Etai Sella

@etai_sella

PhD student at Tel-Aviv University, doing research in AI + Computer Graphics, Ruth and Libi's dad

etaisella.github.io

Joined November 2022

168 Following

169 Followers

Replies Reposts Media

Pinned
Etai Sella
@etai_sella
May 4
Even today, with powerful image editing models, making fine-grained structural changes to 3D shapes remains a major challenge. In our new #SIGGRAPH2026 paper, Prox-E, we use primitive-based abstraction to leverage VLMs for precise, reasoning-based 3D editing! 👇
4
Etai Sella
@etai_sella
Oct 7
Had a great time working on this!
Omer Dahary
@OmerDahary
Oct 7
When generating an image with an MM-DiT, the text tokens absorb information from the evolving image through multimodal attention. But what do these contextual tokens actually capture? In our new work, “Learning to Read,” we show that contextual tokens can be read as plain text,
Etai Sella
@etai_sella
Jul 19
Happy SIGGRAPH 2026 to all who celebrate! This year I'll be presenting 2 papers + an interactive demo: Prox-E — 7/20, 11:35am · Room 408B etaisella.github.io/Prox-E/ LooseRoPE — 7/23, 11:25am · Room 408B Demo — 7/22, 12:20pm · Concourse Hall snap-research.github.io/LooseRoPE/ See you there!
Etai Sella
@etai_sella
May 18
The code for Prox-E is now available! - github.com/etaisella/Prox… Check it out and let us know if you find any issues
Etai Sella
@etai_sella
May 4
Even today, with powerful image editing models, making fine-grained structural changes to 3D shapes remains a major challenge. In our new #SIGGRAPH2026 paper, Prox-E, we use primitive-based abstraction to leverage VLMs for precise, reasoning-based 3D editing! 👇
Etai Sella
@etai_sella
Apr 23
Do you like image editing? Don't like prompt engineering? Want to see what a giraffe-duck hybrid looks like? If you answered yes at least once, you may like our new #SIGGRAPH2026 paper: LooseRoPE, which presents a new, prompt-free way to edit images using simple visual cues 👇
9

Etai Sella

Etai Sella’s posts