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 1,765 篇，第 2 / 36 页

51. CVPR 2026Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain
52. CVPR 2026LiDeRe A Lightweight Readout for Fast and Data-Efficient Dense Prediction
53. CVPR 2026LightSplat Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five
54. CVPR 2026Lite Any Stereo Efficient Zero-Shot Stereo Matching
55. CVPR 2026LLM-Guided Probabilistic Fusion for Label-Efficient Document Layout Analysis
56. CVPR 2026MAGICIAN Efficient Long-Term Planning with Imagined Gaussians for Active Mapping
57. CVPR 2026MaskDiME Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual
58. CVPR 2026Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block
59. CVPR 2026Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual
60. CVPR 2026Merge3D Efficient 3D Multimodal LLMs via Joint 2D-3D Token Merging
61. CVPR 2026MERIT Multi-domain Efficient RAW Image Translation
62. CVPR 2026MeToM Metadata-Guided Token Merging for Efficient Video LLMs
63. CVPR 2026MixerCSeg An Efficient Mixer Architecture for Crack Segmentation via Decoupled
64. CVPR 2026NAMI Efficient Image Generation via Bridged Progressive Rectified Flow Transformers
65. CVPR 2026NESTOR A Nested MOE-based Neural Operator for Large-Scale PDE Pre-Training
66. CVPR 2026Parameter-Efficient Adaptation for MLLMs via Implicit Modality Decomposition
67. CVPR 2026Parameter-efficient Continual Learning for Enhancing Plasticity without Forgetting under Limited
68. CVPR 2026PFGNet A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient
69. CVPR 2026PHASE-Net Physics-Grounded Harmonic Attention System for Efficient Remote Photoplethysmography Measurement
70. CVPR 2026Phased DMD Few-step Distribution Matching Distillation via Score Matching within
71. CVPR 2026PhaseWin Search Framework Enable Efficient Object-Level Interpretation
72. CVPR 2026PIX-TAB Efficient PIXel-Precise TABle Structure Recognition Approach with Speculative Decoding
73. CVPR 2026PlannerRFT Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-Tuning
74. CVPR 2026PosterOmni Generalized Artistic Poster Creation via Task Distillation and Unified
75. CVPR 2026Prime Once then Reprogram Locally An Efficient Alternative to Black-Box
76. CVPR 2026RAVEN Radar Adaptive Vision Encoders for Efficient Chirp-wise Object Detection
77. CVPR 2026ReFTA Breaking the Weight Reconstruction Bottleneck in Tensorized Parameter-Efficient Fine-Tuning
78. CVPR 2026RegFormer Transferable Relational Grounding for Efficient Weakly-Supervised Human-Object Interaction Detection
79. CVPR 2026Rejection Mixing Fast Semantic Propagation of Mask Tokens for Efficient
80. CVPR 2026Rethinking Dataset Distillation Hard Truths about Soft Labels
81. CVPR 2026Retrieve-to-Restore Efficient All-in-One Image Restoration with a Retrieval-Based Degradation Bank
82. CVPR 2026Revisiting Unknowns Towards Effective and Efficient Open-Set Active Learning
83. CVPR 2026S2FT Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain
84. CVPR 2026Scan Clusters Not Pixels A Cluster-Centric Paradigm for Efficient Ultra-high-definition
85. CVPR 2026SEA-Flow3D Simplified Efficient and Accurate Scene Flow via Spatial Vector
86. CVPR 2026SEATrack Simple Efficient and Adaptive Multimodal Tracker
87. CVPR 2026SegMo Co-Designing Content-Aware Sparsity and Locally-Cohesive Segment Parallelism for Efficient
88. CVPR 2026ShiftLUT Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration
89. CVPR 2026SkillSight Efficient First-Person Skill Assessment with Gaze
90. CVPR 2026SMV-EAR Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action
91. CVPR 2026SO3-Equivariant ViT-Adapter for Data-Efficient Zero-Shot Sim-to-Real Indoor Panoramic Depth Estimation
92. CVPR 2026Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer
93. CVPR 2026SpikeTrack A Spike-driven Framework for Efficient Visual Tracking
94. CVPR 2026SpikeTrack High-performance and Energy-efficient Event-Based Object Tracking with Spiking Neural
95. CVPR 2026SSM-Aware Token-Efficient VMamba via Adaptive Patch Pruning and Merging for
96. CVPR 2026Streamlined Knowledge Distillation
97. CVPR 2026Submodel Extraction for Efficient and Personalized Federated Learning via Optimal
98. CVPR 2026Token Reduction via Local and Global Contexts Optimization for Efficient
99. CVPR 2026TokenHand Discrete Token Representation for Efficient Hand Mesh Reconstruction
100. CVPR 2026Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework

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。