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

169 papers, page 3 of 4

101. ICML 2026MV-FGAD: Towards Efficient and Effective Federated Graph Anomaly Detection via Multi-view Learning
102. ICML 2026NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models
103. ICML 2026No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
104. ICML 2026No Retraining at Edge: Efficient Resource-Aware Mixed-Precision Quantization via Federated Supernet Learning
105. ICML 2026NorMuon: Making Muon more efficient and scalable
106. ICML 2026OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
107. ICML 2026Obliviate: Efficient Unlearning in Recommender Systems
108. ICML 2026OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale
109. ICML 2026OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
110. ICML 2026On Efficient Scaling of GNNs via IO-Aware Layers Implementations
111. ICML 2026On the Origin of Neural Scaling Laws: from Random Graphs to Natural Language
112. ICML 2026Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
113. ICML 2026Optimal Splitting of Language Models from Mixtures to Specialized Domains
114. ICML 2026OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
115. ICML 2026Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing
116. ICML 2026Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
117. ICML 2026Path-conditioned training: a principled way to rescale ReLU neural networks
118. ICML 2026PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency
119. ICML 2026PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning
120. ICML 2026Platonic Transformers: A Solid Choice For Equivariance
121. ICML 2026PLoRA: Efficient Concurrent LoRA Training for Large Language Models
122. ICML 2026POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
123. ICML 2026PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training
124. ICML 2026Pseudo-Mallows for Efficient Probabilistic Preference Learning
125. ICML 2026PsumQuant: In-line Post-training Partial Sum Quantizer for Energy Efficient NPU Inference
126. ICML 2026PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference
127. ICML 2026Query-efficient model evaluation using cached responses
128. ICML 2026Random Scaling of Emergent Capabilities
129. ICML 2026Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization
130. ICML 2026ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation
131. ICML 2026Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle
132. ICML 2026Revealing Scaling Paradox in Large-scale Time Series Models: Implications for More Efficient and Accurate Forecasting
133. ICML 2026Revisiting Efficiency–Accuracy Scaling in Mixture-of-Experts Architectures
134. ICML 2026RSA-CP: Efficient Conformal Prediction in Small-Sample Regimes via Random Score Alignment
135. ICML 2026Scaling Laws and Architectural Frontiers in Metagenomic Foundation Models
136. ICML 2026Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM Inference
137. ICML 2026Select to Think: Unlocking SLM Potential with Local Sufficiency
138. ICML 2026Selective Deferred Routing: Enabling Cost-Efficient Collaboration between Local SLMs and Remote LLMs
139. ICML 2026Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching
140. ICML 2026Sequential Group Composition: A Window into the Mechanics of Deep Learning
141. ICML 2026Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws
142. ICML 2026Skip-It? Theoretical Conditions for Layer Skipping in Vision–Language Models
143. ICML 2026SLIM: Secure and Efficient Inference for Large Language Models on Untrusted Devices via TEEs
144. ICML 2026Sparser, Faster, Lighter Transformer Language Models
145. ICML 2026SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot
146. ICML 2026Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
147. ICML 2026SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
148. ICML 2026Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
149. ICML 2026Spik4lite: Refactoring Neuromorphic Sparsity for Efficient Spiking Neural Networks on Commodity Edge Devices
150. ICML 2026SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space

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.