iiinova — where your digital self keeps evolving

Rana Hanocka

@ranahanocka.bsky.social

Assistant Professor @uchicago @uchicagocs. PhD from @TelAvivUni. Interested in computer graphics, machine learning, & computer vision 🤖

Posts Replies Media

Reposted by Rana Hanocka

Dale Decatur @daledecatur.bsky.social · 22/10/2025

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/

182

Rana Hanocka @ranahanocka.bsky.social · 15/08/2025

This work was led by Sining Lu and Guan Chen, in collaboration with Nam Anh Dinh, Itai Lang, Ari Holtzman, and me. Check out our paper: arxiv.org/abs/2508.08228 We’re still actively developing LL3M, and we’d love to hear your thoughts! 7/

011

Rana Hanocka @ranahanocka.bsky.social · 15/08/2025

Another cool thing about LL3M: the Blender code it writes is actually readable. Clear structure, detailed comments, intuitive variable names. Easy to tweak a single parameter (e.g. key width) or even change the algorithmic logic (e.g. the keyboard pattern). 6/

100

Rana Hanocka @ranahanocka.bsky.social · 15/08/2025

LL3M generates 3D assets in 3 phases with specialized agents: 1️⃣ Initial Creation → break prompt into subtasks, retrieve relevant code snippets (BlenderRAG) 2️⃣ Auto-refine → critic spots issues, verification checks fixes 3️⃣ User-guided → iterative edits via user feedback 5/

100

Rana Hanocka @ranahanocka.bsky.social · 15/08/2025

LL3M can create a wide range of shapes, without requiring specialized 3D datasets or fine-tuning. Every asset created is represented under the hood as editable Blender code. 4/

100

Rana Hanocka @ranahanocka.bsky.social · 15/08/2025

Even non-experts can jump right in and easily edit 3D shapes. Blender code created by LL3M generates a node graph that is packed with tunable parameters, enabling users to tweak colors, textures, patterns, lengths, heights, and more. 3/

100

Rana Hanocka @ranahanocka.bsky.social · 15/08/2025

What we ❤️ about LL3M: You're in the loop! If you want to make a tweak, LL3M can be your collaborative 3D design partner. And there's no need to regenerate the entire model each time - target a specific part, provide follow-up prompts, and the rest stays intact. 2/

100

Rana Hanocka @ranahanocka.bsky.social · 15/08/2025

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/

120

Rana Hanocka @ranahanocka.bsky.social · 15/06/2025

Our work “Geometry in Style” will be presented at #CVPR2025 on Sunday at 4pm in ExHall D, poster 219. Drop by and say hi! Our technique is capable of performing expressive text-driven deformations that preserve the input shape identity. 1/

1224

Reposted by Rana Hanocka

Omer Shapira @omershapira.com · 03/06/2025

Big update from The Workshop on Computer Vision For Mixed Reality @ CVPR 2025: 📝 Papers and schedule are now up! Our Speakers: Richard Newcombe (Meta) Anjul Patney (NVIDIA) Rana Hanocka (UChicago) Laura Leal-Taixe ‪(NVIDIA) Margarita Grinvald (Meta) 📅 June 11, 8AM 📍Room 109. cv4mr.github.io

2153

Rana Hanocka @ranahanocka.bsky.social · 26/03/2025

Congrats Brian and team on the best paper honorable mention at #3dv2025 🥳🎉 Brian (hywkim-brian.github.io/site/) is going to start his PhD next year at Columbia with @silviasellan.bsky.social Make sure to watch out for their awesome works 📈📈📈

1153

Reposted by Rana Hanocka

Alex Kale @kalealex.bsky.social · 11/12/2024

My colleague Rana Hanocka does exciting work on the frontier for 3D graphics and AI/ML, and she’s recruiting PhD students this cycle!

Tweet advertising that Rana Hanocka at UChicago CS is recruiting PhD students.

161