📢 Announcing our new PEFT family S²FT @NeurIPS2024 ❗️❗️❗️ 😀 Join us at our poster presentation in West Ballroom A-D, Booth #7101, on Friday, December 13, from 11 a.m. to 2 p.m. PST. 🚀 Making Sparse Fine-tuning Great Again Compared to LoRA, S²FT offers several key advantages:

New Research Released! 🚀PosS: Position Specialist Generates Better Draft for Speculative Decoding Is your LLM fast enough? PosS consistently improves over current speculative decoding methods by using position-specialized draft layers to generate high-quality drafts! 🔖Paper:

🚀🚀Excited to share our paper R-Zero: Self-Evolving Reasoning LLM from Zero Data ! How to train LLM without data? R-Zero teaches Large Language Models to reason starting with nothing but a base model. No data required!!! Paper: arxiv.org/abs/2508.05004 Code: