The next generation of open LLMs should be inclusive, compliant, and multilingual by design. That’s why we @icepfl.bsky.social @ethz.ch @cscsch.bsky.social ) built Apertus.

EPFL School of Computer and Communication Sciences@icepfl.bsky.social · last yr.

EPFL, ETH Zurich & CSCS just released Apertus, Switzerland’s first fully open-source large language model. Trained on 15T tokens in 1,000+ languages, it’s built for transparency, responsibility & the public good. Read more: actu.epfl.ch/news/apertus...

🚀 Big time! We can finally do simple LLM RL fine-tuning with rewards and leverage offline/off-policy data! ❌ You want rewards, but GRPO only works online? ❌ You want offline, but DPO is limited to preferences? ✅ QRPO can do both! 🧵Here's how we do it:

⚡️🧠 Excited to share our recent work on long-context efficiency! We propose a new layer called RAT—fast and lightweight like RNNs, yet powerful like Attention. 🐭✨ This is the joint effort with Anunay Yadav, @razvan-pascanu.bsky.social @caglarai.bsky.social !

Excited to share our latest work on EvoTune, a novel method integrating LLM-guided evolutionary search and reinforcement learning to accelerate the discovery of algorithms! 1/12🧵

Anastasia @koloskova.bsky.social recently won the European @ellis.eu PhD award, for her amazing work on AI and optimization. She will be joining University of Zurich as a professor this summer, and hiring PhD students and postdocs. You should apply to her group! Her website: koloskova.github.io

A dream come true! I presented "No Representation, No Trust" on my favorite RL podcast, TalkRL! Make sure to check it out to learn why training with PPO for too long makes your agent collapse!

Robin Ranjit Singh Chauhan@robinchauhan.bsky.social · 2y ago

E63: NeurIPS 2024 - Posters and Hallways 1 Jiaheng Hu of UTexas on Unsupervised Skill Discovery for HRL @skandermoalla.bsky.social of EPFL: Representation and Trust in PPO Adil Zouitine of IRT Saint Exupery/Hugging Face : Time-Constrained Robust MDPs

Excited to share that the first paper of my PhD has been accepted for publication at the ISPRS Geospatial Week 2025! This dataset paper introduces a globally representative, high-resolution (10m) benchmark dataset for Above Ground Biomass estimation.

For my first post on Bluesky .. I'll start by announcing our 2025 edition of EEML which will be in Sarajevo :) ! I'm really excited about it and hope to see many of you there. Please follow the website (and Bluesky account) for more details which are coming soon ..

EEML@eemlcommunity.bsky.social · 2y ago

Hello Bluesky! 🦋 This will be the official account of the Eastern European Machine Learning (EEML) community. Follow us for news regarding our summer schools, workshops, education/community initiatives, and more!

Also, check out our ML project template—it’s a game-changer!🚀🚀 @caglarai.bsky.social 🧑‍💻 github.com/CLAIRE-Labo/...

Skander Moalla@skandermoalla.bsky.social · 2y ago

Ever been puzzled by your PPO agent collapsing out of nowhere? 📈🤯📉 Come check out our poster tomorrow! Wed 11 Dec 11 am - 2 pm PST West Ballroom A-D #6403 @caglarai.bsky.social @andreamiele.bsky.social @razvan-pascanu.bsky.social

Ever been puzzled by your PPO agent collapsing out of nowhere? 📈🤯📉 Come check out our poster tomorrow! Wed 11 Dec 11 am - 2 pm PST West Ballroom A-D #6403 @caglarai.bsky.social @andreamiele.bsky.social @razvan-pascanu.bsky.social

Caglar Gulcehre@caglarai.bsky.social · 2y ago

2. No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO, West Ballroom A-D #6403 Both are on 11 Dec, 2pm-5pm. EST. I am co-organizing the Pluralistic Alignment workshop on the 14th Dec with a fantastic line of speakers: pluralistic-alignment.github.io (2/3)