Topic
All digests tagged Diffusion Models
Suggested route
Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.
World models are defined as real-time, action-conditioned, causal video generators. They represent a shift from traditional simulators to data-driven generative approaches, using diffusion models to create photorealistic video conditioned on text, context, and actions.
Read article
Krea 2’s training methodology reveals that data curation is everything. The talk covers advanced techniques like pHash deduplication, Sparse Autoencoders for unsupervised tagging, and multi-stage training from low to high resolution.
Read article
This session covers Diffusion Models, detailing the loss function $\mathcal{L}_{t-1}$ derived from lower bounds. It also explores Foundation Model paradigms, zero-shot learning, and parameter efficiency techniques like Low-Rank Adaptation (LoRA).
Read article
Diffusion models are generative frameworks used to generate realistic images, videos, and actions. The process involves a fixed forward noising step ($X_0 o X_T$) and a learned reverse denoising step $p_ heta(X_{t-1}|X_t)$, optimized using the Evidence Lower Bound (ELBO).
Read article
The course emphasizes understanding the mathematical foundations of ML, covering Supervised, Unsupervised, and Reinforcement Learning. A key focus is optimizing algorithms for hardware compatibility.
Read article
Xaira's X-Cell uses a 4.9B parameter diffusion model to predict cell response to unseen genetic perturbations. By training on massive causal datasets (Perturb-seq), it moves drug discovery from correlation to prediction.
Read article