matan kleiner

34 posts

matan kleiner

matan kleiner

@MatanKleiner

PhD candidate @TechnionLive

Katılım Ağustos 2022
115 Takip Edilen34 Takipçiler
matan kleiner retweetledi
Tomer Ashuach
Tomer Ashuach@tomerashuach·
🎉 Excited to share our paper accepted at ACL 2026! Do LLMs know when they're about to get an answer right — in a way external observers can't detect? We studied Privileged Knowledge in LLM correctness & found: it depends on the domain. [technion-cs-nlp.github.io/Privileged-Kno…]
English
4
9
42
1.3K
matan kleiner retweetledi
Tomer Ashuach
Tomer Ashuach@tomerashuach·
🎉 CRISP accepted at #ACL2026 ! CRISP: Persistent Concept Unlearning via SAEs LLMs often encode knowledge we want to remove. CRISP enables persistent, interpretable, precise unlearning while keeping models useful & coherent🧵👇 technion-cs-nlp.github.io/CRISP/
English
2
13
43
1.4K
matan kleiner retweetledi
Tal Daniel
Tal Daniel@TalDaniel8·
🚀 #ICLR2026 Oral 💥 How can we design world models that capture object interactions directly from pixels? Introducing Latent Particle World Models-the first end-to-end self-supervised, object-centric world model, trained from videos, supporting action/img/lang conditioning. 1/n
English
4
48
277
23.8K
matan kleiner retweetledi
Inbar Huberman-Spiegelglas
Inbar Huberman-Spiegelglas@inbarhub·
🎉Splatent has been accepted to #CVPR2026 Get sharp, high-quality reconstructions from diffusion latent space. Research by Amazon Prime Video: pape:r arxiv.org/abs/2512.09923 project page: orhir.github.io/Splatent/ Huge thanks to the amazing team @Or_Hirsch @FritzLior @omeriko_
Or Hirschorn@Or_Hirsch

Happy to share Splatent, a new research done during my internship at Amazon @PrimeVideo! 🎬 We tackle a key issue in 3D generation: getting sharp reconstructions directly from diffusion latent space. 📄 Paper: arxiv.org/abs/2512.09923 🌐 Page: orhir.github.io/Splatent/

English
0
3
14
769
matan kleiner retweetledi
Sean Man
Sean Man@sean_8100·
Introducing 🦤 DODO: Discrete OCR Diffusion Models. This work is the result of my summer internship at Amazon and is the first to study masked diffusion models for document parsing. OCR is special: the image already contains the answer.
So why decode one token at a time?
Sean Man tweet media
English
1
3
9
372
matan kleiner retweetledi
LTX Studio
LTX Studio@LTXStudio·
Sometimes prompting takes longer... That’s where the new Brush tool comes in. When prompting falls short, Brush handles the details. Now live in LTX.
English
18
29
290
58.9K
matan kleiner retweetledi
LTX Studio
LTX Studio@LTXStudio·
Introducing Audio-to-Video in LTX. The third paradigm in AI video generation. Start from audio to get consistent voices, control over performance, and actions timed to the beat. We’re proud to partner with @elevenlabs for this launch. Here’s how it works (sound on) 🧵
English
106
150
1.2K
305.5K
matan kleiner retweetledi
Black Forest Labs
Black Forest Labs@bfl_ml·
Introducing FLUX.2 [klein]. Blazing fast. Beautiful. Generate stunning images in under a second while maintaining exceptional quality. Great for fast editing, changing styles, and developing ideas from 0 → 1. Available via API, or run it locally - Klein 4B under Apache 2.0, Klein 9B as open weights. Try it for free in our demo app (link in the thread).
English
74
216
1.9K
438.7K
matan kleiner retweetledi
Noam Elata
Noam Elata@NoamElata·
I'm in London this week, send me a message if you want to chat about Gen AI, diffusion models, or anything else!
Noam Elata tweet media
English
0
1
9
182
matan kleiner retweetledi
LTX
LTX@ltx_model·
LTX-2 is now open source. The first truly open audio-video generation model with open weights and full training code, designed to run locally on @NVIDIA_AI_PC RTX consumer GPUs. Details below 🧵
English
47
153
997
64.4K
matan kleiner retweetledi
Sean Man
Sean Man@sean_8100·
🌟 Excited to share our new paper: “ELAD: Blind Face Restoration using Expectation-based Likelihood Approximation and Diffusion Prior” presented today in #SIGGRAPHAsia2025 (13:40pm, room S423) 🧵[1/8]
English
1
4
6
339
matan kleiner retweetledi
Noam Elata
Noam Elata@NoamElata·
I’ll be at NeurIPS 25 in San Diego to present InvFusion (arxiv.org/abs/2504.01689), and follow up with a visit to the Bay Area to present at @Stanford and @Berkeley. Reach out if you want to talk about new research, diffusion models, efficient attention, or just grab a coffee :)
English
1
5
14
382
matan kleiner retweetledi
#ICCV2025
#ICCV2025@ICCVConference·
#ICCV2025 Best paper awards!!
#ICCV2025 tweet media#ICCV2025 tweet media#ICCV2025 tweet media#ICCV2025 tweet media
English
2
9
126
35.2K
matan kleiner retweetledi
Inbar Huberman-Spiegelglas
Inbar Huberman-Spiegelglas@inbarhub·
🎉 Excited to share that FlowEdit paper got accepted as an ORAL presentation at @ICCVConference! 🎉 See you in Honolulu! 🌺 Thanks to the amazing team @vd_kulikov, @MatanKleiner, @t_michaeli
Inbar Huberman-Spiegelglas@inbarhub

📷  FlowEdit has been accepted to @ICCVConference Edit real images with text-to-image flow models! Check out: code github.com/fallenshock/Fl… webpage matankleiner.github.io/flowedit/ space to edit your images - huggingface.co/spaces/fallens… great ComfyUI plugins (@logtdx) #comfy" target="_blank" rel="nofollow noopener">matankleiner.github.io/flowedit/#comfy

English
1
6
44
3K
matan kleiner
matan kleiner@MatanKleiner·
Don’t miss having coffee with @vd_kulikov and @inbarhub at @ICCVConference in Hawaii 🌸
Inbar Huberman-Spiegelglas@inbarhub

📷  FlowEdit has been accepted to @ICCVConference Edit real images with text-to-image flow models! Check out: code github.com/fallenshock/Fl… webpage matankleiner.github.io/flowedit/ space to edit your images - huggingface.co/spaces/fallens… great ComfyUI plugins (@logtdx) #comfy" target="_blank" rel="nofollow noopener">matankleiner.github.io/flowedit/#comfy

English
0
0
3
78
matan kleiner retweetledi
Overleaf
Overleaf@overleaf·
⚠️ Attention: The site is currently down. Our engineering team is investigating. We will update as soon as possible. You can track progress here: status.overleaf.com Sorry for any inconvenience.
English
214
200
783
271K

Keşfet

@GoogleDeepMind @Roni_Paiss @kusichan @inbar_mosseri @talidekel @t_michaeli @Or_Hirsch @FritzLior