@nirgoren

Researching AI https://xitter.cf/t.co/eMCNT73s4T

Joined May 2018
  • Tweets264
  • Following151
  • Followers126
11Media
It was exciting seeing how quickly the model has learned to natively stabilize multi-turn editing using our training scheme. And without relying on any external post-processing tricks!
Sara Dorfman@Sara__DorfmanOct 17
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
1
6
286
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
5
22
5
88
8,424
[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…
3
19
2
113
5,741
Nir Goren retweeted
Zheng Gu@zhenggu95Oct 10
Glad to share our work, IntrinSync! We jointly decomposes an image into editable intrinsic maps and renders them back to RGB, with cycle consistency to keep the maps coherent and support physically grounded image editing in a unified framework. arxiv.org/abs/2610.11138
3
2
17
2,283
Nir Goren retweeted
Omer Dahary
@OmerDaharyOct 7
When generating an image with an MM-DiT, the text tokens absorb information from the evolving image through multimodal attention. But what do these contextual tokens actually capture? In our new work, “Learning to Read,” we show that contextual tokens can be read as plain text, revealing surprisingly detailed visual semantics. Building on this finding, we introduce a new way to train diffusion models: supervising their contextual tokens to improve generation quality and distributional coverage. 1/n
9
25
1
107
4,236
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]
3
27
1
60
1,962
Nir Goren retweeted
Neta Shaul@shaulnetaJul 29
1/ New paper: Parallel Decoding Distillation (PDD)!🚀 To accelerate diffusion/flow models, trajectory distillation usually merges consecutive ODE steps into 1 larger step. PDD changes this by predicting MULTIPLE ODE steps in 1 network eval.🧵 w/ @julberner @ArashVahdat Chao Liu
5
38
5
166
23,909
🔊 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
3
14
59
5,363
🌟🚀 Excited to share our latest work: "Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping"! TL;DR: Stop wasting compute on redundant tokens! We introduce SparseContext that drops reference tokens for speeding up reference-based image generation⚡
3
14
1
51
10,123
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
2
17
3
37
2,531
Nir Goren retweeted
Zhuang Liu
@liuzhuang1234Jun 22
Can a small academic team build a strong text-to-image model using only public datasets? Introducing i1: a simple, fully open recipe for strong text-to-image models
11
78
9
442
71,459
1/7 New paper 🧵 ScenA generates a multi-speaker audio scene: overlapping speech, laughter, real room noise, from a text description and a few reference voices. When trained in the obvious way, it ignores the text and decides who speaks on its own. We found out why and fixed it.
1
22
4
58
6,166
FUN to share that Sync-LoRA has been accepted to #ECCV2026! 🤗✨🎬 the field moves fast, but the core seems to remain: 1️⃣ IC-LoRA enables diverse edits 2️⃣ high-quality data is key (even if it's a small amount!) Huge thanks to @arash_mham @OPatashnik @DanielCohenOr1
Sagi Polaczek 🦜
@PolaczekSagi4 Dec 2025
[1/4] Sync about it… 💭✨ Editing a portrait video yet keeping it fully synced with the original across the entire sequence. Read more about Sync-LoRA: sagipolaczek.github.io/Sync-… 🚀
3
7
1
36
14,365
Nir Goren retweeted
Jiawei Yang
@JiaweiYang118May 1
Two months ago, I vaguely posted a number: 0.9 FID, one-step, pixel space. Now it is 0.75, and can be even lower. Many wonder how. I thought it might end as a small FID prank: simple and deliberate. It started with one question: can FID be optimized directly, and what does it reveal? Introducing FD-loss.
59
159
41
995
263,140
Nir Goren retweeted
Gal Metzer@galmetzApr 27
Excited to share our work accepted to #SIGGRAPH2026 ! Video generation models struggle with something few talk about: their transformations don't evolve smoothly. You get long boring stretches... then a sudden semantic jump where everything "catches up" at once.
7
27
1
71
6,034
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 🧵
4
28
4
87
14,376
I'll be presenting NoisePrints today at ICLR! 🇧🇷 We exploit the remarkable correlation between a diffusion model's initial random noise and its output for robust and efficient watermarking. Come visit Pavilion 4, poster #3013 at 3:15 PM to hear more and discuss it! #ICLR
Nir Goren@nirgoren16 Oct 2025
The initial noise in diffusion models is surprisingly correlated with the final image. Our NoisePrints paper exploits this to provide a lightweight, distortion-free, cryptographically secure watermark for proving authorship of generated images & videos, requiring no model access.
3
20
2,239
We developed a simple, sample-efficient online RL technique for post-training image generation models. We see it as a possible steerable alternative to CFG, driven by any scalar reward, including human preference.
11
42
8
380
71,477
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
Shai Yehezkel@YehezkelShai29 Oct 2025
Visual Diffusion Models are Geometric Solvers We cast geometry as images: a plain diffusion model denoises into valid solutions. It is simple, general and effective. Shown on Inscribed Square, Steiner Tree, and Maximum Area Polygonization - all classic hard problems.
4
16
1
80
10,112
Nir Goren retweeted
Alon Wolf@AlonWolfyApr 11
[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.
6
24
1
67
12,018
Load more