Upgrading and Customising Open Models: A workshop with Together AI x Black Forest Labs

​Together AI is organising our first workshop in London, inviting everyone excited about model customization and adaptation!

Join Max Ryabinin, VP Research & Development at Together AI, and Stephen Batifol, Developer Advocate at Black Forest Labs, for research talks ranging from RL with LLMs without verifiers to LoRA fine-tuning in diffusion-based image models.

​​At the workshop, you will learn more about:

​Talk 1 (Max Ryabinin): Escaping the Verifier: Learning to Reason via Demonstrations

• ​Leveraging Inverse RL to train reasoning language models

• ​Jointly optimizing the critic and the policy through an adversarial game

• ​How to stabilize adversarial RL with a relativistic objective

• ​Strong empirical gains on both non-verifiable and verifiable benchmarks

​Talk 2 (Stephen Batifol): LoRA for diffusion image models

• ​How LoRA behaves in diffusion models

• ​Choosing effective LoRA hyperparameters for images and how they impact visual quality vs. overfitting

• ​Data strategies for high‑quality image LoRAs and diagnosing common failure modes
  

​Agenda:

​​18:00–18:15 Welcome reception

​​18:15–19:15 Escaping the Verifier: Learning to Reason via Demonstrations

​​19:30–20:30 LoRA for diffusion image models

​20:30–Close Networking

​⚠️ Note - Only company (non-Gmail etc.) emails will be accepted. Please provide your valid corporate email upon registration