Jtd Acad
Research Scientist at ZJU
Hangzhou City, Zhejiang, China
Summary
🤩
RockstarJtd Acad is a research scientist and reinforcement learning (RL) researcher based in Hangzhou with four years of focused experience in machine learning research. He blends experimental RL work with practical problem-solving, likely contributing to reproducible experiments and algorithm development even if not widely published. Comfortable bridging theory and implementation, he brings hands-on GitHub activity as part of his research workflow. Working from a major Chinese tech hub, he’s positioned to collaborate across industry and academia in Asia. Colleagues can expect a practitioner who values iterative experimentation and rigorous evaluation.
4 years of coding experience
Github Skills (30)
transformers10
pytorch10
benchmark10
language-model10
python10
machine-learning10
reinforcement-learning10
datasets10
safety-critical10
deepspeed10
deep-learning10
alpaca10
tensorflow10
beaver10
bert10
Programming languages (2)
Github contributions (5)
calico-1226/safe-rlhf-calico
May 2023 - Sep 2024
Safe-RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Contributions:65 pushes, 26 branches in 1 year 4 months
calico-1226/omnisafe
Nov 2022 - Apr 2023
OmniSafe is a comprehensive and reliable benchmark for safe reinforcement learning.
Contributions:18 pushes, 4 branches in 4 months
benchmarkingreinforcement-learningsafe-reinforcement-learningreliablebenchmark
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.