mlsanityData to 7 Oct 2026

Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference

arXiv 2404.03085 ↗First posted 3 Apr 2024cs.HC cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

On-device machine learning (ML) moves computation from the cloud to personal devices, protecting user privacy and enabling intelligent user experiences. However, fitting models on devices with limited resources presents a major technical challenge: practitioners need to optimize models and balance hardware metrics such as model size, latency, and power. To help practitioners create efficient ML models, we designed and developed Talaria: a model visualization and optimization system. Talaria enables practitioners to compile models to hardware, interactively visualize model statistics, and simulate optimizations to test the impact on inference metrics. Since its internal deployment two years ago, we have evaluated Talaria using three methodologies: (1) a log analysis highlighting its growth of 800+ practitioners submitting 3,600+ models; (2) a usability survey with 26 users assessing the utility of 20 Talaria features; and (3) a qualitative interview with the 7 most active users about their experience using Talaria.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 42 of its 97 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

42 of 97 references.

References · 42

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  6. 2020Knowledge Distillation: A Surveycited by 1,578
  7. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  8. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  9. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 521
  10. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 407
  11. 2018Model compression via distillation and quantizationcited by 287
  12. 2019Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computingcited by 225
30 more
  1. 2019The What-If Tool: Interactive Probing of Machine Learning Modelscited by 207
  2. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
  3. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  4. 2018Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontierscited by 117
  5. 2019FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learningcited by 93
  6. 2020Benchmarking TinyML Systems: Challenges and Directioncited by 89
  7. 2019Machine Learning at the Network Edge: A Surveycited by 83
  8. 2022Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Modelscited by 70
  9. 2020How do Data Science Workers Collaborate? Roles, Workflows, and Toolscited by 64
  10. 2019On-Device Machine Learning: An Algorithms and Learning Theory Perspectivecited by 63
  11. 2021hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devicescited by 61
  12. 2019FairSight: Visual Analytics for Fairness in Decision Makingcited by 59
  13. 2022Machine Learning Model Sizes and the Parameter Gapcited by 39
  14. 2018Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutionscited by 33
  15. 2019exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Modelscited by 33
  16. 2023Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learningcited by 33
  17. 2021Dynamic Resolution Networkcited by 31
  18. 2021DKM: Differentiable K-Means Clustering Layer for Neural Network Compressioncited by 31
  19. 2020VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detectioncited by 28
  20. 2023Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiencescited by 21
  21. 2022Symphony: Composing Interactive Interfaces for Machine Learningcited by 18
  22. 2021Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labelscited by 17
  23. 2020mage: Fluid Moves Between Code and Graphical Work in Computational Notebookscited by 13
  24. 2022DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with Treemapscited by 12
  25. 2020CNNPruner: Pruning Convolutional Neural Networks with Visual Analyticscited by 11
  26. 2018Using the Jupyter Notebook as a Tool for Open Science: An Empirical Studycited by 9
  27. 2020A Visual Analytics Framework for Explaining and Diagnosing Transfer Learning Processescited by 9
  28. 2023The Role of Interactive Visualization in Explaining (Large) NLP Models: from Data to Inferencecited by 9
  29. 2019From Server-Based to Client-Based Machine Learning: A Comprehensive Surveycited by 7
  30. 2019Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time Appscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 2.

6 papers.

  1. 2024Apple Intelligence Foundation Language Modelscited by 22
  2. 2024Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationshipscited by 7
  3. 2024Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experimentscited by 4
  4. 2025RAG Without the Lag: Interactive Debugging for Retrieval-Augmented Generation Pipelinescited by 3
  5. 2026IPBC: An Interactive Projection-Based Framework for Human-in-the-Loop Semi-Supervised Clustering of High-Dimensional Datacited by 0
  6. 2026How Weight Encoding Affects Language Model Placement and Performance on the Apple Neural Enginecited by 0