stellar lineup at ICLR 2026 world models workshop

Heading to ICLR 2026 .... interested in LLM Reasoning or LLMs for Reward Design in RL, come drop by our posters. 1. REvolve: rishihazra.github.io/REvolve/ 2. Can LLMs Reason? @ Workshop on Reasoning and Planning for Large Language Models arxiv.org/pdf/2504.03930 #ICLR2025 #RL #LLMs

We developed a library to make logical reasoning embarrassingly parallel on the GPU. For those at ICLR 🇸🇬: you can get the juicy details tomorrow (poster #414 at 15:00). Hope to see you there!

Happening now in Garnet 214-215! Join us to for a day packed with great posters, contributed talks, and unique perspectives on self-improvement from our fantastic speakers and panelists Ida Momennejad noahdgoodman Minjoon Seo Shunyu Yao Ulyana Piterbarg Jaehun Jung

It's important to properly define problem complexity, like we did in our paper x.com/RishiHazra95/s…. Seems Apple did not do their due diligence while writing.

Better Agents = Smarter Search Algorithms + Improved Operators + Precise Evaluation + Robust Infrastructure. For, even the best F1 driver can't win without a great car! Great to see my PhD research on LLMs + Search come together in this amazing paper! #LLM #Search #AI

Kicking off my Postdoc at FAIR, AI at Meta London with the AI Research Agents team and Yoram Bachrach! Big things coming 🤖✨

Appears to be a breakthrough result but no mention of Nagarajan (Vaishnavh Nagarajan ) and his insight into pitfalls of next token prediction. arxiv.org/abs/2508.08222