None defined yet.
Latent On-Policy Self-Distillation
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
The official Hugging Face space for the National University of Singapore. Users with a verified email ending in nus.edu.sg or u.nus.edu are welcome to join.
QLoRA fine-tuning demo on WeChat essays for style adaptation
Design protein sequences from structures