On-Device Learning papers, 2023–2026

Key findings

• On-Device Learning fell from 122 papers in 2023 to 6 in 2026, so interest is cooling.
• NeurIPS publishes the most On-Device Learning work: 91 papers from 2023 to 2026, 68% of the four-venue total.
• Among the 5 topics under Edge and IoT, it ranks #4 by 2026 paper count; the fastest grower in the group, Sensor Fusion, is up 3.8x versus 0.0x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026MobileMoE: Scaling On-Device Mixture of Experts
• ICML 2026Lower Bounds for Frank-Wolfe on Strongly Convex Sets
• CVPR 2026DeDelayed Deleting Remote Inference Delay via On-Device Correction
• ICLR 2025Robust Function-Calling for On-Device Language Model via Function Masking
• CVPR 2025EdgeTAM: On-Device Track Anything Model
• ICML 2024MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
• CVPR 2024Device-Wise Federated Network Pruning
• NeurIPS 2023[Re] Numerical influence of ReLU'(0) on backpropagation
• ICML 2023Adversarial Collaborative Learning on Non-IID Features
• CVPR 2023Efficient On-Device Training via Gradient Filtering
• ICML 2026On the Fragility of Data Attribution When Learning Is Distributed
• CVPR 2026Mobile-VTON High-Fidelity On-Device Virtual Try-On
• ICML 2024On Online Experimentation without Device Identifiers
• CVPR 2024Cloud-Device Collaborative Learning for Multimodal Large Language Models
• NeurIPS 2023[Re] On the Reproducibility of CartoonX
• ICML 2023FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization
• CVPR 2023TMO: Textured Mesh Acquisition of Objects With a Mobile Device by Using Differentiable Rendering
• ICML 2026Efficient Preference Poisoning Attack on Offline RLHF
• NeurIPS 2023A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning
• ICML 2023Towards Robust Graph Incremental Learning on Evolving Graphs

All On-Device Learning papers

134 papers, page 3 of 3

101. NeurIPS 2023On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms
102. NeurIPS 2023On the Exploitability of Instruction Tuning
103. NeurIPS 2023On the Gini-impurity Preservation For Privacy Random Forests
104. NeurIPS 2023On the Importance of Feature Separability in Predicting Out-Of-Distribution Error
105. NeurIPS 2023On the Learnability of Multilabel Ranking
106. NeurIPS 2023On the Minimax Regret for Online Learning with Feedback Graphs
107. NeurIPS 2023On the Overlooked Structure of Stochastic Gradients
108. NeurIPS 2023On the Pareto Front of Multilingual Neural Machine Translation
109. NeurIPS 2023On the Robustness of Removal-Based Feature Attributions
110. NeurIPS 2023On the Role of Entanglement and Statistics in Learning
111. NeurIPS 2023On the Sublinear Regret of GP-UCB
112. NeurIPS 2023On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training
113. NeurIPS 2023On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks
114. NeurIPS 2023Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
115. NeurIPS 2023Posterior Contraction Rates for Matérn Gaussian Processes on Riemannian Manifolds
116. NeurIPS 2023Prioritizing Samples in Reinforcement Learning with Reducible Loss
117. NeurIPS 2023Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs
118. NeurIPS 2023Provable Training for Graph Contrastive Learning
119. NeurIPS 2023RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks
120. NeurIPS 2023ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
121. NeurIPS 2023Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation
122. NeurIPS 2023Self-Adaptive Motion Tracking against On-body Displacement of Flexible Sensors
123. NeurIPS 2023SoTTA: Robust Test-Time Adaptation on Noisy Data Streams
124. NeurIPS 2023State Regularized Policy Optimization on Data with Dynamics Shift
125. NeurIPS 2023Structure Learning with Adaptive Random Neighborhood Informed MCMC
126. NeurIPS 2023Students Parrot Their Teachers: Membership Inference on Model Distillation
127. NeurIPS 2023Tempo Adaptation in Non-stationary Reinforcement Learning
128. NeurIPS 2023Tight Risk Bounds for Gradient Descent on Separable Data
129. NeurIPS 2023Time Series Kernels based on Nonlinear Vector AutoRegressive Delay Embeddings
130. NeurIPS 2023To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning
131. NeurIPS 2023Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression
132. NeurIPS 2023Towards Semi-Structured Automatic ICD Coding via Tree-based Contrastive Learning
133. NeurIPS 2023Training on Foveated Images Improves Robustness to Adversarial Attacks
134. NeurIPS 2023Unlocking Deterministic Robustness Certification on ImageNet

FAQ

How many On-Device Learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

134 in total: 122 in 2023, 4 in 2024, 2 in 2025, 6 in 2026.

How many On-Device Learning papers are at NeurIPS 2026?

NeurIPS 2026 has 1 On-Device Learning papers.

How many On-Device Learning papers are at ICLR 2025?

ICLR 2025 has 1 On-Device Learning papers.

How many On-Device Learning papers are at ICML 2026?

ICML 2026 has 3 On-Device Learning papers.

How many On-Device Learning papers are at CVPR 2026?

CVPR 2026 has 2 On-Device Learning papers, versus 1 the year before.

Which conference publishes the most On-Device Learning papers?

NeurIPS, with 91 papers from 2023 to 2026.