sem-sparse-debiasing-vlm

【开发与工程】Achieve post-hoc debiasing of frozen vision-language models by operating in sparse autoencoder latent space. Identify and modulate bias-relevant neurons with neuron-level precision while preserving task-relevant features, requiring no task-specific fine-tuning.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准