Hey everyone, I'm so excited to share my recent interview on Imagine while Reasoning in Space: Multimodal Visualization-of-Thought with Sam Charrington for the The TWIML AI Podcast podcast. Check it out! twimlai.com/go/722 from The TWIML AI Podcast

Super nice tool to understand what exactly are the preferences that we're aligning to, and the differences between models!

Most emotion detection models treat affect like a universal constant. But emotions are deeply personal. This paper has a dataset that captures affective responses to news posts along with annotator personas. A goldmine for personalization research. arxiv.org/abs/2503.03335

We created Approximate Likelihood Matching, a principled (and very effective) method for *cross-tokenizer distillation*! With ALM, you can create ensembles of models from different families, convert existing subword-level models to byte-level and a bunch more🧵

Extremely happy to share that our PhD student Tiancheng Hu received the Apple Scholars in AI/ML PhD Fellowship! 🎉 The fellowship will support his research on LLM-based simulation and LLM personalisation. Congratulations again, Tiancheng Hu! 🥳 machinelearning.apple.com/updates/apple-…

95 new scholars will form the Class of 2025, marking a quarter century of the scholarship's existence - gatescambridge.org/about/news/95-… #GatesCambridge25 #scholarship Cambridge University Gates Foundation GatesCambridgeAlumni

🔥 We teach LLMs to say how confident they are on-the-fly during long-form generation. 🤩No sampling. No slow post-hoc methods. Not limited to short-form QA! ‼️Just output confidence in a single decoding pass. ✅Better calibration! 🚀 20× faster runtime. arXiv:2505.23912 👇

Join us at EMNLP 2025 for: "Tailoring AI: Exploring Active and Passive LLM Personalization" 🎯🧠 To answer, when should LLMs personalize? What role do users play in LLM-personalization? 📅 Deadline Aug. 1 📝 Details in thread 🧵👇 #EMNLP2025 #LLM #AI #personalization 1/5

🗣️ Excited to share our new #ACL2025 Findings paper: “Just Put a Human in the Loop? Investigating LLM-Assisted Annotation for Subjective Tasks” with Jad Kabbara and Deb Roy. Arxiv: arxiv.org/abs/2507.15821 Read about our findings ⤵️

🚨 New preprint 🚨 Across 3 experiments (n = 3,285), we found that interacting with sycophantic (or overly agreeable) AI chatbots entrenched attitudes and led to inflated self-perceptions. Yet, people preferred sycophantic chatbots and viewed them as unbiased! Thread 🧵