Want to scale RL with your shiny new GPU? 🚀 In our ICML24 Oral we find that RL algorithms hit a barrier when data is scaled up. Our new algorithm, SAPG, proposes a simple fix. It scales to 25k envs and solves hard tasks where PPO makes no progress. sapg-rl.github.io 1/n

(1/6) Recommender systems shape our digital experiences, filtering much of what we see online. But how should we measure their influence? We provide a unified causal framework to think through this question and develop metrics to audit recommender systems. arxiv.org/abs/2409.13210

Specialized Foundation Models Struggle to Beat Traditional Supervised Learning Baselines 1. This study provides a rigorous comparison between specialized foundation models (FMs) and traditional supervised learning approaches, revealing that well-tuned CNNs and simple

SCiPS-QA now live at - huggingface.co/datasets/zorps…

Turns out that strong baselines still matter in 2024! While there have been a TON of specialized FMs introduced recently, we show that leading FMs in genomics, satellite imaging, and time series are generally no better (and often worse than) much simpler supervised baselines!

📉Time Series FMs hold promise, but still struggle to outperform well-tuned statistical baselines👇 We need better evals, and more research to unlock their full potential🧠. Let's makes today's TSFMs the dumbest we'll every have!📈

Which model is best for coding? Copilot Arena leaderboard is out! Our code completions leaderboard contains data collected over the last month, with >100K completions served and >10K votes! Let’s discuss our findings so far🧵

wake up babe, new AI term just dropped

🧵1/ Introducing ScribeAgent 🤖! Using extensive 𝗿𝗲𝗮𝗹-𝘄𝗼𝗿𝗹𝗱 𝘄𝗲𝗯 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄 𝗱𝗮𝘁𝗮, we at Machine Learning Dept. at Carnegie Mellon and Scribe | Workflow AI Platform have adapted 𝗴𝗲𝗻𝗲𝗿𝗮𝗹-𝗽𝘂𝗿𝗽𝗼𝘀𝗲 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝗟𝗟𝗠𝘀 into 𝘀𝗽𝗲𝗰𝗶𝗮𝗹𝗶𝘇𝗲𝗱 𝘄𝗲𝗯 𝗮𝗴𝗲𝗻𝘁𝘀, outperforming traditional

I have some news to share! Datadog, Inc. is forming a new AI research lab, and I'm excited to announce that I've joined as Chief Scientist to lead this effort. Datadog has a great work culture, lots of data and compute, and is committed to open science and open sourcing. Our team

Excited to present our work at #ICLR2025! Join us on Thursday, April 23 (Afternoon Session) to chat about the current state of foundation models in specialised domains 🧬📈 Hall3+2B #40 Joint work with Zongzhe Xu Wenduo Cheng Alex Shen Junhong Shen Ameet Talwalkar Misha Khodak

Happy to see a time series workshop @ NeurIPS 2025 motivated in part by our search for BERT moments in specialized foundation models (🧵here: x.com/khodakmoments/…)