Yael Vinker (@YVinker) header
Yael Vinker (@YVinker) profile picture

Incoming Assistant Professor at @WeizmannScience · Postdoc at @MIT_CSAIL

Boston
Joined July 2021
Photo by Yael Vinker (@YVinker)Photo by Yael Vinker (@YVinker)Photo by Yael Vinker (@YVinker)Photo by Yael Vinker (@YVinker)Photo by Yael Vinker (@YVinker)Photo by Yael Vinker (@YVinker)Photo by Yael Vinker (@YVinker)Photo by Yael Vinker (@YVinker)Photo by Yael Vinker (@YVinker)Photo by Yael Vinker (@YVinker)
Yael Vinker retweeted
Meet Pika H3 Flex, debuting today as the #1 open weight model on DesignArena’s t2v board. It’s built for professional iteration, with exportable audio stems, resolutions up to 4k, and faster-than-realtime generation. It can produce a 15-second clip with soundtrack in as little as 7 seconds. So, yeah. It’s kind of a flex 💅
311
301
293
1,649
872,686
Yael Vinker retweeted
We raised a $7M pre-seed to make shopping fun again. @daletlabs generates media just for you: like walking into a mall built around your taste. And you can buy everything in-app. Built by researchers from Google, Runway and MIT. Backed by @lightspeedvp and amazing angels.
184
636
119
1,330
989,506
Yael Vinker retweeted
My saturday evening project: hacking my remarkable to see if Opus 5.5 can help me draw (and also animate cuz why not)
66
67
22
1,357
80,719
Yael Vinker retweeted
Spectacular new plotter just dropped from @bantamtools — a paperslinger inspired by the legendary HP7475A: bantamtools.com/products/han…!
6
13
1
148
7,303
Yael Vinker retweeted
Made a little site to learn about architecture, visually architecture.pascal.app/
38
154
16
1,848
61,903
"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.
8
42
6
331
33,993
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 (🧵).
7
24
7
176
16,914
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
15
87
12
756
46,451
reading feynman lecturess as feynman intended: with accompanying ai-made demo sections for each chapter rapid acquisition of knowledge is possible thanks to superintelligence
98
477
47
4,061
194,712
Yael Vinker retweeted
Visualization of the day: 2D Discrete Fourier Transform
3
6
2
70
11,654
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.
2
4
8
1,381
Yael Vinker retweeted
Zoetrope art This is crazy good
34
480
39
3,301
241,906
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.
8
40
18
304
54,786
Yael Vinker retweeted
Every frame drawn with JavaScript by Claude Opus 5.
17
25
3
398
20,985
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
51
1,168
184
7,996
1,163,800
Oh my gosh, this is so much fun!
45
7,051
238
49,081
2,590,794
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
2
2
25
1,305
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
1
1
1
40
2,694
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
11
15
6
86
8,487