Tagged “kl-divergence”

2 posts.

All Model Architecture20 Training & Alignment22 Inference & Serving21 Agents & Orchestration11 Reasoning & Evaluation27 Safety, Security & Governance8 Platforms & Practice22

Training & Alignment 25 min

The Four Faces of KL Divergence: Mode-Seeking, Mode-Covering, and Why Your Estimator Went Negative

You add a KL penalty to an RLHF objective, log it, and it prints minus 0.03. KL divergence is provably non-negative, and nothing is broken. One formula does four different jobs in modern machine learning, and almost every confusi…

math information-theory kl-divergence rlhf ∑ ◫

Model Architecture 24 min

Why GANs Lost Image Generation, and Why Adversarial Losses Are Everywhere Anyway

In 2021 a diffusion model beat BigGAN-deep on ImageNet while nearly doubling its recall, and GANs stopped being the default way to generate images. Yet latent autoencoders, SDXL-Turbo, HiFi-GAN and the neural audio codecs behind …

adversarial-generative-models gans image-generation diffusion-models ∑ ◫