🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

o3 can't multiply beyond a few digits... But I think multiplication, addition, maze solving and easy-to-hard generalization is actually solvable on standard transformers... with recursive self-improvement. Below is the acc of a tiny model teaching itself how to add.

Our work on language model self-improvement will appear as an Oral at ICLR! See you in Singapore! x.com/canondetortuga…

🚨 New Paper 🚨 An Overview of Large Language Models for Statisticians 📝: arxiv.org/abs/2502.17814 - Dual perspectives on Statistics ➕ LLMs: Stat for LLM & LLM for Stat - Stat for LLM: How statistical methods can improve LLM uncertainty quantification, interpretability,

Akshay Krishnamurthy and Audrey Huang (Audrey Huang) have written a nice blog post on the intersection of reinforcement learning theory and language model post-training. let-all.com/blog/2025/03/0…

Very happy to share the almost-final version of our new online control book: arxiv.org/abs/2211.09619

We’ve improved 4o’s capabilities, especially for solving complex technical and coding problems!

#ICLR2025 Oral 🚨 Provably efficient RL has advanced significantly but it's still unclear if efficient algos exist for the simple setting of "Linear Bellman Completeness" We solve for the special case of deterministic state transitions using an approach we call "span argument"!🧵

Come meet Jimmy Di and talk to him about this work about Machine Unlearning right now at #ICLR2025! Hall 3 + Hall 2B #497 Friday April 25 10 AM - 12:30 PM (RIGHT NOW!)

Announcing the first workshop on Foundations of Post-Training (FoPT) at COLT 2025! 📝 Soliciting abstracts/posters exploring theoretical & practical aspects of post-training and RL with language models! │ 🗓️ Deadline: May 19, 2025

Featuring amazing speakers Csaba Szepesvari (Csaba Szepesvari), Sadhika Malladi (Sadhika Malladi), and Samy Jelassi. With co-organizers Adam Block, Dylan Foster (Dylan Foster 🐢), Audrey Huang (Audrey Huang), Akshay Krishnamurthy, and Ayush Sekhari (Ayush Sekhari (on Job Market)).

Website (& CFP/instructions): fopt-workshop.github.io Submission link: openreview.net/group?id=learn… FoPt 2025 for updates. See you in Lyon!

Submission Deadline for the first workshop on Foundations of Post-Training (FoPT) at COLT 2025 is approaching fast - May 19! Submit your best works on exploring theoretical & practical aspects of post-training and RL with language models!

x.com/Nived_Rajarama… Quick reminder post-NeurIPS: The deadline for our workshop on Foundations of Post-Training (FoPT) at COLT 2025 is coming up this Monday, May 19!

The abstract submission deadline for FoPt has been extended to the 21st of May (11:59pm UTC). Submission website: openreview.net/group?id=learn…

>700K people die each year due to S. aureus infection. Today we show that our AI designed new molecule, synthecin, stops drug-resistant S. aureus MRSA in mouse model💊 We created synthecin w/ SyntheMol-RL, our new RL generative AI. All open source biorxiv.org/content/10.110…

The Indian and global scientific community has lost a legend. I express my condolences on the demise of Prof. Jayant Vishnu Narlikar (1938–2025), founder of the Inter-University Centre for Astronomy and Astrophysics Inter-University Centre for Astronomy&Astrophysics, and co-author of the Hoyle–Narlikar theory. Prof.