Research Scientist @ Meta AI Research
Joined October 2015
- Tweets56
- Following77
- Followers361
- Likes157
Uriel Singer retweeted
Why pay full compute for pixels you're not even looking at?
In our new work, Foveated Diffusion, we introduce a new concept for efficient image and video generation, motivated by how the human visual system works.
(See full thread below)
High-resolution image and video generation is hitting a wall because attention in DiTs scales quadratically with token count. But does every pixel need to be in full resolution?
Introducing Foveated Diffusion: a new approach for efficient diffusion-based generation that allocates compute where it matters most.
1/7🧵
Uriel Singer retweeted
Video editing just got more dynamic! 🚀
Thrilled to share DynaEdit: a training-free, text-based method for non-rigid video editing.
Work done during my internship at @GoogleDeepMind with @Roni_Paiss, @kusichan, @inbar_mosseri, @talidekel, @t_michaeli
dynaedit.github.io
Uriel Singer retweeted
New research from @bfl_ml 🥳
Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖
bfl.ai/research/self-flow
Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵
[1/3]
New at #ICLR2026!!! 🎉
Exploring the Design Space of Transition Matching 📄
arxiv.org/abs/2512.12465
[2/3]
In our previous paper, Transition Matching: Scalable and Flexible Generative Modeling (arxiv.org/abs/2506.23589), we introduced transition matching—a new generative paradigm. This follow-up goes beyond the concept and asks: which design choices actually matter? 🔍
Nice results using transition matching for distillation!
🚀🎬We introduce TMD (Transition Matching Distillation): 480p videos generated from text prompts in < 3 NFEs!
1️⃣Main backbone for feature extraction and lightweight head for iterative refinement
2️⃣Distilled from Wan2.1 14B T2V combining MeanFlow & DMD2
🔗research.nvidia.com/labs/gen…
Uriel Singer retweeted
After multiple requests for the code of the visuals from my talk about Transition Matching, I made a notebook that reproduces the DTM vs. FM GIF!
This demo is a good way to build intuition on how TM and FM differ.
github.com/neta93/visual-ill…
@urielsinger
Uriel Singer retweeted
New work: “GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models”. GLASS generates images by sampling stochastic Markov transitions with ODEs - allowing us to boost text-image alignment for large-scale models at inference time!
arxiv.org/pdf/2509.25170
[1/7]
Uriel Singer retweeted
Excited to share our work Set Block Decoding!
A new paradigm combining next-token-prediction and masked (or discrete diffusion) models, allowing parallel decoding without any architectural changes and with exact KV cache.
Arguably one of the simplest ways to accelerate LLMs!
Uriel Singer retweeted
DTM vs FM👇
Lots of interest in how Difference Transition Matching (DTM) connects to Flow Matching (FM).
Here is a short animation that illustrates Theorem 1 in our paper:
For a very small step size (1/T), DTM converges to an Euler step of FM.
[1/n]
New paper alert! 🚀
Excited to introduce 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐓𝐌)! We're replacing short-timestep kernels from Flow Matching/Diffusion with... a generative model🤯, achieving SOTA text-2-image generation!
@urielsinger @itai_gat @lipmanya
Uriel Singer retweeted
If you're curious to dive deeper into Transition Matching (TM)✨🔍, a great starting point is understanding the similarities and differences between 𝐃𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐜𝐞 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐃𝐓𝐌) and Flow Matching (FM)💡.
[1/n]
New paper alert! 🚀
Excited to introduce 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐓𝐌)! We're replacing short-timestep kernels from Flow Matching/Diffusion with... a generative model🤯, achieving SOTA text-2-image generation!
@urielsinger @itai_gat @lipmanya
Uriel Singer retweeted
This paper is awesome.
🔥 Flow-matching for flow-matching!
❌No more coarse-to-fine generation.
🚀Coarse and fine details emerge together during generation.
🏆Results look super promising, especially when you see how the images evolve.
[1/n]
New paper alert! 🚀
Excited to introduce 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐓𝐌)! We're replacing short-timestep kernels from Flow Matching/Diffusion with... a generative model🤯, achieving SOTA text-2-image generation!
@urielsinger @itai_gat @lipmanya
Uriel Singer retweeted
Difference Transition Matching (DTM) process is so simple to Illustrate, you can calculate it on a whiteboard!
At each step:
Draw all lines connecting source and target (shaded)
⬇️
List those intersecting with the current state (yellow)
⬇️
Sample a line from the list (green)
[1/n]
New paper alert! 🚀
Excited to introduce 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐓𝐌)! We're replacing short-timestep kernels from Flow Matching/Diffusion with... a generative model🤯, achieving SOTA text-2-image generation!
@urielsinger @itai_gat @lipmanya
Uriel Singer retweeted
**Transition Matching** is a new iterative generative paradigm using Flow Matching or AR models to transition between generation intermediate states, leading to an improved generation quality and speed!
[1/n]
New paper alert! 🚀
Excited to introduce 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐓𝐌)! We're replacing short-timestep kernels from Flow Matching/Diffusion with... a generative model🤯, achieving SOTA text-2-image generation!
@urielsinger @itai_gat @lipmanya
Uriel Singer retweeted
Check out our team's latest work, led by @urielsinger and @shaulneta!
[1/n]
New paper alert! 🚀
Excited to introduce 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐓𝐌)! We're replacing short-timestep kernels from Flow Matching/Diffusion with... a generative model🤯, achieving SOTA text-2-image generation!
@urielsinger @itai_gat @lipmanya
Introducing Transition Matching (TM) — a new generative paradigm that unifies Flow Matching and autoregressive models into one framework, boosting both quality and speed!
Thank you for the great collaboration @shaulneta @itai_gat @lipmanya
[1/n]
New paper alert! 🚀
Excited to introduce 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐓𝐌)! We're replacing short-timestep kernels from Flow Matching/Diffusion with... a generative model🤯, achieving SOTA text-2-image generation!
@urielsinger @itai_gat @lipmanya
Uriel Singer retweeted
Exciting news from #ICML2025 & #ICCV2025 🥳
- 🥇 VideoJAM accepted as *oral* at #ICML2025 (top 1%)
- Two talks at #ICCV2025
☝️interpretability in the generative era
✌️video customization
- Organizing two #ICCV2025 workshops
☝️structural priors for vision
✌️long video gen
🧵👇
VideoJAM is our new framework for improved motion generation from @AIatMeta
We show that video generators struggle with motion because the training objective favors appearance over dynamics.
VideoJAM directly adresses this **without any extra data or scaling**
👇🧵
Uriel Singer retweeted
Excited to share our recent work on corrector sampling in language models! A new sampling method that mitigates error accumulation by iteratively revisiting tokens in a window of previously generated text.
With: @shaulneta @urielsinger @lipmanya
Link: arxiv.org/abs/2506.06215
Uriel Singer retweeted
Beyond excited to share FlowMo!
We found that the latent representations by video models implicitly encode motion information, and can guide the model toward coherent motion at inference time
Very proud of @ariel__shaulov @itayhzn for this work!
Plus, it’s open source! 🥳
