ActiveUltraFeedback: Sample-Efficient RLHF Preference data generation using Active Learning

AI & ML interests

NLP, LLM Alignment, Preference Data generation, Active Learning

Recent Activity

MariSchn  authored a paper 4 days ago

Apertus 1.5: From Open Text Models to Open Multimodal Reasoners

davmel  authored a paper 4 days ago

Apertus 1.5: From Open Text Models to Open Multimodal Reasoners

davmel  authored a paper 4 days ago

Apertus LLM Family Expansion via Distillation and Quantization

View all activity

Team members 3