Uniform sampling hampers offline RL. How to fix it? Check our paper at #NeurIPS2023. Time: Wed 13 Dec 5 p.m. CST — 7 p.m. CST Location: Great Hall & Hall B1+B2 (level 1) #1908 Paper: openreview.net/forum?id=TW99H… Code: github.com/Improbable-AI/…

Interested in learning how generative models can help with constrained design generation and topology optimization? Come to poster 540, 10:45am session today neurips.cc/virtual/2023/p… where Giorgio Giannone will be presenting our work on aligning TO with diffusion models #NeurIPS23

❤️ #NeurIPS2023. After 4 years, met my adviser and my adviser's advisor at the same time.

New work on automated red-teaming in LLMs using curiosity-driven exploration! #iclr24

New work from MIT-IBM Watson AI Lab researchers on large scale alignment of LLMs. Check out the models at HF huggingface.co/ibm/merlinite-…

Check out our work titled "From Automation to Augmentation: Redefining Engineering Design and Manufacturing in the Age of NextGen-AI", where we highlight the requirements for NextGenAI suitable for design, engineering, and manufacturing. mit-genai.pubpub.org/pub/9s6690gd/r…

Attending #ICLR2024, interested in continual learning and like probabilistic modeling? Lazar from the MIT-IBM Watson AI Lab, will be presenting our latest work that takes a probabilistic approach to modular continual learning on Tuesday, 7 May, Halle B #222 (iclr.cc/virtual/2024/p…).

Excited to give a talk on our hottest, newest work “Value Augmented Sampling for Language Model Alignment and Personalization” at 2:30p Halle A3 in #ICLR2024 Reliable and Responsible Foundation Models Workshop 🥳🥳

🚀 Stronger, simpler, and better! 🚀 Introducing Value Augmented Sampling (VAS) - our new algorithm for LLM alignment and personalization that outperforms existing methods!

What will a foundation model for the brain look like? We argue that it must be able to solve a diverse set of tasks across multiple brain regions and animals. Check out our preprint where we introduce a multi-region, multi-animal, multi-task model (MtM): arxiv.org/abs/2407.14668

Neural activity is correlated among animals performing the same task and across sequential trials. Led by Yizi Zhang and @hl3616, we develop an reduced-rank model that exploits shared structure across animals to improve neural decoding. biorxiv.org/content/10.110…

🧩 Why do task vectors exist in pretrained LLMs? Our new research uncovers how transformers form internal abstractions and the mechanisms behind in-context learning(ICL).

Excited to share our latest work with Isha Puri et al.! 🚀 We introduce a probabilistic inference approach for inference-time scaling of LLMs using particle-based Monte Carlo methods—achieving 4–16x better scaling on math reasoning tasks and O1-level performance on MATH500.

Come along and help us build reasoning in small LLMs

had a great time giving a talk about probabilistic inference scaling and the power of small models at the IBM Research ML Seminar Series - the best talks end with tons of questions, and it was great to see everyone so engaged : ) youtube.com/watch?v=--3rsQ…

Excited to share our preliminary work on customizing reasoning models using Red Hat AI Innovation’s Synthetic Data Generation (SDG) package! 📄 Turn your documents into training data for LLMs. 🧵👇

SQuat: KV-Cache for making reasoning models go 🚀 📄paper: lnkd.in/emKhAVZu 💻 code: lnkd.in/e8TJ7N3R From my awesome collaborators Red Hat AI

🚀 How is generative AI transforming the way we design cars, planes, and entire systems? In Ep 2 of No Math AI, Isha Puri and I chat with Dr. Faez Ahmed (Massachusetts Institute of Technology (MIT) DeCoDE Lab) about how AI boosts creativity, cuts design time, and works with engineers—not against them.

What does it take to scale AI beyond the lab? At #RedHatSummit, Isha Puri and I spoke with Red Hat CEO Matt Hicks & CTO Chris Wright on inference-time scaling, open infra (LLMD), and making AI affordable for enterprise. 🎧 youtu.be/mj1dwrPfvb4 #NoMathAI Red Hat AI