Efficient Training papers, 2023–2026

Key findings

• Efficient Training went from 346 papers in 2023 to 603 in 2026, roughly 1.7x in three years.
• NeurIPS publishes the most Efficient Training work: 499 papers from 2023 to 2026, 28% of the four-venue total.
• The fastest-growing overlap is with Deep learning · large language models: papers tagged with both rose from 6 in 2023 to 50 in 2026.
• Among the 5 topics under Efficiency and Systems, it ranks #3 by 2026 paper count; the fastest grower in the group, Hardware-Aware ML, is up 4.4x versus 1.7x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Efficient Training papers

419 papers, page 2 of 9

51. ICLR 2026EffiVMT: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning
52. ICLR 2026ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains
53. ICLR 2026Energy-Efficient Random Variate Generation via Compressed Lookup Tables
54. ICLR 2026Ensemble Prediction of Task Affinity for Efficient Multi-Task Learning
55. ICLR 2026Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
56. ICLR 2026Entropy-Based Block Pruning for Efficient Large Language Models
57. ICLR 2026ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping
58. ICLR 2026Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products
59. ICLR 2026Fast-dLLM v2: Efficient Block-Diffusion LLM
60. ICLR 2026Fewer Battles, More Gain: An Information-Efficient Framework for Arena-based LLM Evaluation
61. ICLR 2026Flatter Tokens are More Valuable for Speculative Draft Model Training
62. ICLR 2026Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning
63. ICLR 2026Forge: Compiling a Unified Abstraction into Scalable Kernels for Linear Attention
64. ICLR 2026FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
65. ICLR 2026FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel
66. ICLR 2026FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation
67. ICLR 2026GAGA: Gaussianity-Aware Gaussian Approximation for Efficient 3D Molecular Generation
68. ICLR 2026GradPruner: Gradient-guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs
69. ICLR 2026Grounding and Enhancing Informativeness and Utility in Dataset Distillation
70. ICLR 2026Guided Speculative Inference for Efficient Test-Time Alignment of LLMs
71. ICLR 2026HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space
72. ICLR 2026Highly Efficient and Effective LLMs with Multi-Boolean Architectures
73. ICLR 2026Householder-Diagonalized Linear Attention (HDLA): Utilizing Enhanced Decay Mechanism for Efficient Sequence Modeling
74. ICLR 2026How Reliable is Language Model Micro-Benchmarking?
75. ICLR 2026How Text Quality Interventions Reshape Neural Scaling Laws for LLMs: Empirical Study
76. ICLR 2026How to train data-efficient LLMs
77. ICLR 2026Image is All You Need: Towards Efficient and Effective Large Language Model-Based Recommender Systems
78. ICLR 2026Inconsistency Biases in Dynamic Data Pruning
79. ICLR 2026KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
80. ICLR 2026Knowledge Distillation for Large Language Models through Residual Learning
81. ICLR 2026Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better
82. ICLR 2026Libra: Effective yet Efficient Load Balancing for Large-scale MoE Inference
83. ICLR 2026LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution
84. ICLR 2026LipNeXt: Scaling up Lipschitz-based Certified Robustness to Billion-parameter Models
85. ICLR 2026LiteGuard: Efficient Task-Agnostic Model Fingerprinting with Enhanced Generalization
86. ICLR 2026Lookup multivariate Kolmogorov-Arnold Networks
87. ICLR 2026ManipEvalAgent: Promptable and Efficient Evaluation Framework for Robotic Manipulation Policies
88. ICLR 2026MatRIS: Toward Reliable and Efficient Pretrained Machine Learning Interaction Potentials
89. ICLR 2026MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models
90. ICLR 2026MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure
91. ICLR 2026MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs
92. ICLR 2026MoL: Adaptive Mixture-of-Length Reasoning for Efficient Question Answering with Context
93. ICLR 2026MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling
94. ICLR 2026NAIPv2: Debiased Pairwise Learning for Efficient Paper Quality Estimation
95. ICLR 2026NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization
96. ICLR 2026NLI : Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference
97. ICLR 2026No outlier channels but with outlier blocks
98. ICLR 2026Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs
99. ICLR 2026Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling
100. ICLR 2026Otters: An Energy-Efficient Spiking Transformer via Optical Time-to-First-Spike Encoding

FAQ

How many Efficient Training papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,765 in total: 346 in 2023, 300 in 2024, 516 in 2025, 603 in 2026.

How many Efficient Training papers are at NeurIPS 2026?

NeurIPS 2026 has 177 Efficient Training papers, versus 190 the year before.

How many Efficient Training papers are at ICLR 2026?

ICLR 2026 has 148 Efficient Training papers, versus 126 the year before.

How many Efficient Training papers are at ICML 2026?

ICML 2026 has 169 Efficient Training papers, versus 118 the year before.

How many Efficient Training papers are at CVPR 2026?

CVPR 2026 has 109 Efficient Training papers, versus 82 the year before.

Which conference publishes the most Efficient Training papers?

NeurIPS, with 499 papers from 2023 to 2026.