zhuoc3.bsky.social
@zhuoc3.bsky.social
🎉 Excited to present our work on long-context language modeling at NeurIPS 2025 in San Diego!
📅 Join us on Thu Dec 4, 4:30–7:30 p.m. PST at Exhibit Hall C,D,E #3901.
▶️ Video: www.youtube.com/watch?v=--q7...
📄 Paper: arxiv.org/abs/2503.04725
🧾 NeurIPS page: neurips.cc/virtual/2025...
(NeurIPS 2025) L2M: Mutual Information Scaling Law for Long-Context Language Modeling
YouTube video by Zhuo
www.youtube.com
December 1, 2025 at 7:27 PM
🚀 Excited to share: L²M: Mutual Information Scaling Law for Long-Context Language Modeling
We’ve uncovered a fundamental pattern in natural language with direct implications for how LLMs handle long documents
📝 arxiv.org/abs/2503.04725
#MachineLearning #LanguageModels #InformationTheory #LLMs
March 11, 2025 at 12:59 PM