🔥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

⭐️Looking for a PhD Intern⭐️ Join me this summer at MSR to work on personal AI agents! We're developing innovative models to enhance personalized MS Copilot experiences. I'm seeking candidates with strong modeling skills and experience with LLM (multi-)agents/preference learning

Our paper "Improving Instruction-Following in Language Models through Activation Steering” has been accepted to #ICLR2025! We're also excited to share that our public GitHub repo is now live. Code: github.com/microsoft/llm-… Camera-ready: arxiv.org/abs/2410.12877

openreview.net/forum?id=kNHVV… by Mazda Moayeri (and the awesome AI frontiers team at MSR) discusses how LLMs maybe useful in helping us understand how they work (04/25, 3-5:30 PM, Board #623)

Mazda Moayeri and finally, openreview.net/pdf?id=Xh6S3X3… by Natasha Butt (and the awesome AI frontiers team at MSR) discusses how to dynamically create benchmarks using multi-LLM agent interaction (at the DATA-FM workshop on 04/28). Vidhisha Balachandran will be presenting again!

In Singapore! We have an exciting set of talks and papers at #ICLR2025. Besmira Nushi 💙💛 , Vibhav and I will be around to chat about our recent inference scaling evaluation report. You can also talk to Mazda Moayeri and Alessandro Stolfo about their internship projects on model understanding.

While I'm on X to share my paper, I also have a life update I'll be joining School of Information - UT Austin as an assistant professor starting Fall 2026! Excited for this next chapter, and to keep working on teaching computers to better understand language and humans (+now teaching humans too)

🚨 Announcing Nemotron-MIND ICLR 2026 ! We’re releasing a 138B tokens synthetic pretraining dataset designed to boost LLM math reasoning. Powered by MIND, it transforms math texts into rich, dialectic dialogues. Smarter data → better models. #ICLR2025 #AI

Check out Phi-4-reasoning models!

I will be presenting 👇work at #NAACL2025 tomorrow (May 2) from 12 pm in Ballroom A. Please stop by if curious about inductive biases in transformers, generalization, and applying Bayesian models of cognition for understanding language models.

Fastino trains AI models on cheap gaming GPUs and just raised $17.5M led by Khosla | TechCrunch techcrunch.com/2025/05/07/fas…

Excited to release my first lead project Magentic-UI at Microsoft Research, an OS web agent application designed for efficient human-agent interaction. CUA agents are cool but they're not so useful yet, Magentic-UI helps us study how to get value from them. github.com/microsoft/mage…