descent through Universal Compression
54. NeurIPS 2026Understanding Layer Patching in Model Size Interpolation
55. NeurIPS 2026Understanding Sample Efficiency in Predictive Coding
56. NeurIPS 2026Understanding the Co-evolutionary Solution Exchange of the MOEA/D: Minimal Communication Gives Maximal Speed-Ups
57. NeurIPS 2026Understanding the Convergence of Direct Training of SNNs with Surrogate Gradients
58. NeurIPS 2026Understanding the Curse of Unrolling
59. NeurIPS 2026Understanding the Effects of Hyper-Connections on Self-Attention Dynamics: A Bifurcation Analysis
60. NeurIPS 2026ViMU: Benchmarking Video Metaphorical Understanding
61. NeurIPS 2026When Safety Becomes An Outlier: Understanding the Retention of LLM Safety Behaviors
62. CVPR 2025Apollo: An Exploration of Video Understanding in Large Multimodal Models
63. CVPR 2025ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding
64. CVPR 2025DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding
65. CVPR 2025EventGPT: Event Stream Understanding with Multimodal Large Language Models
66. CVPR 2025FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding
67. CVPR 2025Ges3ViG : Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding
68. CVPR 2025GroundingFace: Fine-grained Face Understanding via Pixel Grounding Multimodal Large Language Model
69. CVPR 2025HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics
70. CVPR 2025LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
71. CVPR 2025Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models
72. CVPR 2025MP-GUI: Modality Perception with MLLMs for GUI Understanding
73. CVPR 2025MPDrive: Improving Spatial Understanding with Marker-Based Prompt Learning for Autonomous Driving
74. CVPR 2025PEACE: Empowering Geologic Map Holistic Understanding with MLLMs
75. CVPR 2025Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs
76. CVPR 2025Towards Universal Soccer Video Understanding
77. CVPR 2025Understanding Multi-layered Transmission Matrices
78. CVPR 2025VEU-Bench: Towards Comprehensive Understanding of Video Editing
79. CVPR 2025VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
80. CVPR 2025VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding
81. ICLR 2025Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
82. ICLR 2025Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models
83. ICLR 2025Toward Understanding In-context vs. In-weight Learning
84. ICLR 2025Understanding Factual Recall in Transformers via Associative Memories
85. ICLR 2025Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry
86. ICLR 2025Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape View
87. ICLR 2025Uni-Sign: Toward Unified Sign Language Understanding at Scale
88. ICML 2025On Understanding Attention-Based In-Context Learning for Categorical Data
89. ICML 2025Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
90. ICML 2025Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis
91. ICML 2025Understanding Mode Connectivity via Parameter Space Symmetry
92. ICML 2025Understanding Nonlinear Implicit Bias via Region Counts in Input Space
93. ICML 2025Understanding the difficulties of posterior predictive estimation
94. ICML 2025Understanding the Kronecker Matrix-Vector Complexity of Linear Algebra
95. ICML 2025Understanding the Limits of Deep Tabular Methods with Temporal Shift
96. ICML 2025Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees
97. ICML 2025Understanding the Unfairness in Network Quantization
98. NeurIPS 2025FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing
99. NeurIPS 2025Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks
100. NeurIPS 2025The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

常见问题

2023–2026 年四大会议一共有多少篇口语理解论文？

共 189 篇，按年份分别是 2023 年 40 篇、2024 年 38 篇、2025 年 50 篇、2026 年 61 篇。

NeurIPS 2026 有多少篇口语理解论文？

NeurIPS 2026 有 25 篇口语理解论文，上一届是 14 篇。

ICLR 2026 有多少篇口语理解论文？

ICLR 2026 有 6 篇口语理解论文，上一届是 7 篇。

ICML 2026 有多少篇口语理解论文？

ICML 2026 有 12 篇口语理解论文，上一届是 10 篇。

CVPR 2026 有多少篇口语理解论文？

CVPR 2026 有 18 篇口语理解论文，上一届是 19 篇。

哪个会议的口语理解论文最多？

CVPR，2023–2026 年共 62 篇。