Picture for José Cano

José Cano

Quantitative Analysis of Deeply Quantized Tiny Neural Networks Robust to Adversarial Attacks

Add code
Mar 12, 2025
Viaarxiv icon

Exploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNs

Add code
Mar 12, 2025
Viaarxiv icon

Biases in Edge Language Models: Detection, Analysis, and Mitigation

Add code
Feb 17, 2025
Viaarxiv icon

DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations

Add code
Dec 12, 2024
Viaarxiv icon

Accelerating PoT Quantization on Edge Devices

Add code
Sep 30, 2024
Figure 1 for Accelerating PoT Quantization on Edge Devices
Figure 2 for Accelerating PoT Quantization on Edge Devices
Figure 3 for Accelerating PoT Quantization on Edge Devices
Figure 4 for Accelerating PoT Quantization on Edge Devices
Viaarxiv icon

Designing Efficient LLM Accelerators for Edge Devices

Add code
Aug 01, 2024
Figure 1 for Designing Efficient LLM Accelerators for Edge Devices
Figure 2 for Designing Efficient LLM Accelerators for Edge Devices
Figure 3 for Designing Efficient LLM Accelerators for Edge Devices
Viaarxiv icon

Fix-Con: Automatic Fault Localization and Repair of Deep Learning Model Conversions

Add code
Dec 22, 2023
Viaarxiv icon

DLAS: An Exploration and Assessment of the Deep Learning Acceleration Stack

Add code
Nov 15, 2023
Viaarxiv icon

MutateNN: Mutation Testing of Image Recognition Models Deployed on Hardware Accelerators

Add code
Jun 21, 2023
Viaarxiv icon

Fault Localization for Framework Conversions of Image Recognition Models

Add code
Jun 10, 2023
Figure 1 for Fault Localization for Framework Conversions of Image Recognition Models
Figure 2 for Fault Localization for Framework Conversions of Image Recognition Models
Figure 3 for Fault Localization for Framework Conversions of Image Recognition Models
Figure 4 for Fault Localization for Framework Conversions of Image Recognition Models
Viaarxiv icon