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 6 / 6 页

251. ICML 2024Robust Yet Efficient Conformal Prediction Sets
252. ICML 2024Saliency strikes back: How filtering out high frequencies improves white-box explanations
253. ICML 2024Scalable AI Safety via Doubly-Efficient Debate
254. ICML 2024Scalable and Flexible Causal Discovery with an Efficient Test for Adjacency
255. ICML 2024Scaling Beyond the GPU Memory Limit for Large Mixture-of-Experts Model Training
256. ICML 2024Scaling Down Deep Learning with MNIST-1D
257. ICML 2024Scaling Laws for Fine-Grained Mixture of Experts
258. ICML 2024Scaling Laws for the Value of Individual Data Points in Machine Learning
259. ICML 2024See More Details: Efficient Image Super-Resolution by Experts Mining
260. ICML 2024Selecting Large Language Model to Fine-tune via Rectified Scaling Law
261. ICML 2024SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching
262. ICML 2024Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences
263. ICML 2024Simple linear attention language models balance the recall-throughput tradeoff
264. ICML 2024SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization
265. ICML 2024SparQ Attention: Bandwidth-Efficient LLM Inference
266. ICML 2024Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting
267. ICML 2024SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models
268. ICML 2024Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC
269. ICML 2024Tandem Transformers for Inference Efficient LLMs
270. ICML 2024Towards efficient deep spiking neural networks construction with spiking activity based pruning
271. ICML 2024Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration
272. ICML 2024Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations
273. ICML 2024Trainable Transformer in Transformer
274. ICML 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
275. ICML 2024Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning
276. ICML 2024TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks
277. ICML 2024Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention
278. ICML 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
279. ICML 2024What is Dataset Distillation Learning?
280. ICML 2024When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
281. NeurIPS 2024$\texttt{dattri}$: A Library for Efficient Data Attribution
282. NeurIPS 2024A Label is Worth A Thousand Images in Dataset Distillation
283. NeurIPS 2024AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment
284. NeurIPS 2024BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
285. NeurIPS 2024DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking
286. NeurIPS 2024E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
287. NeurIPS 2024Efficient Convex Algorithms for Universal Kernel Learning
288. NeurIPS 2024FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation
289. NeurIPS 2024Genetic-guided GFlowNets for Sample Efficient Molecular Optimization
290. NeurIPS 2024LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment
291. NeurIPS 2024LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing
292. NeurIPS 2024Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
293. NeurIPS 2024Provable and Efficient Dataset Distillation for Kernel Ridge Regression
294. NeurIPS 2024Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching
295. NeurIPS 2024Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies
296. NeurIPS 2024Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
297. NeurIPS 2024SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
298. NeurIPS 2024SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead
299. NeurIPS 2024TorchOpt: An Efficient Library for Differentiable Optimization
300. NeurIPS 2024V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark

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。