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

1,765 papers, page 22 of 36

1051. NeurIPS 2025Memory-Efficient Training with In-Place FFT Implementation
1052. NeurIPS 2025Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression
1053. NeurIPS 2025Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks
1054. NeurIPS 2025Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training
1055. NeurIPS 2025MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
1056. NeurIPS 2025Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures
1057. NeurIPS 2025Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
1058. NeurIPS 2025Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE
1059. NeurIPS 2025Oracle-Efficient Combinatorial Semi-Bandits
1060. NeurIPS 2025Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables
1061. NeurIPS 2025Parallel Scaling Law for Language Models
1062. NeurIPS 2025ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
1063. NeurIPS 2025Pay Attention to Small Weights
1064. NeurIPS 2025Position: AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
1065. NeurIPS 2025Power Lines: Scaling laws for weight decay and batch size in LLM pre-training
1066. NeurIPS 2025PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectors
1067. NeurIPS 2025Predictable Scale (Part II) --- Farseer: A Refined Scaling Law in LLMs
1068. NeurIPS 2025Private Statistical Estimation via Truncation
1069. NeurIPS 2025Private Training Large-scale Models with Efficient DP-SGD
1070. NeurIPS 2025Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths
1071. NeurIPS 2025PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning
1072. NeurIPS 2025Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment
1073. NeurIPS 2025Quadratic Coreset Selection: Certifying and Reconciling Sequence and Token Mining for Efficient Instruction Tuning
1074. NeurIPS 2025Random Search Neural Networks for Efficient and Expressive Graph Learning
1075. NeurIPS 2025RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation
1076. NeurIPS 2025RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget
1077. NeurIPS 2025REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders
1078. NeurIPS 2025REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning
1079. NeurIPS 2025Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
1080. NeurIPS 2025Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks
1081. NeurIPS 2025Ridge Boosting is Both Robust and Efficient
1082. NeurIPS 2025Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions
1083. NeurIPS 2025Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
1084. NeurIPS 2025Scaling Embedding Layers in Language Models
1085. NeurIPS 2025Scaling Law with Learning Rate Annealing
1086. NeurIPS 2025Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling
1087. NeurIPS 2025SDPGO: Efficient Self-Distillation Training Meets Proximal Gradient Optimization
1088. NeurIPS 2025Searching Efficient Semantic Segmentation Architectures via Dynamic Path Selection
1089. NeurIPS 2025SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling
1090. NeurIPS 2025Self-Refining Language Model Anonymizers via Adversarial Distillation
1091. NeurIPS 2025Sign-In to the Lottery: Reparameterizing Sparse Training
1092. NeurIPS 2025Simple and Efficient Heterogeneous Temporal Graph Neural Network
1093. NeurIPS 2025SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference
1094. NeurIPS 2025Smooth Regularization for Efficient Video Recognition
1095. NeurIPS 2025SparseDiT: Token Sparsification for Efficient Diffusion Transformer
1096. NeurIPS 2025Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks
1097. NeurIPS 2025Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
1098. NeurIPS 2025Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment
1099. NeurIPS 2025StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
1100. NeurIPS 2025StreamForest: Efficient Online Video Understanding with Persistent Event Memory

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.