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 499 篇，第 3 / 10 页

101. NeurIPS 2026Neural Neural Scaling Laws
102. NeurIPS 2026NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training
103. NeurIPS 2026NIKA: Efficient Neural Video Representation via Structured Latent Diversity
104. NeurIPS 2026Normalized Architectures are Natively 4-Bit
105. NeurIPS 2026NoTA: Normalized Tensor Adaptation for Parameter-Efficient Continual Learning
106. NeurIPS 2026Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamic Mechanisms and Efficient Alignment
107. NeurIPS 2026OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
108. NeurIPS 2026OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs
109. NeurIPS 2026On Minimizing Regret in Fixed-Confidence $\varepsilon$-Best Arm Identification
110. NeurIPS 2026On Neural Scaling Laws for Weather Emulation through Continual Training
111. NeurIPS 2026On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing
112. NeurIPS 2026One Temperature to Rule Them All?
113. NeurIPS 2026Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation
114. NeurIPS 2026Optimal scaling laws in learning hierarchical multi-index models
115. NeurIPS 2026Orlicz–Sobolev with Musielak: An Efficient Regularization Approach for Graph-based IPM
116. NeurIPS 2026Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers
117. NeurIPS 2026PACE: Pareto-Adaptive Compression for Efficient Native MLLMs
118. NeurIPS 2026Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
119. NeurIPS 2026Patch Hierarchical Attention Transformers for Efficient Particle Jet Tagging
120. NeurIPS 2026PipeFSDP: Efficient Pipeline Parallel under Fully Sharded Data Parallel for Large Language Model Training
121. NeurIPS 2026Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation
122. NeurIPS 2026Predicting and improving test-time scaling laws via reward tail-guided search
123. NeurIPS 2026Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs Inference
124. NeurIPS 2026Progressive Layer-wise Supervision: Deep-to-Shallow Supervision Annealing for Efficient and Robust Speech Deepfake Detection
125. NeurIPS 2026Proper Agnostic Learning of Functions of Halfspaces
126. NeurIPS 2026QueryStop: Dynamic Stop Signals for Efficient Streaming Inference
127. NeurIPS 2026Random Attention Pattern Learning Enables Emergent Capabilities
128. NeurIPS 2026Relaxed On-Policy Distillation: Selective Credit Allocation for Scaling Reasoning Efficiently
129. NeurIPS 2026RelFlexformer: Efficient Attention Transformers for Integrable Relative Positional Encodings
130. NeurIPS 2026RePiD: Efficient Recursive Pixel-Space Diffusion via Hierarchical Patch Denoising
131. NeurIPS 2026Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?
132. NeurIPS 2026Rethinking Expressivity and Efficiency in Test-Time Training
133. NeurIPS 2026Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm
134. NeurIPS 2026Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization
135. NeurIPS 2026Robust and Efficient Backdoor Mitigation for ML Models via Tolerant Property Testing
136. NeurIPS 2026Robust and Efficient Continual Model Merging via Global Singular Subspace Separation and Restoration
137. NeurIPS 2026ROCKET: Rapid Optimization via Calibration-guided Knapsack-Enhanced Truncation for Efficient Model Compression
138. NeurIPS 2026RubiConv - Efficient Boundary-Respecting Convolutions
139. NeurIPS 2026SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity
140. NeurIPS 2026Sample-Efficient Optimization over Generative Priors via Coarse Learnability
141. NeurIPS 2026Scaling Laws for SAE Training Data
142. NeurIPS 2026Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks
143. NeurIPS 2026Should We Pay This Much for Robustness? Efficient Proxy Certificates with Marginal Guarantees
144. NeurIPS 2026Show Me What You Don’t Know: Efficient Sampling from Invariant Sets for Model Validation
145. NeurIPS 2026SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
146. NeurIPS 2026SimpleEvol: Efficient Intelligence Conversion via Less Human Prior in Automated Heuristic Design
147. NeurIPS 2026SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining
148. NeurIPS 2026SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
149. NeurIPS 2026Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache
150. NeurIPS 2026Speculative Self-Distillation enables Efficient Knowledge Internalization

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。