Sharing some free, useful resources for you. In this collection, we’ve gathered books and surveys that can be your perfect guides to the major fields and technique. Hope this really helps you master AI and machine learning and fill in any gaps in your knowledge!
Machine Learning Systems by Vijay Janapa Reddi → Read more
Provides a framework for building effective ML solutions, covering data engineering, optimization, hardware-aware training, inference acceleration, architecture choice, and other key principles.
Understanding Deep Learning by Simon J.D. Prince → Read more
Explores core deep learning concepts: models, training, evaluation, RL, architectures for images, text and graphs, addressing open theoretical questions.
Interpretable Machine Learning by Christoph Molnar → Read more
A practical guide to simple, transparent models (e.g. decision trees) and model-agnostic methods like LIME, Shapley values, permutation importance, and accumulated local effects.
Foundations of Large Language Models by Tong Xiao and Jingbo Zhu → Read more
Many recommend this 270-page book as a good resource to focus on fundamental concepts, such as pre-training, generative models, prompting, alignment, and inference.
A Survey on Post-training of Large Language Models → Read more
Read this to master policy optimization (RLHF, DPO, GRPO), supervised and parameter-efficient fine-tuning, reasoning, integration, and adaptation techniques.
A Survey of Generative Categories and Techniques in Multimodal Generative Models → Read more
Covers multimodal models, exploring six generative modalities, key techniques (SSL, RLHF, CoT), architectural trends, and challenges.
Context Engineering 2.0: The Context of Context Engineering → Read more
Explores context engineering – how AI understands human situations and goals – and traces its roots from early human–computer interaction to modern agents, and outlines key ideas and future directions.
Agentic Large Language Models, a survey → Read more
Explains agentic LLMs across reasoning, tools and multi-agent collaboration, highlighting their synergy. It also explores their promise, risks and applications in medicine, finance, science, etc.
Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges → Read more
Explores unified geometric principles to analyze neural networks' architectures: CNNs, RNNs, GNNs, Transformers, and guide the design of the future ones.
Mathematical Foundations of Geometric Deep Learning by Haitz Saez de Ocariz Borde and Michael Bronstein → Read more
Dives into the the key math concepts behind geometric Deep Learning: geometric and analytical structures, vector calculus, differential geometry and others.