Shimon Vainer (@esx2ve) header
Shimon Vainer (@esx2ve) profile picture

curr: cohead research @ https://teapawt.net/t.co/PGmY28ajQJ prev: game-dev (graphics), CTO @ RestAR, Research @ Unity,

Israel
Joined May 2009
Photo by Shimon Vainer (@esx2ve)Photo by Shimon Vainer (@esx2ve)Photo by Shimon Vainer (@esx2ve)Photo by Shimon Vainer (@esx2ve)Photo by Shimon Vainer (@esx2ve)Photo by Shimon Vainer (@esx2ve)Photo by Shimon Vainer (@esx2ve)Photo by Shimon Vainer (@esx2ve)Photo by Shimon Vainer (@esx2ve)Photo by Shimon Vainer (@esx2ve)
Shimon Vainer retweeted
Our entire research team at Stability AI will be at ECCV next week! 👋 If you’d like to chat about our research, hear what we’re working on, or learn about open roles, send me a DM. We’re hiring!
3
6
18
1,605
Shimon Vainer retweeted
Today marks a new milestone for Stability AI. We've closed our Series B, bringing total funding to $232M under new leadership. This moment is more than the number, it's about who's in the room.
16
16
14
111
43,832
Shimon Vainer retweeted
We're excited to be releasing the model weights for our paper Stable Layers! It's an RL finetune of Qwen-image-layered for drastically improved image decomposition and editability. Model files: huggingface.co/StabilityLabs… Project Page: stability-ai.github.io/stabl…
7
23
3
165
14,839
Shimon Vainer retweeted
We're excited to share Stable-Layers! We train Qwen-Image-Layered further with RL for improved layerization, using only feedback from a VLM — no paired supervision required! Paper: arxiv.org/abs/2605.30257 Project Page: stability-ai.github.io/stabl…
12
51
275
18,688
Shimon Vainer retweeted
We initially cared about local LLMs, but KV caches appear in more than text. So we also investigated OCTOPUS for autoregressive video and audio transformers. Joined work with @VikramVoleti, Simon Donné, @esx2ve
3
1
6
308
Shimon Vainer retweeted
Current hobby: vibecoding tiny tools that eliminate annoying tasks. I open-sourced them in case they’re useful to others.
1
1
11
695
Shimon Vainer retweeted
The first lab to open-source a solid pixel-space video diffusion model will be cited a bazillion times by everyone working on inverse problems esp. related to 3D/4D. With JiT/Simple(r) Diffusion the tech is mostly there, someone with more GPUs than me should make it happen (plz)
14
7
1
165
20,685
We are hiring! ☺️
We’re hiring 3 researchers for the Stability AI 3D team — and with our new EA partnership, this is an absolutely massive opportunity. If you’re passionate about 3D, graphics, AI models, or VLMs consider applying below:
215
Shimon Vainer retweeted
We need something like full of interactive visualization and hover documentation, like distill pub like visualization, for everything. Math, physics, chemistry, etc etc LLMs can totally make epic interactive diagrams and visualizations at massive scale, we need entire textbooks like this.
1
2
48
4,877
Shimon Vainer retweeted
Introducing our new work, "Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video" It's a control model for Stable Audio to generate aligned audio from an input video. Project Page: stability-ai.github.io/foley… Paper: tinyurl.com/4929p8bh 🧵 @StabilityAI
1
1
15
763
Working on 3D, video, or image generation? We’re hiring at @StabilityAI — building next-gen creative AI tools with EA to reimagine world-building. If you’ve been affected by recent layoffs (Meta/FAIR or elsewhere), DM me. Around #ICCV2025? Let’s connect.
1
1
383
Read more about the EA/SAI announcement here: stability.ai/news/stability-…
151
Shimon Vainer retweeted
New paper & surprising result. LLMs transmit traits to other models via hidden signals in data. Datasets consisting only of 3-digit numbers can transmit a love for owls, or evil tendencies. 🧵
274
1,093
756
8,201
1,963,382
Shimon Vainer retweeted
this guy's channel is so small with only a couple K views here and there if you're interested in GPU programming and still a beginner, he's worth a look (Simon Oz on yt)
26
132
2
2,181
86,053
Shimon Vainer retweeted
Congratulations to @gintszilbalodis and the entire Flow film crew for the Academy Award win! Flow is the manifestation of Blender’s mission, where a small independent team is able to create a story that moves audiences worldwide. Thank you for the shout out! 🧡 #b3d
139
4,680
312
33,363
667,161
The post below (learnable lambda has to do with skip connections) reminded me of some ResNet and Transformer architecture-related lore that I thought would be fun to write up! Blogpost: lb.eyer.be/s/residuals.html
Learnable lambda is so good. its just so good.
14
36
2
365
64,331
I’m currently exploring new job opportunities🧑‍🔬 My work revolves around text-to-3D with Geometry Images, generative UV mapping, multi-view models for texturing, and other genAI applications in graphics. I’d love to discuss how I can contribute to your research efforts!
Does 3D generation always have to be either slow or complex and data-hungry?🤔 We don’t think so! With Geometry Image Diffusion, we’re all about reusing (and recycling ♻️) what already works — making it faster and easier by reducing complexity and data needs 🚀(1/10)
4
9
1
46
9,869
Recordings for Graphics Programming Conference 2024 are now up. The lineup is packed with amazing talks ranging from rendering for games like Tiny Glade, Hades, and Baldur’s Gate 3, to even a talk on designing your own GPU! youtube.com/playlist?list=PL…
30
112
5,205
ECCV '24: Visit our poster at #309 (Oct 2. afternoon session)! Learn about how to generate high resolution PBR textures :)
8
733