Process supervision for reasoning is 🔥! While previous approaches often relied on human annotation and struggled to generalize across different reasoning tasks, we're now asking: Can we improve this? Introducing 𝐑𝐀𝐓𝐈𝐎𝐍𝐀𝐋𝐘𝐒𝐓: a new model pre-trained on implicit

🤖 New Multimodal Task! 🤖 We tackle the problem of piecing complex stories together through short snippets of video and text, and introduce a novel task + benchmark for grounding real-world events in multimodal data. 🌏 🧵⬇️

🤖 LLMs are powerful, but their "one-size-fits-all" safety alignment limits flexibility. Safety standards vary across cultures and users—what’s safe in one context might not be in another. 🌍 We propose ✨Controllable Safety Alignment✨ for inference-time safety adaptation! 🧵👇

📢 Want to host MASC 2025? The 12th Mid-Atlantic Student Colloquium is a one day event bringing together students, faculty and researchers from universities/industry in the Mid-Atlantic. Please submit this very short form if you are interested in hosting! Deadline January 6th

‼️Tired of dealing with long reasoning chains?‼️ Introducing Compressed Chain of Thought (CCoT), a framework to perform efficient reasoning through a few dense representations in place of long sequences of discrete tokens. 📜: arxiv.org/abs/2412.13171

Ever wonder how test-time compute would do in retrieval? 🤔 introducing ✨rank1✨ rank1 is distilled from R1 & designed for reranking. rank1 is state-of-the-art at complex reranking tasks in reasoning, instruction-following, and general semantics (often 2x RankLlama 🤯) 🧵

Our latest on compressed representations: Key-Value Distillation (KVD). Query-independen transformer compression, with offline supervised distillation.

👁️Recent works use LLMs for social simulations—but can these agents help shape effective policies? 💥Our new paper tackles a bold question many have wondered about: Can generative agent societies simulate to inform public health policy? 🔗: arxiv.org/abs/2503.09639

📣 New Preprint 📣 Did you realize there is a hidden misalignment between decomposer and verifier in long-form text factuality evaluation—an NP-hard puzzle for current methods? 🤔 We tackle this with an online RL solution called Dynamic Decomposition 👇 huggingface.co/papers/2503.15…

Check out our latest work, Video-ColBERT, an efficient late interaction approach for video retrieval! Recently accepted at #CVPR2025

🚨 Our latest paper is now on ArXiv! 👻 (w/ Benjamin Van Durme) SpectR: Dynamically Composing LM Experts with Spectral Routing (1/4) 🧵

Extremely excited to announce that I will be joining UT Austin Computer Science at UT Austin in August 2025 as an Assistant Professor! 🎉 I’m looking forward to continuing to develop AI agents that interact/communicate with people, each other, and the multimodal world. I’ll be recruiting PhD