Xia “Ben” Hu (@huxia) 's Twitter Profile
Xia “Ben” Hu

@huxia

Associate Professor of CS@Rice working on AutoML, XAI and Network Analytics. Author of AutoKeras and NCF.

ID: 72885746

linkhttps://cs.rice.edu/~xh37/index.html calendar_today09-09-2009 16:04:41

103 Tweet

666 Followers

329 Following

Jingfeng Yang (@jingfengy) 's Twitter Profile Photo

Welcome more people to trying Self-Extend/LongLM on more diverse tasks and models to see when it works and identify its limitations. Here is our implementation github.com/datamllab/Long… . Credits to HongyeJ !

Jiayi Yuan (@jiayiyuan99) 's Twitter Profile Photo

Excited to introduce KIVI🥝, the first 2bit KV cache quantization breakthrough! 🚀 KIVI can be directly integrated into existing LLMs without any tuning. 📄 Paper: arxiv.org/abs/2402.02750 💻 Code: github.com/jy-yuan/KIVI #KIVI #LLM #AI #MachineLearning

Excited to introduce KIVI🥝, the first 2bit KV cache quantization breakthrough! 🚀 KIVI can be directly integrated into existing LLMs without any tuning.
📄 Paper: arxiv.org/abs/2402.02750
💻 Code: github.com/jy-yuan/KIVI
#KIVI #LLM #AI #MachineLearning
Xia “Ben” Hu (@huxia) 's Twitter Profile Photo

Without fine-tuning, Self-Extend has significantly improved performance of the Gemma-2b-it performance in the needle in the haystack task, increasing its capability from less than 8k (pretraining window) to over 90k!! lnkd.in/gD_DqJvi

Hanjie Chen (@hanjie_chen) 's Twitter Profile Photo

📢Postdoc Position📢 Dr. Xia Hu Xia “Ben” Hu and I are looking for a Chairman's Postdoctoral Fellow in Efficient and Trustworthy LLMs Rice Computer Science If you are interested, please do not hesitate to apply: docs.google.com/document/d/1Ks…

📢Postdoc Position📢

Dr. Xia Hu <a href="/huxia/">Xia “Ben” Hu</a> and I are looking for a Chairman's Postdoctoral Fellow in Efficient and Trustworthy LLMs <a href="/RiceCompSci/">Rice Computer Science</a>

If you are interested, please do not hesitate to apply: docs.google.com/document/d/1Ks…
Shubham Saboo (@saboo_shubham_) 's Twitter Profile Photo

AWS just released a new Multi-Agent AI framework It lets you manage multiple AI agents, dynamically route LLM queries, maintain context across AI Agents and can be deployed locally on your computer. 100% opensource.

AWS just released a new Multi-Agent AI framework

It lets you manage multiple AI agents, dynamically route LLM queries, maintain context across AI Agents and can be deployed locally on your computer.

100% opensource.