Nowadays ML project feel like they need to be compressed into a few months. Its refreshing to be able to work on something for a few years! But also a slog.

A lot of papers claim to have low-memory optimizers that are just as good as Adam. Our recent study observes that this isn't always true - but we try to nail down when it is.

Great article by Anil Ananthaswamy on latent reasoning systems coming out of AI at Meta, UMD Department of Computer Science , and ELLIS Institute Tübingen. quantamagazine.org/to-make-langua…

🚨 How much parameter redundancy does LoRA really contain? We introduce LoRI, a method that keeps performance strong—even when we drastically shrink trainable parameters of LoRA. 🧵1/N

fine-grained editing of videos is hard. if I use a Video Diffusion Transformer to make my videos, just adding "red" to the prompt totally changes the video. in our new paper, we dive deep into the attention maps of VDiTs and find a way to do fine-grained editing, and other stuff!