Everything I Learned Training Frontier Small Models — Maxime Labonne, Liquid AI
A new class of small models is emerging with the ability to reliably follow instructions and call tools while running on-device under 1 GB of memory. In this talk, we'll break down how to post-train frontier small models using the LFM2.5 recipe: on-policy preference alignment, agentic reinforcement learning, and curriculum training with iterative model merging. We'll cover training challenges unique to the 1B scale, like doom loops, capability interference, and how to fix them. The goal is to give you a concrete playbook to fine-tune and deploy small models for your own use cases, from structured data extraction to multi-turn tool use. Speaker info: https://x.com/maximelabonne / maxime-labonne https://github.com/mlabonne Timestamps: 0:00:00 - Start 0:00:14 - Introduction to frontier small models at Liquid AI 0:01:02 - Characteristics: memory-bound, task-specific, latency-sensitive 0:02:20 - Architecture: why large embedding layers are inefficient 0:04:01 - LFM2 architecture: using gated short convolutions for speed 0:06:09 - LFM 2.5 recipe: 28T tokens and post-training stages 0:08:34 - Post-training: SFT, preference alignment, and RL best practices 0:10:43 - Identifying "doom loops" in reasoning models 0:11:34 - Solutions: mitigating loops via preference alignment and RL 0:15:29 - Future focus: using agentic tools to overcome memory limits 0:17:58 - Q&A: real-world applications for small vs. large models

LLMs Don't Need More Parameters. They Need Loops.

How I deleted 95% of my agent skills and got better results — Nick Nisi, WorkOS

Introduction to Visual ML

LLM vs. SLM vs. FM: Choosing the Right AI Model

No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer

"Software Fundamentals Matter More Than Ever" — Matt Pocock

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

Harnesses in AI: A Deep Dive — Tejas Kumar, IBM

Yann LeCun's $1B Bet Against LLMs

Demis Hassabis: Why AGI is Bigger than the Industrial Revolution & Where Are The Bottlenecks in AI

The Multi-Agent Architecture That Actually Ships — Luke Alvoeiro, Factory

DeepSeek Gave LLMs a Real Memory (It's Not RAG)

Small vs. Large AI Models: Trade-offs & Use Cases Explained

Pinecone Just Demoted Vector Search. Here's the Knowledge Layer.

Google Maps is unreasonably fast. Let me explain

From 46% to 90%: Fine-Tuning Tiny LLMs for On-Device Agents — Cormac Brick, Google

How Anthropic Engineers ACTUALLY Prompt Claude Code

What Is Yann LeCun Cooking? JEPA Explained Simply

Gemma 4 Deep Dive — Cassidy Hardin, Researcher, Google DeepMind

