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

190 papers, page 3 of 4

101. NeurIPS 2025Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing
102. NeurIPS 2025Improved Scaling Laws in Linear Regression via Data Reuse
103. NeurIPS 2025Improving Decision Trees through the Lens of Parameterized Local Search
104. NeurIPS 2025InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
105. NeurIPS 2025Interpretable and Parameter Efficient Graph Neural Additive Models with Random Fourier Features
106. NeurIPS 2025Irrational Complex Rotations Empower Low-bit Optimizers
107. NeurIPS 2025Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
108. NeurIPS 2025Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
109. NeurIPS 2025Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation
110. NeurIPS 2025Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning
111. NeurIPS 2025LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language Models
112. NeurIPS 2025Learned Prefix Caching for Efficient LLM Inference
113. NeurIPS 2025Learning in Compact Spaces with Approximately Normalized Transformer
114. NeurIPS 2025Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws
115. NeurIPS 2025Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
116. NeurIPS 2025Linear Attention for Efficient Bidirectional Sequence Modeling
117. NeurIPS 2025LLM at Network Edge: A Layer-wise Efficient Federated Fine-tuning Approach
118. NeurIPS 2025LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision
119. NeurIPS 2025LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
120. NeurIPS 2025Mamba Modulation: On the Length Generalization of Mamba Models
121. NeurIPS 2025Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection
122. NeurIPS 2025Memory-Efficient Training with In-Place FFT Implementation
123. NeurIPS 2025Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression
124. NeurIPS 2025Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks
125. NeurIPS 2025Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training
126. NeurIPS 2025MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
127. NeurIPS 2025Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures
128. NeurIPS 2025Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
129. NeurIPS 2025Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE
130. NeurIPS 2025Oracle-Efficient Combinatorial Semi-Bandits
131. NeurIPS 2025Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables
132. NeurIPS 2025Parallel Scaling Law for Language Models
133. NeurIPS 2025ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
134. NeurIPS 2025Pay Attention to Small Weights
135. NeurIPS 2025Position: AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
136. NeurIPS 2025Power Lines: Scaling laws for weight decay and batch size in LLM pre-training
137. NeurIPS 2025PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectors
138. NeurIPS 2025Predictable Scale (Part II) --- Farseer: A Refined Scaling Law in LLMs
139. NeurIPS 2025Private Statistical Estimation via Truncation
140. NeurIPS 2025Private Training Large-scale Models with Efficient DP-SGD
141. NeurIPS 2025Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths
142. NeurIPS 2025PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning
143. NeurIPS 2025Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment
144. NeurIPS 2025Quadratic Coreset Selection: Certifying and Reconciling Sequence and Token Mining for Efficient Instruction Tuning
145. NeurIPS 2025Random Search Neural Networks for Efficient and Expressive Graph Learning
146. NeurIPS 2025RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation
147. NeurIPS 2025RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget
148. NeurIPS 2025REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders
149. NeurIPS 2025REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning
150. NeurIPS 2025Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling

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.