@yuntiandeng Really like this whole Claudish thing! The next step might be a mcp server to help Claude rephrase its outputs to become more human readable 🤣
📣 New paper by my Ph.D. student @hyungjoochae
How can we build a safe, scalable learning environment for web agents?
Paper: https://t.co/jtndyaCKKQ
We introduce VERIENV, which clones real websites into executable synthetic environments using coding agents.
The duration is flexible, ideally over 6 months, ending by September 2026. It's in-person based in the Santa Clara Valley, CA
If you are interested, please email your resume to "[email protected]" and also apply at https://t.co/FBtaWn3h6H (3/3)
📣 Ph.D. research Internship on Foundation Models at Apple AIML – Data & ML Innovation
Our team is seeking a PhD intern with a strong research background to work on advanced topics in improving the agentic/tool-use capabilities of large language models. Details in 🧵 (1/3)
Topics include benchmarking, post-training, and synthetic datagen. Prior publications in related areas are a big plus. This is a pure-research internship where the objective is to publish high-quality work. (2/3)
As artificial intelligence (AI) continues to evolve, its impact on society becomes increasingly profound. To gain insights into the trends shaping the AI landscape in 2025, we spoke with Wei Xu (@cocoweixu), an associate professor at Georgia Tech’s School of Interactive Computing (@ICatGT), whose research focuses on natural language processing and machine learning.
Check out the Q&A and learn about the fast growth of #AI research: https://t.co/vkMJ5klDEW
I defended my doctoral thesis, "Studying Text Revision in Scientific Writing," yesterday!🎓
A big thanks to my advisor @cocoweixu for training me to become a researcher, and thanks to my respected committee @alan_ritter@kartik_goyal_@VioletNPeng & Dr. Cheng Li from DeepMind!
"If you can't measure it, you can't improve it." ✨
Excited to share our #EMNLP main conference work w/ a meta-review score of 5:🔬𝐌𝐞𝐝𝐑𝐞𝐚𝐝𝐌𝐞, the first systematic study on medical sentence readability!
📝https://t.co/F5HHCHNqrM
Big thanks to @cocoweixu and @mlatgt!
"If you can't measure it, you can't improve it." ✨
Excited to share our #EMNLP main conference work w/ a meta-review score of 5:🔬𝐌𝐞𝐝𝐑𝐞𝐚𝐝𝐌𝐞, the first systematic study on medical sentence readability!
📝https://t.co/F5HHCHNqrM
Big thanks to @cocoweixu and @mlatgt!
👉 Virtual poster sessions will be organized as a pre-conference event, right before the main conference.
👉 The main conference will focus on the in-person experience.
👉 Findings papers will be presented at the virtual poster pre-conference event.
Love these changes!