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 109 篇，第 1 / 3 页

1. CVPR 2026A Bit is All You Need Efficient Video Capture via
2. CVPR 2026AdaBet Gradient-free Layer Selection for Efficient Training of Deep Neural
3. CVPR 2026Adaptive Bayesian Early-Exit Networks for Efficient Non-Transferable Learning
4. CVPR 2026Adaptive Data Augmentation with Multi-armed Bandit Sample-Efficient Embedding Calibration for
5. CVPR 2026All Vehicles Can Lie Efficient Adversarial Defense in Fully Untrusted-Vehicle
6. CVPR 2026An Efficient Token Compression Framework for Visual Object Tracking
7. CVPR 2026Annotation-Efficient Coreset Selection for Context-dependent Segmentation
8. CVPR 2026Beyond Top Activations Efficient and Reliable Crowdsourced Evaluation of Automated
9. CVPR 2026Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers
10. CVPR 2026CoIn Coverage and Informativeness-Guided Token Reduction for Efficient Large Multimodal
11. CVPR 2026CoLC Communication-Efficient Collaborative Perception with LiDAR Completion
12. CVPR 2026Complementary Prototype Mapping for Efficient Multimodal Anomaly Detection
13. CVPR 2026Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict
14. CVPR 2026CoV-Align Efficient Fine-grained Cross-Modal Alignment with Cohesive Visual Semantics Priority
15. CVPR 2026Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation
16. CVPR 2026DAGE Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
17. CVPR 2026DDiT Dynamic Patch Scheduling for Efficient Diffusion Transformers
18. CVPR 2026Decompose Mix Adapt A Unified Framework for Parameter-Efficient Neural Network
19. CVPR 2026Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity
20. CVPR 2026Discovering Adaptive Task Dependencies for Efficient Multi-Task Representation Compression
21. CVPR 2026Distilling Quasi-Conformal Mapping A Generalizable and Efficient Solution for Wide-Angle
22. CVPR 2026DiT-IC Aligned Diffusion Transformer for Efficient Image Compression
23. CVPR 2026dMLLM-TTS Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large
24. CVPR 2026DP-FedAdamW An Efficient Optimizer for Differentially Private Federated Large Models
25. CVPR 2026Dual-branch Distilled Transformer for Efficient Asymmetric UAV Tracking
26. CVPR 2026Dual-Granularity Memory for Efficient Video Generation
27. CVPR 2026Edge-RecViT Efficient Vision Transformer via Semantic-Refined Dynamic Recursion
28. CVPR 2026Efficiency Follows Global-Local Decoupling
29. CVPR 2026Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation
30. CVPR 2026Efficient and High-Fidelity Omni Modality Retrieval
31. CVPR 2026Efficient Equivariant Transformer for Self-Driving Agent Modeling
32. CVPR 2026Efficient Hybrid SE3-Equivariant Visuomotor Flow Policy via Spherical Harmonics for
33. CVPR 2026Efficient Unrolled Networks for Large-Scale 3D Inverse Problems
34. CVPR 2026Efficient Weighted Sampling via Score-based Generative Models
35. CVPR 2026EfficientVPR Toward Efficient Visual Place Recognition via Scene-Aware Prompt Tuning
36. CVPR 2026ELiC Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and
37. CVPR 2026ELITE Efficient Gaussian Head Avatar from a Monocular Video via
38. CVPR 2026Enhancing Accuracy of Uncertainty Estimation in Appearance-based Gaze Tracking with
39. CVPR 2026FastGaMer Efficient GainMap Learning for Practical Inverse Tone Mapping
40. CVPR 2026FlexiVideo Variation-Aware Temporal Dynamics Modeling for Efficient Video Understanding
41. CVPR 2026Flow Map Distillation Without Data
42. CVPR 2026From Sketch to Fresco Efficient Diffusion Transformer with Progressive Resolution
43. CVPR 2026GeoDexGrasp Geometry-aware Generation for Data-efficient and Physics-plausible Dexterous Grasping
44. CVPR 2026Geometry-driven OOD Detectors Are Class-Incremental Learners
45. CVPR 2026GIFT Global Irreplaceability Frame Targeting for Efficient Video Understanding
46. CVPR 2026GR-Gauge Cost-efficient Training Configuration By Gauging the Gradient Redundancy
47. CVPR 2026High-Quality and Efficient Turbulence Mitigation with Events
48. CVPR 2026Hyperbolic Busemann Neural Networks
49. CVPR 2026IAFMNet Information-Aware Feature Modulation for Efficient Super-Resolution
50. CVPR 2026LaRP Efficient Multi-View Inpainting with Latent Reprojection Priors

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。