🔥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

New blogpost dropped: Towards Reliable and Trustworthy MultiAgent Debate amayuelas.me/blog/2024/11/2…

happy to see an approach that took inspiration from SWE-Search achieving SOTA on SWE-bench. while there is still plenty of room for improvement, search is a vital tool for navigating complex SWE environments, and I expect more approaches to follow suit.

🚀🚀🚀Today's top SWEBench model, built using Antonis Antoniades's SWE-Search

🚀🚀 Life update: I just defended my PhD and have joined xAI to advance the visual generation models with Hexiang Hu Ting Chen Words cannot describe how grateful I am to my awesome advisor, William Wang, and my committee members, Xifeng Yan and Wenhu Chen. Huge thanks to

I’m excited to share that I’ve joined AI at Meta as a Research Scientist, where I’ll be working on Llama Post-training (multimodality). Can’t wait to work with the team and contribute to open-source multimodal AI! This new chapter comes right after successfully completing my PhD

🚀 Excited to share the latest on our recent UCSB NLP alumni! 🎉 🔹 Jiachen Li (PhD '25) → xAI 🔹 Yujie Lu (PhD '25) → Meta GenAI 🔹 Liangming Pan (Postdoc '24) → Asst. Prof., Arizona 🔹 @Qnolan4 (PhD '24) → Meta GenAI Proud of their achievements—onward and upward! 🚀

MLGym A New Framework and Benchmark for Advancing AI Research Agents

🎉Thrilled to share my internship work with the @NVIDIA GenAIR team (accepted to #CVPR2025): BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations! 🚀BlobGEN-Vid is a model-agnostic framework that delivers: - SOTA layout controllability - Enhanced

📜🚨 Check out our latest work on "Self-Resource Allocation in Multi-Agent LLM Systems" where we explore how LLMs can be used to optimize task allocation in multi-agent systems 🤖 🧵(1/3)

🧠 Reasoning models often overthink. 🚀 In our new paper, we show: 1️⃣ Two overthinking scores. 2️⃣ DUMB500 — a benchmark of extremely easy questions. 3️⃣ THOUGHT TERMINATOR — a decoding method that reduces token waste by up to 90%, often improving accuracy. Details below 👇

I’m attending #ICLR in Singapore! Also excited to share that I’m joining the Princeton Language and Intelligence Lab as a postdoc in July. In Fall 2026, I’ll be starting as an Assistant Professor at the University at Buffalo. I’ll be recruiting—feel free to reach out and chat!

📰 Thrilled to be featured in my hometown newspaper🤯 Diario de Burgos as part of a series on people living abroad! The article discusses my journey from Burgos to California. Check out the article in español 🇪🇸🔗diariodeburgos.es/noticia/z35dd9…

Lab celebration lunch after Xinyi Wang's defense!

If you're trying to decide which CVPR tutorial to attend, Check out Kaijie Zhu, Sophia Xiao Pu, @nieyuzhou, Hao Chen, and my tutorial on Evaluating Multimodal Models Unfortunately, I won't be able to attend, but my lovingly crafted slides are in the mix :)

RLVR is not just about RL, it's more about VR! Particularly for LLM coding, good verifiers (tests) are hard to get! In our latest work, we ask 3 questions: How good are current tests? How do we get better tests? How much does test quality matter? leililab.github.io/HardTests/

After all the papers, presentations, and sleepless nights... You can finally say it: Call me Doctor. 😎🎓 Congrats to the PhD Class of 2025! ❤️

Congratulations to all! Super excited to graduate 7 PhD students this year: they are joining UW, Princeton, Google x 2, xAI, Amazon, and Meta. They are the future of AI!

Finally completed this journey. Thanks a lot to my family, advisors and friends!

It is official: my first day at UCSB as a faculty. Happy to join the force to advance AI research and nurture talent. Let's go UC Santa Barbara NLP Group UCSB Computer Science Department!