🚨 FINAL FANTASY XVI Original Soundtracks on music streaming platforms At midnight, on September 18, FINAL FANTASY XVI & DLC OSTs will finally be released on music streaming platforms! 🔥 Links for Spotify & Apple Music below

Good choice, EMNLP😉

Yifang is more than an amazing colleague and collaborator. Chat!

Feel free to stop by our poster if you are interested in online DPO and RLHF. Our proposed method -- a mixture of uniform sampler and policy-dependent sampler -- provably achieves a quadratic convergence rate!

🧠 Your LLM should model how you think, not reduce you to preassigned traits 📢 Introducing LoRe: a low-rank reward modeling framework for personalized RLHF ❌ Demographic grouping/handcrafted traits ✅ Infers implicit preferences ✅ Few-shot adaptation 📄 arxiv.org/abs/2504.14439

Two-stage RLHF or one-stage DPO: Which one is better for learning from preferences? Equal under strong assumptions, but representation differences break the tie. Our paper reveals their fine-grained performance gaps under various conditions. paper: arxiv.org/abs/2505.19770

The Illusion of Thinking in LLMs Apple researchers discuss the strengths and limitations of reasoning models. Apparently, reasoning models "collapse" beyond certain task complexities. Lots of important insights on this one. (bookmark it!) Here are my notes:

Thrilled to announce that CASCADE is accepted to #COLM2025! It is one of the most interesting project I've done this far -- so I'm grateful to all the reviewers and ACs for helping me to improve the paper. Most importantly! Thank you Yi Zhang for your mentorship and support

Transformers can be exponentially more efficient than RNNs in code analysis tasks. Check out our #COLM2025 paper!

In this report we describe the 2025 Apple Foundation Models ("AFM"). We also introduce the new Foundation Models framework, which gives app developers direct access to the on-device AFM model. machinelearning.apple.com/research/apple…

Tired intricate system code for RL training? 🤯 We release AReaL-lite – A lightweight AReaL version for AI researchers! 🚀#opensource ✨ Algorithm-first design & APIs🎉 ✨ 80% less code w. 90% AReaL's full efficiency 🎉 ✨ Customizable agentic RL🎉 🔗 github.com/inclusionAI/AR…