Shaobai Jiang
shaobaij
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
How Far Can Unsupervised RLVR Scale LLM Training? upvoted a paper 1 day ago
Scalable Training of Mixture-of-Experts Models with Megatron Core upvoted a paper 1 day ago
OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning Organizations
None yet