If this is not why we are working on pushing AI boundaries, I don't know what is.

Ten years ago in 2015 we published a paper called End-to-End Memory Networks (arxiv.org/abs/1503.08895). Looking back, this paper had many of the ingredients of current LLMs. Our model was the first language model that completely replaced RNN with attention. It had dot-product

Google friends & ex-colleagues -- Google scholar seems pretty broken😔. Our most cited paper from last year "Self-Rewarding LLMs" has disappeared! Scholar has clustered it with another paper (SPIN) and it isn't in the search results. This is bad for PhD student & first author

the workshop is tomorrow! and it will be livestreamed at iclr.cc/virtual/2025/w… for those not in Singapore

There are still some spots in the room, but they are running low fast!

panel on decentralized training @ ICLR

Thanks to all the organizers, it was a pleasure to attend and learn from great speakers!

🎉 Excited to share that my internship work, ScPO, on self-training LLMs to improve reasoning without human labels, has been accepted to #ICML2025! Many thanks to my awesome collaborators at AI at Meta and @uncnlp🌞Looking forward to presenting ScPO in Vancouver 🇨🇦

We are hiring a PhD research intern at FAIR w/ Mark Ibrahim Kamalika Chaudhuri to start this summer or Fall! Potential topics: trustworthy and reliable LLMs, multi-modal LLMs and agents, post-training, reasoning, with a focus on open science/sharing our findings in the paper at the end

Just look at the list of the invited speakers! Submit your papers by June 23rd, we are waiting for you 🫵🏿

Our presentations are now available online!

🍿🍿🥤

Reasoning, Attention & Memory Workshop @ COLM Submission Deadline: June 23, 2025 -- Today!

Don't lose it, reuse it! Instead of filtering out bad data samples, we propose to rewrite low-quality samples for better quality.

✨MTA was accepted at #COLM2025 ✨ Since our first announcement, we have updated the paper with scaling laws, new baselines, and more evaluations! Code is now available in our repo: github.com/facebookresear… Conference on Language Modeling

Our team is hiring a postdoc in (mech) interpretability! The ideal candidate will have research experience in interpretability for text and/or image generation models and be excited about open science! Please consider applying or sharing with colleagues: metacareers.com/jobs/222395396…

After almost 10 years in AI, my most cited work is still about *underground* hidden layers

BREAKING: we've partnered with AI at Meta and Papers with Code to build a successor to Papers with Code (which was sunsetted yesterday) PWC, founded by Robert Stojnic and Ross Taylor has been an invaluable resource for AI scientists and engineers over the years (and an inspiration

...is today a good day for new paper posts? 🤖Learning to Reason for Factuality 🤖 📝: arxiv.org/abs/2508.05618 - New reward func for GRPO training of long CoTs for *factuality* - Design stops reward hacking by favoring precision, detail AND quality - Improves base model across

Huge computer science result: A Tsinghua professor JUST discovered the fastest shortest path algorithm for graphs in 40yrs. This improves on Turing award winner Tarjan’s O(m + nlogn) with Dijkstra’s, something every Computer Science student learns in college.