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

91 papers, page 1 of 2

1. NeurIPS 2026MobileMoE: Scaling On-Device Mixture of Experts
2. NeurIPS 2023[Re] Numerical influence of ReLU'(0) on backpropagation
3. NeurIPS 2023[Re] On the Reproducibility of CartoonX
4. NeurIPS 2023A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction
5. NeurIPS 2023A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning
6. NeurIPS 2023A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process
7. NeurIPS 2023A Variational Perspective on High-Resolution ODEs
8. NeurIPS 2023Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism
9. NeurIPS 2023Actively Testing Your Model While It Learns: Realizing Label-Efficient Learning in Practice
10. NeurIPS 2023Adversarial Model for Offline Reinforcement Learning
11. NeurIPS 2023ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning
12. NeurIPS 2023An Empirical Investigation of the Role of Pre-training in Lifelong Learning
13. NeurIPS 2023An Empirical Study Towards Prompt-Tuning for Graph Contrastive Pre-Training in Recommendations
14. NeurIPS 2023BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking
15. NeurIPS 2023Bayesian Optimisation of Functions on Graphs
16. NeurIPS 2023Beyond Normal: On the Evaluation of Mutual Information Estimators
17. NeurIPS 2023Binary Classification with Confidence Difference
18. NeurIPS 2023CLeAR: Continual Learning on Algorithmic Reasoning for Human-like Intelligence
19. NeurIPS 2023Collaborative Learning via Prediction Consensus
20. NeurIPS 2023Convergence Analysis of Sequential Federated Learning on Heterogeneous Data
21. NeurIPS 2023Convolution Monge Mapping Normalization for learning on sleep data
22. NeurIPS 2023Cookie Consent Has Disparate Impact on Estimation Accuracy
23. NeurIPS 2023Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First
24. NeurIPS 2023Doubly-Robust Self-Training
25. NeurIPS 2023Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
26. NeurIPS 2023EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning
27. NeurIPS 2023FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
28. NeurIPS 2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
29. NeurIPS 2023HiBug: On Human-Interpretable Model Debug
30. NeurIPS 2023Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality
31. NeurIPS 2023Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills
32. NeurIPS 2023Large-Scale Distributed Learning via Private On-Device LSH
33. NeurIPS 2023Latent SDEs on Homogeneous Spaces
34. NeurIPS 2023Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation
35. NeurIPS 2023Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions
36. NeurIPS 2023Learning Provably Robust Estimators for Inverse Problems via Jittering
37. NeurIPS 2023Learning to Augment Distributions for Out-of-distribution Detection
38. NeurIPS 2023Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling
39. NeurIPS 2023Learning via Wasserstein-Based High Probability Generalisation Bounds
40. NeurIPS 2023Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
41. NeurIPS 2023May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations
42. NeurIPS 2023Mitigating the Effect of Incidental Correlations on Part-based Learning
43. NeurIPS 2023Mixed-Initiative Multiagent Apprenticeship Learning for Human Training of Robot Teams
44. NeurIPS 2023On Convergence of Polynomial Approximations to the Gaussian Mixture Entropy
45. NeurIPS 2023On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
46. NeurIPS 2023On Generalization Bounds for Projective Clustering
47. NeurIPS 2023On Imitation in Mean-field Games
48. NeurIPS 2023On kernel-based statistical learning theory in the mean field limit
49. NeurIPS 2023On Robust Streaming for Learning with Experts: Algorithms and Lower Bounds
50. NeurIPS 2023On Separate Normalization in Self-supervised Transformers

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.