Incoming Assistant Professor at @WeizmannScience · Postdoc at @MIT_CSAIL
Boston
Joined July 2021
- Tweets874
- Following403
- Followers1.7K
- Likes3.2K
Yael Vinker retweeted
Spectacular new plotter just dropped from @bantamtools — a paperslinger inspired by the legendary HP7475A: bantamtools.com/products/han…!
Yael Vinker retweeted
Made a little site to learn about architecture, visually
architecture.pascal.app/
Yael Vinker retweeted
"Evolution is anything but random."
This is INSANE...
@akarshkumar0101 (@MIT_CSAIL, @SakanaAILabs) on artificial life: searching the space of possible universes with foundation models, why evolved networks find structure SGD misses (with @kenneth0stanley), and LLMs evolving Core War programs.
Yael Vinker retweeted
My favorite artist has always been M.C. Escher. His "Print Gallery" has been hanging in my home for years.
Recently I bumped into a 3B1B video about it that was really awesome and I thought it would be cool to generate such art. A bit out of my comfort zone, but luckily @Sophie0tq took the lead (🧵).
Yael Vinker retweeted
(1/7) Humans can acquire many capabilities without (catastrophically) forgetting previous ones. Why can't neural networks do the same?
Local Support Learning (LSL) takes us a step closer towards this goal.
In LLMs of up to 7B parameters, LSL augments gradient-based training to retain prior capabilities while learning new tasks at full capacity. Notably, it does so without access to prior data.
Key idea: casting forgetting as a geometric problem, and optimizing for the worst case.
Paper: arxiv.org/abs/2610.02126
Website and code: assafbk.github.io/lsl
Yael Vinker retweeted
reading feynman lecturess as feynman intended: with accompanying ai-made demo sections for each chapter
rapid acquisition of knowledge is possible thanks to superintelligence
Yael Vinker retweeted
1/5 "Sometimes words are not enough," said Yael Vinker (@YVinker) of @MIT_CSAIL at TTIC's Young Researcher Seminar Series in Nov '25. "I want to teach machines to speak the language of sketches." This involves using visual means to communicate concepts under a set of constraints.
Yael Vinker retweeted
Real-time video models are unlocking new capabilities.
A first experiment: a drawing app that animates your sketches as you draw. Under the hood, a video model generates each frame live, turning every idea into motion instantly.
Yael Vinker retweeted
「ひらがなを読み書き学習したハエ」作ってみた。読めたらドーパミンを与えて10万文字のひらがなを8時間学習した結果のハエ。約85%確率で正解出してる
hae.satoru.net/
#flywire #ハエ
Yael Vinker retweeted
Oh my gosh, this is so much fun!
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
Yael Vinker retweeted
Can AI learn origami by watching us fold? 🤖📄
In FoldingAgent, we translate visual demonstrations 🎥 into executable, physically plausible folding procedures, combining vision, geometric reasoning, and agentic planning. 🦢🐦🔥
Very excited to share my first paper! 🎉
FoldingAgent has been accepted to SIGGRAPH Asia 2026 ✨
🔹 Reconstructs parametric origami from demonstration videos
🔹 Uses a VLM agent + origami simulator
Project: maya-moriya.github.io/origam…
Joint work with @sigal_raab @YVinker @talidekel
Yael Vinker retweeted
FoldingAgent accepted to SIGGRAPH Asia 2026 ✨ It allows reconstructing parametric, simulator-verified origami straight from demonstration videos!
Fun fact: all-female, 4-author paper! 👩💻📄✨ w/ @mayamoriya @sigal_raab @YVinker
Very excited to share my first paper! 🎉
FoldingAgent has been accepted to SIGGRAPH Asia 2026 ✨
🔹 Reconstructs parametric origami from demonstration videos
🔹 Uses a VLM agent + origami simulator
Project: maya-moriya.github.io/origam…
Joint work with @sigal_raab @YVinker @talidekel
Yael Vinker retweeted
Very excited to share my first paper! 🎉
FoldingAgent has been accepted to SIGGRAPH Asia 2026 ✨
🔹 Reconstructs parametric origami from demonstration videos
🔹 Uses a VLM agent + origami simulator
Project: maya-moriya.github.io/origam…
Joint work with @sigal_raab @YVinker @talidekel
Yael Vinker retweeted
Just over a week until our workshop at @eccvconf!
We have a great lineup of speakers, including @paschalidoud_1, @y_m_asano, @MattNiessner, @jmin__cho, @andrew_ilyas, @SergeBelongie, and @YunzhuLiYZ!
Come say hi!
Full schedule available soon at curateddata.github.io/
Yael Vinker retweeted
1/ I let @claudeai use the animoflow.ai API, and the result is an effectively infinite G1 locomotion dataset, rendered in a CAD apartment environment. Here's how:
Yael Vinker retweeted
Introducing LTX-2.5, the world model the world builds on.
One of the biggest upgrades yet to the model already powering film, robotics, and real-time workflows. Higher pixel fidelity, multishot scenes that hold together across cuts, and a pretrained foundation built to be finetuned across domains.
Plus: Diffusion Fidelity Rendering, a new rendering approach built for pixel quality that holds up frame by frame, even on a cinema screen.
This isn't a tool you rent. It's a foundation you build on, open and yours.
Yael Vinker retweeted
I was looking for an "immediate-mode" way to work with differentiable vector graphics. Ended up developing a small lib, Dpy5, which provides a Processing-like API around DiffVg, where all primitives are differentiable. Code and examples here github.com/colormotor/dpy5