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 190 篇，第 1 / 4 页

1. NeurIPS 2025$\texttt{BetaConform}$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer
2. NeurIPS 20254DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
3. NeurIPS 2025A Stable Whitening Optimizer for Efficient Neural Network Training
4. NeurIPS 2025A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone
5. NeurIPS 2025A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values
6. NeurIPS 2025Accurate and Efficient Low-Rank Model Merging in Core Space
7. NeurIPS 2025Accurate KV Cache Eviction via Anchor Direction Projection for Efficient LLM Inference
8. NeurIPS 2025Active Measurement: Efficient Estimation at Scale
9. NeurIPS 2025Active Seriation: Efficient Ordering Recovery with Statistical Guarantees
10. NeurIPS 2025Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
11. NeurIPS 2025AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
12. NeurIPS 2025All You Need is One: Capsule Prompt Tuning with a Single Vector
13. NeurIPS 2025AmorLIP: Efficient Language-Image Pretraining via Amortization
14. NeurIPS 2025An Efficient Local Search Approach for Polarized Community Discovery in Signed Networks
15. NeurIPS 2025Angles Don’t Lie: Unlocking Training‑Efficient RL Through the Model’s Own Signals
16. NeurIPS 2025Are Language Models Efficient Reasoners? A Perspective from Logic Programming
17. NeurIPS 2025Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives
18. NeurIPS 2025Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training
19. NeurIPS 2025Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression
20. NeurIPS 2025CAT: Circular-Convolutional Attention for Sub-Quadratic Transformers
21. NeurIPS 2025Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach
22. NeurIPS 2025ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
23. NeurIPS 2025COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation
24. NeurIPS 2025CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
25. NeurIPS 2025CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization
26. NeurIPS 2025Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo
27. NeurIPS 2025Computation and Memory-Efficient Model Compression with Gradient Reweighting
28. NeurIPS 2025Computational Budget Should Be Considered in Data Selection
29. NeurIPS 2025Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based Models
30. NeurIPS 2025Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning
31. NeurIPS 2025CrossSpectra: Exploiting Cross-Layer Smoothness for Parameter-Efficient Fine-Tuning
32. NeurIPS 2025D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction
33. NeurIPS 2025DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
34. NeurIPS 2025Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
35. NeurIPS 2025Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
36. NeurIPS 2025DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method
37. NeurIPS 2025Dependency Parsing is More Parameter-Efficient with Normalization
38. NeurIPS 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradients
39. NeurIPS 2025Diffusion on Demand: Selective Caching and Modulation for Efficient Generation
40. NeurIPS 2025Dimension-adapted Momentum Outscales SGD
41. NeurIPS 2025DoDo-Code: an Efficient Levenshtein Distance Embedding-based Code for 4-ary IDS Channel
42. NeurIPS 2025Don't be lazy: CompleteP enables compute-efficient deep transformers
43. NeurIPS 2025DuSA: Fast and Accurate Dual-Stage Sparse Attention Mechanism Accelerating Both Training and Inference
44. NeurIPS 2025DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation
45. NeurIPS 2025E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products
46. NeurIPS 2025EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization
47. NeurIPS 2025ECO: Evolving Core Knowledge for Efficient Transfer
48. NeurIPS 2025Efficient $k$-Sparse Band–Limited Interpolation with Improved Approximation Ratio
49. NeurIPS 2025Efficient and Generalizable Mixed-Precision Quantization via Topological Entropy
50. NeurIPS 2025Efficient Data Selection at Scale via Influence Distillation

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。