高效训练论文趋势 2023–2026
Scaling law、MoE、蒸馏与训练效率
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,765 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 112 | 67 | 83 | 84 | 346 |
| 2024 | 20 | 78 | 122 | 80 | 300 |
| 2025 | 190 | 126 | 118 | 82 | 516 |
| 2026 | 177 | 148 | 169 | 109 | 603 |
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 177 篇，第 4 / 4 页
- NeurIPS 2026Speed Predictions for Online Energy-Efficient Scheduling
- NeurIPS 2026Spike-SFT: Selective Parameter Enhancement and Fusion for Efficient Spiking Neural Networks
- NeurIPS 2026Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference
- NeurIPS 2026Stroke-Audited Quadratic Bezier Splatting with Structural Initialization for Efficient Painting Rendering
- NeurIPS 2026Structured Unitary Tensor Network Representations for Circuit-Efficient Quantum Data Encoding
- NeurIPS 2026Subdata Selection: A Unified Framework for Optimal Selection and Statistical Efficiency Assessment
- NeurIPS 2026SWE-Crafter: Scaling Executable Multilingual Software Engineering Data with Meta-Skill Agents
- NeurIPS 2026Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models
- NeurIPS 2026Talk Less, Work More: Communication-Efficient Decentralized Stochastic Approximation
- NeurIPS 2026Target-Budget Best-Function Identification for Scaling-Law-Guided Model Selection
- NeurIPS 2026TeMPO: Frame-Causal Token Compression for Efficient Video Large Language Model
- NeurIPS 2026Temporal Smoothness Constraints on Efficient Neurobiological Codes Imply Temporal Specialization
- NeurIPS 2026The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks
- NeurIPS 2026The Kernel Reality Check: Benchmarking and Distilling Efficient Attention at Scale
- NeurIPS 2026The SEC Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data
- NeurIPS 2026Token Filtering: Online Attention Pruning via KV Similarity for Efficient LLM Inference
- NeurIPS 2026TokenRouter: Efficient Serving System for Token-Level LLM Routing
- NeurIPS 2026ToLD: Efficient Time Series Forecasting via Tokenized Truncated Latent Diffusion
- NeurIPS 2026Towards Principled Efficient Rollout Allocation in Test-Time Training
- NeurIPS 2026TTB: Test-time MLP Baking for Efficient Rendering of Decoder-only View Synthesis Models
- NeurIPS 2026Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting
- NeurIPS 2026UTOPI: Efficient Egocentric Long-Video Understanding in AR via User-Guided Token Pre-Compression
- NeurIPS 2026Vendi Anomaly Scores for Efficient and Accurate Anomaly Detection
- NeurIPS 2026Vortex: Efficient and Programmable Sparse Attention Serving
- NeurIPS 2026What to Predict for Efficient Scheduling on Parallel Machines
- NeurIPS 2026Where You Backpropagate Matters: Token Hypothesis for Memory-Efficient Fine-Tuning
- NeurIPS 2026Winfree Oscillatory Neural Network
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查高效训练在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "efficient-training"}
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。