Research Papers Featured Feb 12, 2024 Suppressing Pink Elephants with Direct Principle Feedback Feb 12, 2024 Feb 12, 2024 Feb 6, 2024 Neural networks learn moments of increasing order Feb 6, 2024 Feb 6, 2024 Dec 17, 2023 Sparse Autoencoders Find Highly Interpretable Features in Language Models Dec 17, 2023 Dec 17, 2023 Dec 16, 2023 Quality-Diversity through AI Feedback Dec 16, 2023 Dec 16, 2023 Dec 16, 2023 ReLoRA: High-Rank Training Through Low-Rank Updates Dec 16, 2023 Dec 16, 2023
