Robin Faro

Working on enhancing reasoning capabilities of LLMs | PhD Student @UniBasel under @ilijabogunovic and @AurelienLucchi | ex-@EPFL 🇨🇭 and @unict_it 🇮🇹

[Robin Faro @robinfaro13]

📄 Paper Link: https://t.co/TPAd0cN4zg

[Robin Faro @robinfaro13]

🎯 Learning is most effective at the frontier of capability: problems that are too easy or too hard teach nothing.

For LLM reasoners trained with GRPO this is literal: problems the model always or never solves give zero gradient.

We introduce Frontier Learning👇🧵

[Robin Faro @robinfaro13]

Joint work with co-first author @shyam91019594, @ilijabogunovic and @AurelienLucchi 🙌

📄 https://t.co/TPAd0cNCoO

[Robin Faro @robinfaro13]

✅ Takeaway: good training data isn't something you pick once before training. It has to keep moving with the model, toward what it can almost do. Frontier learning does exactly that, and the longer you train, the more it pays

[Robin Faro @robinfaro13]

@andreamiele_ Congrats!🚀

[Andrea Miele @andreamiele_]

DiffusionGemma is one of the first large, open-weight uniform diffusion LLMs.

But how can the community actually post-train it?

New blog 📁: what works, what breaks, and the SFT objective that wins. 🧵

[Aurelien Lucchi @AurelienLucchi]

We’re hiring! 🇨🇭
Join the University of Basel as a PhD student or postdoctoral researcher in the field of LLM training.
Work on:
🤖 LLM pre- and post-training
🎯 Reinforcement learning and reasoning
📈 Reliable generalization
⚙️ Large-scale experiments

📍 Basel, Switzerland

[Ilija Bogunovic @ilijabogunovic]

RhineAI @ ICML 2026 🇰🇷
Come find us 👇

[Ilija Bogunovic @ilijabogunovic]

Heading to ICML? Check out this RL work from my student @xiaohang_tang and collaborators on teaching diffusion language models to reason by denoising sequences. Featuring wd1, wd1++ & GDSD

[Ilija Bogunovic @ilijabogunovic]

Hiring 2 summer ML research interns at the University of Basel 🇨🇭.

Research topics: RL/diffusion LLM post-training, reasoning, or LLM orchestration. Possible fully funded PhD offers to follow.

I'll be at ICLR this week and happy to chat.
Apply: https://t.co/gOdLRv771L