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

122 papers, page 2 of 3

51. NeurIPS 2023Convergence Analysis of Sequential Federated Learning on Heterogeneous Data
52. NeurIPS 2023Convolution Monge Mapping Normalization for learning on sleep data
53. NeurIPS 2023Cookie Consent Has Disparate Impact on Estimation Accuracy
54. NeurIPS 2023Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First
55. NeurIPS 2023Doubly-Robust Self-Training
56. NeurIPS 2023Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
57. NeurIPS 2023EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning
58. NeurIPS 2023FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
59. NeurIPS 2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
60. NeurIPS 2023HiBug: On Human-Interpretable Model Debug
61. NeurIPS 2023Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality
62. NeurIPS 2023Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills
63. NeurIPS 2023Large-Scale Distributed Learning via Private On-Device LSH
64. NeurIPS 2023Latent SDEs on Homogeneous Spaces
65. NeurIPS 2023Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation
66. NeurIPS 2023Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions
67. NeurIPS 2023Learning Provably Robust Estimators for Inverse Problems via Jittering
68. NeurIPS 2023Learning to Augment Distributions for Out-of-distribution Detection
69. NeurIPS 2023Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling
70. NeurIPS 2023Learning via Wasserstein-Based High Probability Generalisation Bounds
71. NeurIPS 2023Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
72. NeurIPS 2023May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations
73. NeurIPS 2023Mitigating the Effect of Incidental Correlations on Part-based Learning
74. NeurIPS 2023Mixed-Initiative Multiagent Apprenticeship Learning for Human Training of Robot Teams
75. NeurIPS 2023On Convergence of Polynomial Approximations to the Gaussian Mixture Entropy
76. NeurIPS 2023On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
77. NeurIPS 2023On Generalization Bounds for Projective Clustering
78. NeurIPS 2023On Imitation in Mean-field Games
79. NeurIPS 2023On kernel-based statistical learning theory in the mean field limit
80. NeurIPS 2023On Robust Streaming for Learning with Experts: Algorithms and Lower Bounds
81. NeurIPS 2023On Separate Normalization in Self-supervised Transformers
82. NeurIPS 2023On Slicing Optimality for Mutual Information
83. NeurIPS 2023On student-teacher deviations in distillation: does it pay to disobey?
84. NeurIPS 2023On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay
85. NeurIPS 2023On the Convergence of Black-Box Variational Inference
86. NeurIPS 2023On the Convergence of CART under Sufficient Impurity Decrease Condition
87. NeurIPS 2023On the Convergence of Encoder-only Shallow Transformers
88. NeurIPS 2023On the Convergence of No-Regret Learning Dynamics in Time-Varying Games
89. NeurIPS 2023On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms
90. NeurIPS 2023On the Exploitability of Instruction Tuning
91. NeurIPS 2023On the Gini-impurity Preservation For Privacy Random Forests
92. NeurIPS 2023On the Importance of Feature Separability in Predicting Out-Of-Distribution Error
93. NeurIPS 2023On the Learnability of Multilabel Ranking
94. NeurIPS 2023On the Minimax Regret for Online Learning with Feedback Graphs
95. NeurIPS 2023On the Overlooked Structure of Stochastic Gradients
96. NeurIPS 2023On the Pareto Front of Multilingual Neural Machine Translation
97. NeurIPS 2023On the Robustness of Removal-Based Feature Attributions
98. NeurIPS 2023On the Role of Entanglement and Statistics in Learning
99. NeurIPS 2023On the Sublinear Regret of GP-UCB
100. NeurIPS 2023On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training

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.