Dale Decatur

daledecatur.bsky.social

22 October 2025 20:24

Excited to share our #ICCV2025 work Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets! Our method generates large sets of images using significantly less compute than standard diffusion. 📎https://ddecatur.github.io/hierarchical-diffusion/ 1/

Dale Decatur

daledecatur.bsky.social

22 October 2025 20:23

This work was completed in collaboration with @thibaultgroueix.bsky.social, Yifan Wang, @ranahanocka.bsky.social, @vovakim.bsky.social, and @gadelha.bsky.social‬. Check out our #ICCV2025 poster #153 today during Poster Session #4 from 2:45-4:45 HST! Paper: arxiv.org/abs/2508.21032 7/

Rana Hanocka

ranahanocka.bsky.social

15 August 2025 06:05

We’ve been building something we’re 𝑟𝑒𝑎𝑙𝑙𝑦 excited about – LL3M: LLM-powered agents that turn text into editable 3D assets. LL3M models shapes as interpretable Blender code, making geometry, appearance, and style easy to modify. 🔗 threedle.github.io/ll3m 1/

lea

leeps.bsky.social

16 June 2025 20:29

This is so cool!

Keenan Crane

keenancrane.bsky.social

15 June 2025 20:20

Shout out today to parents, grandparents, aunts, uncles, or anyone else who helps raise a kid. It didn’t really click until I was a dad: without parents, human civilization ends. Only with good parents does the future look bright. So, give a nod to anyone putting in the work.