Uriel Singer

Research Scientist @ Meta AI Research

[Lior Yariv @YarivLior]

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)

[Vova Kulikov @vd_kulikov]

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
https://t.co/l5uKGwL7cT

[Hila Chefer @hila_chefer]

New research from @bfl_ml 🥳
Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖
https://t.co/AshY8IkSEe

Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

[Uriel Singer @urielsinger]

[3/3]
We systematically study the key modeling/training/sampling knobs and share practical guidance for better quality ✅ and faster generation ⚡—backed by a large-scale sweep of 56 pretrained models and 549 evaluations to map the design space. 📊

[Uriel Singer @urielsinger]

[1/3]
New at #ICLR2026!!! 🎉
Exploring the Design Space of Transition Matching 📄
https://t.co/hrBzP3TRza

[Uriel Singer @urielsinger]

[2/3]
In our previous paper, Transition Matching: Scalable and Flexible Generative Modeling (https://t.co/1atqaxcns8), we introduced transition matching—a new generative paradigm. This follow-up goes beyond the concept and asks: which design choices actually matter? 🔍

[Uriel Singer @urielsinger]

Nice results using transition matching for distillation!

[Julius Berner @julberner]

🚀🎬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

🔗https://t.co/o4VyCBl3mJ

[Neta Shaul @shaulneta]

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.

https://t.co/Qh3W9nfDrr

@urielsinger

[Peter Holderrieth @peholderrieth]

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!

https://t.co/unsuG3mYer
[1/7]

[Heli Ben-Hamu @helibenhamu]

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!

[Neta Shaul @shaulneta]

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.

[Neta Shaul @shaulneta]

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)💡.

[moab.arar @ArarMoab]

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.

[Neta Shaul @shaulneta]

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)

[Uriel Singer @urielsinger]

@hila_chefer @shaulneta @itai_gat @lipmanya Thank you Hila!

[Uriel Singer @urielsinger]

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

[Neta Shaul @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

[Yaron Lipman @lipmanya]

**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!

[Itai Gat @itai_gat]

Check out our team's latest work, led by @urielsinger and @shaulneta!

[Hila Chefer @hila_chefer]

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
🧵👇

[Itai Gat @itai_gat]

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: https://t.co/54etkhxNEK