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 4 / 4 页

151. CVPR 2023CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP
152. CVPR 2023Habitat-Matterport 3D Semantics Dataset
153. CVPR 2023Improving Visual Representation Learning Through Perceptual Understanding
154. CVPR 2023Long Range Pooling for 3D Large-Scale Scene Understanding
155. CVPR 2023OpenScene: 3D Scene Understanding With Open Vocabularies
156. CVPR 2023PanelNet: Understanding 360 Indoor Environment via Panel Representation
157. CVPR 2023Panoptic Lifting for 3D Scene Understanding With Neural Fields
158. CVPR 2023PanoSwin: A Pano-Style Swin Transformer for Panorama Understanding
159. CVPR 2023Skinned Motion Retargeting With Residual Perception of Motion Semantics & Geometry
160. CVPR 2023Therbligs in Action: Video Understanding Through Motion Primitives
161. CVPR 2023Understanding Imbalanced Semantic Segmentation Through Neural Collapse
162. CVPR 2023Understanding Masked Autoencoders via Hierarchical Latent Variable Models
163. ICLR 2023Deconstructing Distributions: A Pointwise Framework of Learning
164. ICLR 2023First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains
165. ICLR 2023ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
166. ICLR 2023Towards Understanding Why Mask Reconstruction Pretraining Helps in Downstream Tasks
167. ICLR 2023Understanding DDPM Latent Codes Through Optimal Transport
168. ICLR 2023Understanding Embodied Reference with Touch-Line Transformer
169. ICLR 2023Understanding new tasks through the lens of training data via exponential tilting
170. ICLR 2023Understanding the Covariance Structure of Convolutional Filters
171. ICLR 2023Understanding Train-Validation Split in Meta-Learning with Neural Networks
172. ICLR 2023Understanding weight-magnitude hyperparameters in training binary networks
173. ICLR 2023Understanding Why Generalized Reweighting Does Not Improve Over ERM
174. ICLR 2023Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding
175. ICML 2023How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding
176. ICML 2023Towards Understanding Ensemble Distillation in Federated Learning
177. ICML 2023Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
178. ICML 2023Understanding Plasticity in Neural Networks
179. ICML 2023Understanding Self-Distillation in the Presence of Label Noise
180. NeurIPS 2023ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
181. NeurIPS 2023Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities
182. NeurIPS 2023From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Models to Pre-trained Machine Reader
183. NeurIPS 2023InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding
184. NeurIPS 2023NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding
185. NeurIPS 2023RaLEs: a Benchmark for Radiology Language Evaluations
186. NeurIPS 2023Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective
187. NeurIPS 2023Understanding Deep Gradient Leakage via Inversion Influence Functions
188. NeurIPS 2023Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization
189. NeurIPS 2023Understanding the detrimental class-level effects of data augmentation

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。