Till Aczel

Orcid: 0009-0007-0715-5880

According to our database1, Till Aczel authored at least 15 papers between 2024 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
BitLogic: Training Framework for Gradient-Based FPGA-Native Neural Networks.
CoRR, February, 2026

GIC-DLC: Differentiable Logic Circuits for Hardware-Friendly Grayscale Image Compression.
CoRR, January, 2026

2025
Efficient Bayesian Inference from Noisy Pairwise Comparisons.
CoRR, October, 2025

Light Differentiable Logic Gate Networks.
CoRR, October, 2025

Virtual Fashion Photo-Shoots: Building a Large-Scale Garment-Lookbook Dataset.
CoRR, October, 2025

From MNIST to ImageNet: Understanding the Scalability Boundaries of Differentiable Logic Gate Networks.
CoRR, September, 2025

The Impact of Scaling Training Data on Adversarial Robustness.
CoRR, September, 2025

The Unwinnable Arms Race of AI Image Detection.
CoRR, September, 2025

Recurrent Deep Differentiable Logic Gate Networks.
CoRR, August, 2025

Keep It Real: Challenges in Attacking Compression-Based Adversarial Purification.
CoRR, August, 2025

Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks.
CoRR, June, 2025

Human Aligned Compression for Robust Models.
CoRR, April, 2025

Conditional Hallucinations for Image Compression.
Proceedings of the Data Compression Conference, 2025

2024
SUPClust: Active Learning at the Boundaries.
CoRR, 2024

Bridging Diversity and Uncertainty in Active learning with Self-Supervised Pre-Training.
CoRR, 2024


  Loading...