Stephan Alaniz

End-to-end learned subspace projections shatter prior compression limits, achieving 70% weight reduction in Llama-2-7B with near-dense performance and drastically shrinking KV cache memory.

Direct manipulation of latent spaces in diffusion models can lead to severe visual artifacts, but using sparse autoencoders for semantic detection offers a cleaner alternative for object erasure.

Unlock CLIP's black box: EZPC reveals the "why" behind zero-shot image recognition by grounding predictions in human-understandable concepts, without sacrificing accuracy.