Explore how RL can be blended with natural language
few-shot, zero-shot, meta and in-context learning. Dive in!
Explore the key concepts of Flow Matching, its relation to diffusion models, and how it can enhance the training of generative models
Let's explore a smarter Vision-Language Model (VLM) that thinks step-by-step
core methodologies behind training machine learning models
Explore how transformers can select different depths of processing and reduce compute needs
we trace Mistral's strategic roadmap and and unpack the unique performance of les Ministraux (Ministral)
4 RL+F approaches that guide a model with targeted feedback
Explore how MLLMs can visually "think" step-by-step
Explore how OpenAI made their automatic speech recognition (ASR) model multilingual and multitasking
The recent Nobel Prizes in Chemistry and Physics were actually awarded for Deep Learning! Time to update your 'playing deck' of key ML concepts
we compare three fine-tuning methods – DoRA, QLoRA, and QDoRA – each designed to improve model performance and memory efficiency in different ways.
