2 papers
cs.LG2026
A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models
Nima Eshraghi, Lovedeep Gondara, Yuqing Huang +5
Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning, but standard methods apply the steering si…
q-bio.BM2024
Ranking protein-protein models with large language models and graph neural networks
Xiaotong Xu, Alexandre M. J. J. Bonvin
Protein-protein interactions (PPIs) are associated with various diseases, including cancer, infections, and neurodegenerative disorders. Obtaining three-dimensional structural info…