This month, we’re spotlighting the most essential AI topics of 2025 – the ones that keep showing up no matter where the tech goes. We’re organizing our AI 101 series recaps into three parts: 1) methods and techniques, 2) models, and 3) core concepts.

Today we’re refreshing 9 techniques from AI 101 that shaped the way we think about AI from January to June 2025. There’s a lot to explore. Happy learning! →

1. What is HtmlRAG, Multimodal RAG and Agentic RAG?

These three RAG methods do what original RAG can’t – 1) HtmlRAG works directly with HTML version of text, 2) Multimodal RAG can retrieve image information; and 3) Agentic RAG incorporates agentic capabilities in RAG technique. Here’s all about them and why they are special.

2. Everything You Need to Know about Knowledge Distillation

Proposed a decade ago, knowledge distillation is still a cornerstone technique for transferring knowledge from a larger model — the teacher, to a smaller one — the student. With this training style, smaller models become inheritors of their larger counterparts’ capabilities. Here’s a closer look at knowledge distillation, covering the main aspects you need to know.

3. The Keys to Prompt Optimization

Practical insights for more effective prompting from Isabel González that uncover the four main pillars of query optimization: expansion, decomposition, disambiguation, abstraction.

4. What is GRPO and Flow-GRPO?

DeepSeek’s Group Relative Policy Optimization (GRPO) is a twist on traditional reinforcement learning methods like PPO (Proximal Policy Optimization). It skips the critic model in the workflow, letting a model learn from its own outputs. This makes it especially efficient for using in Reasoning Models that need to solve hard math and coding tasks, and perform long Chain-of-Thought (CoT) reasoning. Also, we dive into Flow-GRPO – the implementation of GRPO in flow models.

5. What are Chain-of-Agents and Chain-of-RAG?

Chain-of-… methods and agents are defining trends of 2025, and RAG is always a hot topic. This episode highlights two fascinating advances: Google’s Chain-of-Agents (CoA) uses a structured multi-agent chain for long-context tasks, while Microsoft’s Chain-of-Retrieval-Augmented Generation (CoRAG) enables strong multi-hop reasoning via iterative retrieval. A must read in terms of current trends.

6. How to Reduce Memory Use in Reasoning Models

With the rise of Reasoning Models that outline their thought process step by step during inference, the challenge of managing memory use has become even more noticeable. Here we discuss two approaches to mitigate this:

Plus, we propose an idea of their combination.

7. Slim Attention, KArAt, and XAttention Explained – What’s Really Changing in Transformers?

These three types of attention mechanisms take the models we use daily to the next level:

In this episode we discuss all their specific features, strengths, weaknesses and future potential.

8. What is MoE 2.0? Update Your Knowledge about Mixture-of-experts

Mixture-of-Experts (MoE) is a classical approach, but it keeps evolving rapidly. Here we highlight the latest developments: Structural Mixture of Residual Experts (S’MoRE), Symbolic‑MoE that works in pure language space, eMoE, MoEShard, Speculative-MoE, and MoE-Gen. It’s a truly fresh angle on current MoE.

9. The Human Touch: How HITL is Saving AI from Itself with Synthetic Data

Explore how AI teams are using human-in-the-loop (HITL) systems to make synthetic data useful and safe. We break down how humans guide and validate the process real-world examples of how this is being implemented today.