←
Selena Ling 凌子涵157 posts
Selena Ling 凌子涵 avatar

Selena Ling 凌子涵

@seleniumlzh

Member of Technical Staff @ideogram_ai | Prev. PhD @UofTCompSci DGP @AdobeResearch @NVIDIA : )

◷ Joined August 2012▧ 20 Photos and videos
Selena Ling 凌子涵 avatar
Selena Ling 凌子涵@seleniumlzh·Sep 30

Proud of the team! 👏

Introducing Ideogram 4.5, the most precise edit model. With each edit, leading models add artifacts, pixel shifts, and color changes. Ideogram 4.5 eliminates artifact buildup, making multi-turn editing possible. Live in Ideogram, the API, and launch partners. Open weights soon.

0:47
DesignArena avatar
⟳ Selena Ling 凌子涵 retweeted
DesignArena@DesignArena·Oct 15

BREAKING: Ideogram 4.5 (Very Low) by @ideogram_ai ranks #23 in the Image Editing Arena on Design Arena with an Elo of 1189. At 8.2s per edit, it's over 7x faster than Ideogram 4.5 (High), and at $0.008 per image it's the cheapest model on the board, making it the highest rated model under 9s and leading every faster model by about 90 Elo points. Congratulations to the @ideogram_ai team on delivering top value and speed in image editing!

Post attachmentPost attachment
Artificial Analysis avatar
⟳ Selena Ling 凌子涵 retweeted
Artificial Analysis@ArtificialAnlys·Oct 9

We gave four frontier image editing models the same photo and 30 edits in a row: Ideogram 4.5 keeps most of the room intact, while the others drift, GPT Image 2.5 Sunburst most visibly. We've seen some interesting demos of multi-turn editing consistency from the latest image editing models, so we ran our own test: GPT Image 2.5 Sunburst, #1 on our Image Editing leaderboard, against Ideogram 4.5, FLUX 3 and Nano Banana 2.1. Our leaderboard scores single edits; this tests what happens when 30 consecutive changes stack up, with each model editing its own previous output through a 30-step real estate staging sequence: light the fire, add a sofa, repaint the walls, swap day for twilight, and more. Why are the final results so different? @ideogram_ai's Ideogram 4.5 and @bfl_ml's FLUX 3 edit locally. On small edits like adding a vase of tulips, we measured that they left 95% or more of the image essentially untouched. GPT Image 2.5 (Sunburst) re-renders most of the entire image on every edit, leaving only about a fifth of the image unchanged, so small shifts in colour and detail compound over turns. Nano Banana 2.1 sits in between: its edits stay local, but the rest of the image shifts slightly and gradually darkens.

0:47
Christopher Manning avatar
⟳ Selena Ling 凌子涵 retweeted
Christopher Manning@chrmanning·Sep 30

High long term fidelity across many edits is a research breakthrough — and an open weights model helps power a broader community

Introducing Ideogram 4.5, the most precise edit model. With each edit, leading models add artifacts, pixel shifts, and color changes. Ideogram 4.5 eliminates artifact buildup, making multi-turn editing possible. Live in Ideogram, the API, and launch partners. Open weights soon.

0:47
Benjamin Parry avatar
⟳ Selena Ling 凌子涵 retweeted
Benjamin Parry@_benjaminparry·Sep 28

In the real world, all the positive AI sentiment I hear is from small business owners. They love the posters, the cool custom websites, accounting, legal help, support agents.

Nick Sharp avatar
⟳ Selena Ling 凌子涵 retweeted
Nick Sharp@nmwsharp·Aug 18

Excited to announce: In 2027 I'll join the UW Allen School (@UWCSE) in Seattle as tenure-track faculty in Computer Science! My group will advance core geometry processing + 3D AI for visual computing, science, & engineering. I'll be recruiting PhD students in the next cycle!

Post attachmentPost attachment
Chenxi Liu avatar
⟳ Selena Ling 凌子涵 retweeted
Chenxi Liu@chenxil21·Jul 22

We are presenting GimmBO tomorrow at #SIGGRAPH NPR, Style & Abstraction session, 9-10:30 am, Room 408B. s2026.conference-schedule.or…

Paper announcement📢 GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization Chenxi Liu, Selena Ling (@seleniumlzh), Alec Jacobson 🏆 SIGGRAPH 2026 Best Paper Selena and I will be presenting in LA (July 19-23)! 🌐 Project: gimmbo-project.github.io/ [1/7]

Post attachment
Selena Ling 凌子涵 avatar
Selena Ling 凌子涵@seleniumlzh·Jul 3

📢Join Chenxi at University of Victoria if you are interested in building systems for creativity!

📢 Joining today as Assistant Professor of Computer Science at University of Victoria, leading the Creative eXperience Lab (CXL). We study how people create and build systems for visual creativity. Recruiting PhD & MSc: chenxil21.github.io/ Also at SIGGRAPH NA 2026 in LA.

Yael Vinker avatar
⟳ Selena Ling 凌子涵 retweeted
Yael Vinker@YVinker·Apr 9

I am *very* excited to announce our SIGGRAPH 2026 workshop: Lines & Minds: Visual Abstraction in Art, Psychology, and Computer Graphics 🎨🧠🫖 🔗 lines-and-minds.github.io 📅 Sunday, July 19 Join us to explore how visual abstraction shapes how we think, create, and communicate.

Post attachment
Google DeepMind avatar
⟳ Selena Ling 凌子涵 retweeted
Google DeepMind@GoogleDeepMind·Jan 26

Our short film Dear Upstairs Neighbors is previewing at @sundancefest. 🎬 It’s a story about noisy neighbors, but behind the scenes, it’s about solving a huge challenge in generative AI: control. Developed by Pixar alumni, an Academy Award winner, researchers, and engineers, here’s how it came together. 🎨

1:07
Jeff Dean avatar
⟳ Selena Ling 凌子涵 retweeted
Jeff Dean@JeffDean·Jan 24

This is absolutely shameful. Agents of a federal agency unnecessarily escalating, and then executing a defenseless citizen whose offense appears to be using his cell phone camera. Every person regardless of political affiliation should be denouncing this.

Drop Site obtained harrowing footage of the latest killing which appears to be from the perspective of the woman in pink filming from the sidewalk

2:50
Blender 🔶 avatar
⟳ Selena Ling 凌子涵 retweeted
Blender 🔶@Blender·13 Nov 2025

Did Blender help you this year? Help back! If every active user contributed $5 this month, Blender would be funded for the entire year 2026. Professional 3D software. No subscriptions. No limits. Just your support. Do your part. Donate today. blender.org/news/give-back-t… #b3d

Post attachment
Sherwin Bahmani avatar
⟳ Selena Ling 凌子涵 retweeted
Sherwin Bahmani@sherwinbahmani·25 Sep 2025

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: research.nvidia.com/labs/tor… Code and Models: github.com/nv-tlabs/lyra Paper: arxiv.org/abs/2509.19296

0:50