4 accepted papers
Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential requires learned features to be both interpretable and steerable. To that end, we introduce two new computationally inexp
Traditionally, developing new language models (LMs) capable of addressing multiple tasks involves fine-tuning pre-trained LMs using a wide collection of datasets, a process that often incurs significant computational expenses. Model merging emerges as a cost-effective alternative, allowing the integ…
Generative Adversarial Networks (GANs) are notoriously difficult to train especially for complex distributions and with limited data. This has driven the need for interpretable tools to audit trained networks, for example, to identify biases or ensure fairness. Existing GAN audit tools are restricte…
Rich semantics exist in latent spaces inferred using deep generative models. The ability to extract and interpret them is not only essential for understanding the underlying factors of variation in the data distribution, but also crucial for con-trolled image generation. Several methods have been pr…