Search papers, labs, and topics across Lattice.
2
20
3
1
Unlock precise, training-free color control in text-to-image models by directly manipulating the latent space's emergent Hue, Saturation, and Lightness structure.
Unlocking VLM interpretability, sparse autoencoders let you directly steer multimodal LLMs like LLaVA by intervening on CLIP's vision encoder.
