Excited to share that I’ve been working on scaling up diffusion language models at Inception. A new generation of LLMs with unprecedented capabilities is coming!

Can't wait to see everyone at ICLR and NAACL! Check out some of our awesome papers. Come and say hi, we'd love to have a chat :)

Amazing work from my colleagues Imperial NLP

MBZUAI with 4 awards at NAACL'2025: Best Theme paper award, Outstanding paper award, SAC award for the Special theme, and SAC award for Resources and Evaluation. hashtag#NAACL2025

🚨One (more!) fully-funded PhD position in our group at Imperial College London – Privacy & Machine Learning 🔐🤖 starting Oct 2025 Plz RT 🔄

Thanks Choi Dong Hee (far left in picture) for your great presentation on your last day here at Imperial! Been brilliant having you here, and looking forward to following your work in the future :)

Thrilled to share our new preprint on Reinforcement Learning for Reverse Engineering (RLRE) 🚀 We demonstrate that human preferences can be reverse engineered effectively by pipelining LLMs to optimise upstream preambles via reinforcement learning 🧵⬇️

We have a new paper up on arXiv! 🥳🪇 The paper tries to improve the robustness of closed-source LLMs fine-tuned on NLI, assuming a realistic training budget of 10k training examples. Here's a 60 second rundown of what we found!

For trying to understanding LMs deeply, EleutherAI’s Pythia has been an invaluable resource: 16 LMs (70M to 12B parameters) trained on the same data (The Pile) in the same order, with intermediate checkpoints. It’s been two years and it’s time for a refresh.

🧵 1/8 The Illusion of Thinking: Are reasoning models like o1/o3, DeepSeek-R1, and Claude 3.7 Sonnet really "thinking"? 🤔 Or are they just throwing more compute towards pattern matching? The new Large Reasoning Models (LRMs) show promising gains on math and coding benchmarks,

ACL is almost here 🎉 Our Imperial NLP community will be presenting several papers at the conference next week. We look forward to seeing everyone in Vienna!

MBZUAI is represented at ACL 2025 in Vienna with 66 papers: 39 Main, 25 Findings, 1 TACL, 1 Demo. Talk to us about faculty and postdoc opportunities (15 of our 18 NLP faculty and several students and postdocs are here). #ACL #ACL2025 #NLProc #MBZUAI

Party time 💃🏼 come and join me this morning 🇦🇹

This week we will be presenting our work at #ACL2025. StateAct is like ReAct but better ;) Shunyu Yao We discovered that if you enhance the Agent with “self-prompting” and “state-tracking” you get greater long-range reasoning performance for free. arxiv.org/abs/2410.02810

I read the first 4 books extensively during my PhD, highly recommended 👍 I'd also highlight the 5th book as my first read re deep learning. Mind-blowing for a young math undergrad (me) at the time, made me decide to go for ML

Massive congrats to Shamsuddeen Hassan Muhammad, PhD 👏

We have released #AgentCoMa, an agentic reasoning benchmark where each task requires a mix of commonsense and math to be solved 🧐 LLM agents performing real-world tasks should be able to combine these different types of reasoning, but are they fit for the job? 🤔 🧵⬇️

✨ Accepted as a Spotlight at #NeurIPS2025! Huge thanks to my coauthors and everyone who supported us. Check out the details below 👇