Research & Publications

My research focuses on autonomous driving, computer vision, and generative AI. I work on end-to-end learning, attention mechanisms, and neural network interpretability for safety-critical systems.

📊 5 publications | 🏷️ Topics: Autonomous Driving, Computer Vision, Deep Learning, Generative Models

📚 All Publications

2024

Towards Kinetic Manipulation of the Latent Space thumbnail

Towards Kinetic Manipulation of the Latent Space

NeurIPS 2024 Creative AI Track ⭐ Featured
Diego Porres

We introduce a novel approach for manipulating the image synthesis process of generative models with a simple camera, enabling dynamic and controllable generation of content without the need of specialized hardware.

📄 PDF 📚 arXiv 💻 Code
generative AIlatent spacecomputer-visioncreativityneural-networks
At the edge of a generative cultural precipice thumbnail

At the edge of a generative cultural precipice

CVPR 2024 Workshop
Diego Porres, Alexandra Gomez-Villa

Analyzed sustainability and data scarcity challenges in training large-scale generative models and their implications for both new models and incoming artists.

📄 PDF 📚 arXiv
generative AIethicscreativitycomputer-vision
Guiding Attention in End-to-End Driving Models thumbnail

Guiding Attention in End-to-End Driving Models

IV 2024 ⭐ Featured
Diego Porres, Yi Xiao, Gabriel Villalonga, Alexandre Levy, Antonio M. López

We propose a novel method to guide attention in end-to-end driving models, improving interpretability and performance in autonomous driving tasks.

📄 PDF 📚 arXiv 💻 Code 🌐 Project
autonomous drivingcomputer-visionattention mechanismsend-to-end learning

2023

Scaling Vision-based End-to-End Driving with Multi-View Attention Learning thumbnail

Scaling Vision-based End-to-End Driving with Multi-View Attention Learning

IROS 2023 ⭐ Featured
Yi Xiao, Felipe Codevilla, Diego Porres, Antonio M. López

We present a scalable approach for vision-based end-to-end driving using multi-view attention learning, enhancing the model's ability to process and integrate information from multiple camera views.

📄 PDF 📚 arXiv 💻 Code
autonomous drivingcomputer-visionattention mechanismsend-to-end learning

2021

Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks thumbnail

Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks

NeurIPS 2021 Workshop ML4CD
Diego Porres

Call to action to repurpose GAN discriminators for novel image synthesis tasks.

📄 PDF 📚 arXiv 💻 Code
generative AIcomputer-visioncreativityneural-networks

🔬 Research Areas

Autonomous Driving Computer Vision Explainability/XAI End-to-End Learning Generative AI GANs Deep Learning 3D Vision Neural Networks

💬 Interested in collaborating? Check out my GitHub or read more on my blog.