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 300 篇，第 3 / 6 页

101. ICLR 2024Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
102. ICLR 2024Efficient Streaming Language Models with Attention Sinks
103. ICLR 2024Efficient Subgraph GNNs by Learning Effective Selection Policies
104. ICLR 2024Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products
105. ICLR 2024Fair and Efficient Contribution Valuation for Vertical Federated Learning
106. ICLR 2024Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models
107. ICLR 2024Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
108. ICLR 2024Fast-ELECTRA for Efficient Pre-training
109. ICLR 2024Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers
110. ICLR 2024FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler
111. ICLR 2024Finite-State Autoregressive Entropy Coding for Efficient Learned Lossless Compression
112. ICLR 2024FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
113. ICLR 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
114. ICLR 2024IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
115. ICLR 2024Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
116. ICLR 2024Jointly-Learned Exit and Inference for a Dynamic Neural Network
117. ICLR 2024Knowledge Distillation Based on Transformed Teacher Matching
118. ICLR 2024Language Model Cascades: Token-Level Uncertainty And Beyond
119. ICLR 2024Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
120. ICLR 2024LEMON: Lossless model expansion
121. ICLR 2024Linear Log-Normal Attention with Unbiased Concentration
122. ICLR 2024LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized Attention
123. ICLR 2024LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
124. ICLR 2024LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
125. ICLR 2024Manipulating dropout reveals an optimal balance of efficiency and robustness in biological and machine visual systems
126. ICLR 2024MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding
127. ICLR 2024MEND: Meta Demonstration Distillation for Efficient and Effective In-Context Learning
128. ICLR 2024Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
129. ICLR 2024Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings
130. ICLR 2024Node2ket: Efficient High-Dimensional Network Embedding in Quantum Hilbert Space
131. ICLR 2024Object centric architectures enable efficient causal representation learning
132. ICLR 2024OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
133. ICLR 2024Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models
134. ICLR 2024PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
135. ICLR 2024Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features
136. ICLR 2024Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
137. ICLR 2024QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
138. ICLR 2024RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design
139. ICLR 2024ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion
140. ICLR 2024Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning
141. ICLR 2024RETSim: Resilient and Efficient Text Similarity
142. ICLR 2024Scaling Laws for Sparsely-Connected Foundation Models
143. ICLR 2024Scaling Laws of RoPE-based Extrapolation
144. ICLR 2024Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
145. ICLR 2024SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
146. ICLR 2024ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
147. ICLR 2024Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework
148. ICLR 2024Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features
149. ICLR 2024Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation
150. ICLR 2024Tree-Planner: Efficient Close-loop Task Planning with Large Language Models

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。