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 4 of 4

151. NeurIPS 2025Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks
152. NeurIPS 2025Ridge Boosting is Both Robust and Efficient
153. NeurIPS 2025Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions
154. NeurIPS 2025Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
155. NeurIPS 2025Scaling Embedding Layers in Language Models
156. NeurIPS 2025Scaling Law with Learning Rate Annealing
157. NeurIPS 2025Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling
158. NeurIPS 2025SDPGO: Efficient Self-Distillation Training Meets Proximal Gradient Optimization
159. NeurIPS 2025Searching Efficient Semantic Segmentation Architectures via Dynamic Path Selection
160. NeurIPS 2025SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling
161. NeurIPS 2025Self-Refining Language Model Anonymizers via Adversarial Distillation
162. NeurIPS 2025Sign-In to the Lottery: Reparameterizing Sparse Training
163. NeurIPS 2025Simple and Efficient Heterogeneous Temporal Graph Neural Network
164. NeurIPS 2025SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference
165. NeurIPS 2025Smooth Regularization for Efficient Video Recognition
166. NeurIPS 2025SparseDiT: Token Sparsification for Efficient Diffusion Transformer
167. NeurIPS 2025Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks
168. NeurIPS 2025Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
169. NeurIPS 2025Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment
170. NeurIPS 2025StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
171. NeurIPS 2025StreamForest: Efficient Online Video Understanding with Persistent Event Memory
172. NeurIPS 2025Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models
173. NeurIPS 2025Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism
174. NeurIPS 2025SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training
175. NeurIPS 2025SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
176. NeurIPS 2025Superposition Yields Robust Neural Scaling
177. NeurIPS 2025SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning
178. NeurIPS 2025Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
179. NeurIPS 2025Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error
180. NeurIPS 2025Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context
181. NeurIPS 2025The Omni-Expert: A Computationally Efficient Approach to Achieve a Mixture of Experts in a Single Expert Model
182. NeurIPS 2025Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
183. NeurIPS 2025Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few
184. NeurIPS 2025TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model
185. NeurIPS 2025UMoE: Unifying Attention and FFN with Shared Experts
186. NeurIPS 2025Unified Scaling Laws for Compressed Representations
187. NeurIPS 2025V2V: Scaling Event-Based Vision through Efficient Video-to-Voxel Simulation
188. NeurIPS 2025Venus-MAXWELL: Efficient Learning of Protein-Mutation Stability Landscapes using Protein Language Models
189. NeurIPS 2025Zebra-Llama: Towards Extremely Efficient Hybrid Models
190. NeurIPS 2025ZeroS: Zero‑Sum Linear Attention for Efficient Transformers

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.