I am looking for new PhD students for Fall 2025 at CMU ECE on LLM reasoning, alignment, and efficiency. You can refer to for more information. If interested, apply to the CMU ECE PhD program by Dec 15 at

Want to learn more? 📝 Blog: 📜 Paper: 🧑‍💻 Code:

@AlexGDimakis Congrats!!!!

@preminstrel and I will present Fast Best-of-N Decoding via Speculative Rejection today at NeurIPS, where we accelerate Best of N alignment by ~8x - 16x. If you’re around the poster session at 4:30pm, come and say “Hi!” at #4605 For more info check out:

RT @yus167: LLM self-improvement has critical implications in synthetic data, post-training and test-time inference. To understand LLMs' tr…

@JoshPurtell @aviral_kumar2 @YifeiZhou02 @pan_jiayipan @svlevine There is an oracle (another LLM) who plays the other side of the conversation

RT @YifeiZhou02: Check out our new algorithm that significantly improves the sample efficiency over PPO for language agent tasks! 😉

RT @aviral_kumar2: How can we train LLM Agents, to learn from their own experience autonomously? Introducing ArCHer, a simple (i.e., small…