I will attend the Advanced Language Processing School in Aussois 🇫🇷 and present a poster on 30/03 (Session 2) on how latent reasoning may help bridge neural and symbolic reasoning. Looking forward to the talks, discussions, and meeting peers from the field. The schedule this year looks amazing!
Our paper “Retrieval-Augmented LLM Agents: Learning to Learn from Experience” was accepted at the Workshop on Memory for LLM-Based Agentic Systems - MemAgents @ ICLR 2026, our team will be presenting it in Rio de Janeiro 🇧🇷 in April! We are also releasing it as pre-print, check here on Arxiv!
We are offering 2 internship positions in our LLM Agents team for 2026, focusing on Memory for LLM Agents. One position focuses on Prompt-based Memory and the other on Continuous Memory. We welcome applications from Master’s and PhD students. Interested in working with us next year? Apply here.
I am excited to share that I am rejoining NAVER LABS Europe as a Research Scientist. I was intern there 2 years ago. I’ll be working on exciting topics around Memory and Reasoning for LLM Agents with Vassilina Nikoulina and Stéphane Clinchant.
Our DeCRIM work on LLM self-correction was accepted to the EMNLP 2024 (see you in Miami 🇺🇸 in November!) and the System 2 Reasoning at Scale Workshop @ NeurIPS (see you in Vancouver 🇨🇦 in December!).
Happy to share I am joining Meta for Reserch Scientist Interniship on Sparse Architectures and Mixture-of-Experts for Efficient Training. I will be on the ML Ads Infra Team, in Bellevue, WA 🇺🇸.
Released a preprint on distilling multi-task speech models with language-specific experts, enabling efficient multilingual ASR. View the paper.