#CIFAR-1011/01/2026
Demonstrating Targeted Data Poisoning with PyTorch
Learn to execute data poisoning attacks on CIFAR-10 through label flipping.
FILTER MODE ACTIVE
#CIFAR-10
Records found: 3
#CIFAR-1011/10/2025
Master Self-Supervised Learning with Lightly: SimCLR, Coresets and Active Learning in Colab
'Step-by-step Colab tutorial showing how to train a SimCLR model with Lightly, visualize embeddings, select informative coresets and evaluate transfer performance with a linear probe.'
#CIFAR-1021/06/2025
Generalization in Flow Matching Models Driven by Velocity Field Approximation, Not Noise
New research reveals that generalization in flow matching models emerges from the neural network's approximation of velocity fields during early trajectories, challenging the belief that stochasticity drives this process.