←
Raphael Avalos56 posts
Raphael Avalos avatar

Raphael Avalos

@raphael_avalos

Writing the PhD thesis @aibrussels | ex Cohere and FWO Fellow

◷ Joined May 2019▧ 2 Photos and videos
Raphael Avalos avatar
Raphael Avalos@raphael_avalos·20 May 2025

Last week, I wrapped up my internship @cohere, where I had the chance to work with fantastic people on RL for LLMs. It was an amazing 6 months, and I'm excited to share one of the outcomes: ShiQ, a Q-value based RL algorithm for fine-tuning LLMs 🚀 🧵Details in @irombie's post!

Irem Ergün@irombie19 May 2025

I'm excited to share our new pre-print ShiQ: Bringing back Bellman to LLMs! arxiv.org/abs/2505.11081 In this work, we propose a new, Q-learning inspired RL algorithm for finetuning LLMs 🎉 (1/n)

Raphael Avalos avatar
Raphael Avalos@raphael_avalos·4 Jun 2025

🚀 Excited to share the 3rd outcome of my internship at @CohereAI: a new RL algo for agentic LLMs that combines policy learning and world modeling, letting agents verify actions before executing them. Check out the 🧵 and 📄! Big thanks to my co-authors and Cohere’s RL team 🙏

📢After months of work, I can finally share our latest research, couldn’t be more thrilled and excited. 🎉 We unify a policy 🤖 and a world model 🌍 into a single LLM, thus no external dynamics model needed! Why does this matter? Because now, the policy can plan based on its internal world model! And this planning boosts tool-use success rates to >90%, on top of SFT + RL. 📄: arxiv.org/abs/2506.02918 🧵[1/8]

Post attachmentPost attachment
Raphael Avalos avatar
Raphael Avalos@raphael_avalos·28 Mar 2025

Excited to share the technical report on Command R7B (7B) and Command A (111B), our flagship model! These models are the result of incredible teamwork at @cohere, and it was an honor to be part of it. Report: cohere.com/research/papers/c…

Today (two weeks after model launch 🔥) we're releasing a technical report of how we made Command A and R7B 🚀! It has detailed breakdowns of our training process, and evaluations per capability (tools, multilingual, code, reasoning, safety, enterprise, long context)🧵 1/3.

Raphael Avalos avatar
Raphael Avalos@raphael_avalos·3 Jan 2025

The X account and website for the next edition of the ALA workshop is live! Follow it to get all the updates :)

Excited to announce the 17th Adaptive Learning Agent workshop at @AAMASconf in May! We welcome full papers, work in progress, and 2-page abstracts of recently published journal papers. Find out more at our website: ala-workshop.github.io/. Deadline for submissions: February 4th.

Florent Delgrange avatar
⟳ Raphael Avalos retweeted
Florent Delgrange@f_delgrange·3 Sep 2024

Two weeks ago, I publicly defended my PhD thesis, entitled « Activating Formal Verification of Deep Reinforcement Learning Policies by Model Checking Bisimilar Latent Space Models ». 📚 The full dissertation is available here: tinyurl.com/formarl (1/n)

Post attachment