高效训练论文趋势 2023–2026

主要结论

• 高效训练论文从 2023 年的 346 篇增长到 2026 年的 603 篇，三年间扩大到约 1.7 倍。
• NeurIPS 是发高效训练论文最多的会议，2023–2026 年共 499 篇，占四个会议总量的 28%。
• 交叉方向里涨得最快的是深度学习 · large language models：同时属于两个主题的论文从 2023 年的 6 篇增至 2026 年的 50 篇。
• 在「效率与系统」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的硬件协同是 4.4 倍，高效训练是 1.7 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 2026Adaptive Residual Quantization for Memory-Efficient Temporal Action Segmentation
• ICML 2026A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization
• ICLR 2026An Efficient SE(p)-Invariant Transport Metric Driven by Polar Transport Discrepancy-based Representation
• CVPR 2026A Bit is All You Need Efficient Video Capture via
• NeurIPS 20254DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
• ICML 2025A Sample Efficient Conditional Independence Test in the Presence of Discretization
• ICLR 2025Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator
• CVPR 2025Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation
• NeurIPS 2024$\texttt{dattri}$: A Library for Efficient Data Attribution
• ICML 2024A fast algorithm to simulate nonlinear resistive networks
• ICLR 2024Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks
• CVPR 2024Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack
• NeurIPS 2023Alternating Updates for Efficient Transformers
• ICML 2023Auxiliary Modality Learning with Generalized Curriculum Distillation
• ICLR 2023A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
• CVPR 2023A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization
• NeurIPS 2026Advanced Routing as Regularization Allocation for Efficient Diffusion Transformer Training
• ICML 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
• ICLR 2026AQER: A Scalable and Efficient Data Loader for Digital Quantum Computers
• CVPR 2026Adaptive Bayesian Early-Exit Networks for Efficient Non-Transferable Learning

全部高效训练论文

共 355 篇，第 3 / 8 页

101. CVPR 2026Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
102. CVPR 2026TriLite Efficient Weakly Supervised Object Localization with Universal Visual Features
103. CVPR 2026UETrack A Unified and Efficient Framework for Single Object Tracking
104. CVPR 2026VDOT Efficient Unified Video Creation via Optimal Transport Distillation
105. CVPR 2026VEMamba Efficient Isotropic Reconstruction of Volume Electron Microscopy with Axial-Lateral
106. CVPR 2026VMonarch Efficient Video Diffusion Transformers with Structured Attention
107. CVPR 2026WhisperNet A Scalable Solution for Bandwidth-Efficient Collaboration
108. CVPR 2026WikiCLIP An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition
109. CVPR 2026YOSE You Only Select Essential Tokens for Efficient DiT-based Video
110. CVPR 2025Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation
111. CVPR 2025ATP: Adaptive Threshold Pruning for Efficient Data Encoding in Quantum Neural Networks
112. CVPR 2025Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression
113. CVPR 2025AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video Hashing
114. CVPR 2025Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning
115. CVPR 2025Brain-Inspired Spiking Neural Networks for Energy-Efficient Object Detection
116. CVPR 2025CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution
117. CVPR 2025Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs
118. CVPR 2025CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR
119. CVPR 2025COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection
120. CVPR 2025Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
121. CVPR 2025Dataset Distillation with Neural Characteristic Function: A Minmax Perspective
122. CVPR 2025DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging
123. CVPR 2025DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos
124. CVPR 2025DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models
125. CVPR 2025DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows
126. CVPR 2025DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables
127. CVPR 2025EASEMVC:Efficient Dual Selection Mechanism for Deep Multi-View Clustering
128. CVPR 2025EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting
129. CVPR 2025EdgeTAM: On-Device Track Anything Model
130. CVPR 2025Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement
131. CVPR 2025Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks
132. CVPR 2025Efficient Depth Estimation for Unstable Stereo Camera Systems on AR Glasses
133. CVPR 2025Efficient Diffusion as Low Light Enhancer
134. CVPR 2025Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation
135. CVPR 2025Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention
136. CVPR 2025Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction
137. CVPR 2025Efficient Motion-Aware Video MLLM
138. CVPR 2025Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency
139. CVPR 2025Efficient Visual State Space Model for Image Deblurring
140. CVPR 2025EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
141. CVPR 2025Enduring, Efficient and Robust Trajectory Prediction Attack in Autonomous Driving via Optimization-Driven Multi-Frame Perturbation Framework
142. CVPR 2025Enhancing Dataset Distillation via Non-Critical Region Refinement
143. CVPR 2025EVOS: Efficient Implicit Neural Training via EVOlutionary Selector
144. CVPR 2025Faster Parameter-Efficient Tuning with Token Redundancy Reduction
145. CVPR 2025Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints
146. CVPR 2025FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training
147. CVPR 2025Flexible Frame Selection for Efficient Video Reasoning
148. CVPR 2025From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning
149. CVPR 2025From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling
150. CVPR 2025GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction

常见问题

2023–2026 年四大会议一共有多少篇高效训练论文？

共 1,765 篇，按年份分别是 2023 年 346 篇、2024 年 300 篇、2025 年 516 篇、2026 年 603 篇。

NeurIPS 2026 有多少篇高效训练论文？

NeurIPS 2026 有 177 篇高效训练论文，上一届是 190 篇。

ICLR 2026 有多少篇高效训练论文？

ICLR 2026 有 148 篇高效训练论文，上一届是 126 篇。

ICML 2026 有多少篇高效训练论文？

ICML 2026 有 169 篇高效训练论文，上一届是 118 篇。

CVPR 2026 有多少篇高效训练论文？

CVPR 2026 有 109 篇高效训练论文，上一届是 82 篇。

哪个会议的高效训练论文最多？

NeurIPS，2023–2026 年共 499 篇。