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 148 篇，第 1 / 3 页

1. ICLR 2026$\mu$LO: Compute-Efficient Meta-Generalization of Learned Optimizers
2. ICLR 2026A Generalized Geometric Theoretical Framework of Centroid Discriminant Analysis for Linear Classification of Multi-dimensional Data
3. ICLR 2026A universal compression theory: Lottery ticket hypothesis and superpolynomial scaling laws
4. ICLR 2026Achieving low-bit Muon through subspace preservation and grid quantization
5. ICLR 2026An Efficient SE(p)-Invariant Transport Metric Driven by Polar Transport Discrepancy-based Representation
6. ICLR 2026Annotation-Efficient Honesty Alignment via Confidence Elicitation and Calibration
7. ICLR 2026AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
8. ICLR 2026AQER: A Scalable and Efficient Data Loader for Digital Quantum Computers
9. ICLR 2026ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality
10. ICLR 2026Batch Pruning by Activation Stability
11. ICLR 2026Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes
12. ICLR 2026Beyond Outliers: A Study of Optimizers Under Quantization
13. ICLR 2026Beyond Student: An Asymmetric Network for Neural Network Inheritance
14. ICLR 2026Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining
15. ICLR 2026BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation
16. ICLR 2026Break the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models
17. ICLR 2026Cascadia: An Efficient Cascade Serving System for Large Language Models
18. ICLR 2026CaTS: Calibrated Test-Time Scaling for Efficient LLM Reasoning
19. ICLR 2026Channel-Aware Mixed-Precision Quantization for Efficient Long-Context Inference
20. ICLR 2026Composer: A Search Framework for Hybrid Neural Architecture Design
21. ICLR 2026Compute-Optimal Quantization-Aware Training
22. ICLR 2026Convex Efficient Coding
23. ICLR 2026Cost-Aware Dynamic Tree Construction for Efficient Large Language Model Inference
24. ICLR 2026CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure
25. ICLR 2026DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection
26. ICLR 2026Difficulty–Diversity Collaborative Filtering for Data-Efficient LLM Fine-Tuning
27. ICLR 2026DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation
28. ICLR 2026DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
29. ICLR 2026Distillation of Large Language Models via Concrete Score Matching
30. ICLR 2026Distilling to Hybrid Attention Models via KL-Guided Layer Selection
31. ICLR 2026DPad: Efficient Diffusion Language Models with Suffix Dropout
32. ICLR 2026DPQuant: Efficient and Private Model Training via Dynamic Quantization Scheduling
33. ICLR 2026Dual Language Models: Balancing sample-efficiency and overfitting resilience
34. ICLR 2026DUET: DISTILLED LLM UNLEARNING FROM AN EFFICIENTLY CONTEXTUALIZED TEACHER
35. ICLR 2026Efficient and Sharp Off-Policy Learning under Unobserved Confounding
36. ICLR 2026Efficient Approximate Posterior Sampling with Annealed Langevin Monte Carlo
37. ICLR 2026Efficient Autoregressive Inference for Transformer Probabilistic Models
38. ICLR 2026Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits
39. ICLR 2026Efficient Credal Prediction through Decalibration
40. ICLR 2026Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization
41. ICLR 2026Efficient Differentiable Contact Model with Long-range Influence
42. ICLR 2026Efficient Ensemble Conditional Independence Test Framework for Causal Discovery
43. ICLR 2026Efficient Learning on Large Graphs using a Densifying Regularity Lemma
44. ICLR 2026Efficient Message-Passing Transformer for Error Correcting Codes
45. ICLR 2026Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits
46. ICLR 2026Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation
47. ICLR 2026Efficient Prediction of Large Protein Complexes via Subunit-Guided Hierarchical Refinement
48. ICLR 2026Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees
49. ICLR 2026Efficient Sliced Wasserstein Distance Computation via Adaptive Bayesian Optimization
50. ICLR 2026Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval

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。