Los Angeles, California, United States
CS Phd student at USC Viterbi. CS undergrad, master at ShanghaiTech. Currently interested in LLM Reasoning, RL, and AI4Science. More at https://shangshang-wang.github.io/
Large-scale, stable, and efficient agentic RL for large language models. Host: Guoyin Wang (Qwen Pilot Team), Hao Zhou (Qwen 3.7 Team)
Agentic RL post-training acceleration via reward/environment curation. Host: Mahesh Sathiamoorthy, Alex Dimakis, Greg Durrett, Shreyas Pimpalgaonkar
Pre-training cross-layer transcoders over reasoning models and interpret model internals. Hosts: John Carlsson, Gunnar Carlsson, Jakob Hansen
Six-semester as a head TA for undergraduate Probability course and graduate RL course. Host: Ziyu Shao