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 126 篇，第 3 / 3 页

101. ICLR 2025RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
102. ICLR 2025Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions
103. ICLR 2025Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
104. ICLR 2025Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens
105. ICLR 2025Scaling Laws for Precision
106. ICLR 2025Scaling Optimal LR Across Token Horizons
107. ICLR 2025Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study
108. ICLR 2025SelectFormer in Data Markets: Privacy-Preserving and Efficient Data Selection for Transformers with Multi-Party Computation
109. ICLR 2025Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts
110. ICLR 2025Skill Expansion and Composition in Parameter Space
111. ICLR 2025SONICS: Synthetic Or Not - Identifying Counterfeit Songs
112. ICLR 2025SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
113. ICLR 2025Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
114. ICLR 2025Structural-Entropy-Based Sample Selection for Efficient and Effective Learning
115. ICLR 2025Surprising Effectiveness of pretraining Ternary Language Model at Scale
116. ICLR 2025The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
117. ICLR 2025ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels
118. ICLR 2025TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
119. ICLR 2025TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
120. ICLR 2025Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning
121. ICLR 2025Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models
122. ICLR 2025u-$\mu$P: The Unit-Scaled Maximal Update Parametrization
123. ICLR 2025U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models
124. ICLR 2025Unified Parameter-Efficient Unlearning for LLMs
125. ICLR 2025Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
126. ICLR 2025ZETA: Leveraging $Z$-order Curves for Efficient Top-$k$ Attention

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。