אבא של סנדי (מאמי שלי כלבה חמודה) וכותב מאמר בזמני הפנוי
Israel
Joined July 2009
- Tweets2.8K
- Following751
- Followers276
- Likes15K
Ariel Bereslavsky retweeted
Multi-turn image editing is notoriously challenging: as edits accumulate, unintended changes and artifacts build up.
Not anymore!😁
Introducing ACEdit ♠️
A training approach that counteracts accumulated drift across successive image edits, preserving scene details as the changes add up.
🌐 saradorfman1.github.io/ACEdi…
1/5
Ariel Bereslavsky retweeted
[1/8] 🚀 New paper: APEX: Asynchronous Prefix Denoising for Extreme Compression
We give the same token multiple diffusion timesteps at once. APEX delivers better generation at the same compute with 4× fewer tokens. 🧵
🌐 Project page + code: daviddinkevich.github.io/APE…
Ariel Bereslavsky retweeted
Excited to share that our paper "ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control" has been accepted to @NeurIPSConf as an oral! 🎉
ParetoSlider enables continuous inference-time control over competing reward trade-offs with a single diffusion model, without retraining or maintaining multiple checkpoints.
Huge thanks to the great team @mikikiFin, @ArielBAMath, @YotamNitzan, @OPatashnik
Paper: arxiv.org/abs/2604.20816
Project page: shelley-golan.github.io/Pare…
Code: github.com/Shelley-Golan/Par…
1/7
When rewards conflict, what should RL post-training of diffusion models optimize?
In visual generation, objectives are often in tension:
Prompt adherence can conflict with source preservation.
Photorealism can conflict with stylization.
In our new paper, ParetoSlider, we introduce a multi-objective RL framework that trains a single diffusion model for continuous control over competing reward objectives 🧵
Ariel Bereslavsky retweeted
You ask for a talking parrot, but the model makes the pirate talk AND gives him a beak! 🦜😮💨
-> Introducing The Attention Triangle in Audio-Video Models: how semantics leak between text, audio, and video, and how we steer them back. 🧵 [1/5]
Ariel Bereslavsky retweeted
🔊 Audio on for this one!
Code + checkpoint for ScenA, our multi-speaker audio scene generation model, are out!
Reference voices + a prompt → a full conversational scene, prompt alone decides who speaks where.
github.com/finmickey/scena
arxiv.org/abs/2606.19325
Ariel Bereslavsky retweeted
Generating images with AI is fun 🤓
Finding the image? Not so much…
The first result is rarely the one. Or the second. Or the third. 🥵
So we built a way to generate diverse possibilities along meaningful semantic axes 🧭 and organize them into a gallery you can effortlessly browse 🧚🏻
Introducing our #ECCV2026 paper: Semantic Browsing: Controllable Diversity for Image Generation ✨
1/5
Scaling Expert Parallelism across nodes? Compute isn't your bottleneck anymore. The network is.
I wrote a breakdown on why wide-EP serving for MoE models is fundamentally network-bound.
getimpala.ai/blog/wide-ep-se…
Ariel Bereslavsky retweeted
1/7
When rewards conflict, what should RL post-training of diffusion models optimize?
In visual generation, objectives are often in tension:
Prompt adherence can conflict with source preservation.
Photorealism can conflict with stylization.
In our new paper, ParetoSlider, we introduce a multi-objective RL framework that trains a single diffusion model for continuous control over competing reward objectives 🧵
Ariel Bereslavsky retweeted
3D editing has long relied on workarounds: per-asset optimization, 2D view propagation, or hacking frozen priors. The bitter lesson is the same one image editing already learned. Train a native model, end-to-end.
Introducing ShapeUP, accepted to SIGGRAPH 2026 💫
Ariel Bereslavsky retweeted
CVPR 2026 highlight! 🔥
In this work co-led with @YehezkelShai, we show that a plain diffusion model can solve hard geometry problems by treating them as conditional image generation problems. No special architecture needed.
w/ @OmerDahary, @kusichan, @OPatashnik, @DanielCohenOr1
Ariel Bereslavsky retweeted
[1/5] Is Text Enough for Control? 🐇
Text-driven video editing lets you describe *what* to change. But what about *how much*?
We introduce Adaptive-Origin Guidance (AdaOr).
A joint work with @DecartAI and @TelAvivUni 🧪
accepted to #SIGGRAPH2026.
Ariel Bereslavsky retweeted
Our latest research, "Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations" is now published in the AAAI 2026 proceedings! 🚀
📄 Paper: ojs.aaai.org/index.php/AAAI/…
💻 GitHub: github.com/yonisGit/RFxG
Ariel Bereslavsky retweeted
We are pleased to share that using Gauss, we have completed a ~200K LOC formalization of Maryna Viazovska’s 2022 Fields Medal theorems on optimal sphere packing in dimensions 8 and 24.
This is the only Fields Medal-winning result from this century to be completely formalized, and is the largest single-purpose Lean formalization in history.
We are honored to have assisted @SidharthHarihar1 and the rest of the sphere packing team in this achievement.
math.inc/sphere-packing
I couldn't find a Python implementation of the Jonckheere-Terpstra test for my current paper, so I decided to build one myself.
Just released it as an open-source package. If you’re working with ordered alternatives in statistics, check it out! 📊
github.com/ScarWar/jonckheer…
Ariel Bereslavsky retweeted
🎵💬 If you are interested in Audio Tokenisers, you should check out our new work!
We empirically analysed existing tokenisers from every way - reconstruction, downstream, LMs and more.
Grab yourself a ☕/🍺 and sit down for a read!
Ariel Bereslavsky retweeted
אני כתב רכב.
לעולם לא יהיו מספיק נתיבים או מספיק מקומות חנייה. צריך דווקא לצמצם את המקום שמוקדש למכוניות ולפנות אותו לנתיבי תחבורה ציבורית, שבילי אופניים ולמדרכות רחבות ומוצלות
Ariel Bereslavsky retweeted
🚧 New blopost!! 🚧
📝 "Localization by design via semantic dropout masks"
Many recent works try to localize model behaviors to params and intervene upon them. Acknowledging how hard it is to do after training, several works have tried to train models that allow localization.
