papers

Publications (23)

cs.LG2025

Exploring the Design Space of Transition Matching

Uriel Singer, Yaron Lipman

Transition Matching (TM) is an emerging paradigm for generative modeling that generalizes diffusion and flow-matching models as well as continuous-state autoregressive models. TM,…

cs.LG2024

Leveraging World Events to Predict E-Commerce Consumer Demand under Anomaly

Dan Kalifa, Uriel Singer, Ido Guy +2

Consumer demand forecasting is of high importance for many e-commerce applications, including supply chain optimization, advertisement placement, and delivery speed optimization. H…

cs.LG2024

Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models

Neta Shaul, Uriel Singer, Ricky T. Q. Chen +4

This paper introduces Bespoke Non-Stationary (BNS) Solvers, a solver distillation approach to improve sample efficiency of Diffusion and Flow models. BNS solvers are based on a fam…

cs.LG2026

GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models

Peter Holderrieth, Uriel Singer, Tommi Jaakkola +3

The performance of flow matching and diffusion models can be greatly improved at inference time using reward alignment algorithms, yet efficiency remains a major limitation. While…

cs.SD2023

AudioGen: Textually Guided Audio Generation

Felix Kreuk, Gabriel Synnaeve, Adam Polyak +6

We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive generative model that generates a…

cs.LG2021

Node Embedding over Temporal Graphs

Uriel Singer, Ido Guy, Kira Radinsky

In this work, we present a method for node embedding in temporal graphs. We propose an algorithm that learns the evolution of a temporal graph's nodes and edges over time and incor…

cs.LG2023

Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning

Lili Yu, Bowen Shi, Ramakanth Pasunuru +24

We present CM3Leon (pronounced "Chameleon"), a retrieval-augmented, token-based, decoder-only multi-modal language model capable of generating and infilling both text and images. C…

cs.LG2025

Transition Matching: Scalable and Flexible Generative Modeling

Neta Shaul, Uriel Singer, Itai Gat +1

Diffusion and flow matching models have significantly advanced media generation, yet their design space is well-explored, somewhat limiting further improvements. Concurrently, auto…

cs.CV2023

Emu Edit: Precise Image Editing via Recognition and Generation Tasks

Shelly Sheynin, Adam Polyak, Uriel Singer +5

Instruction-based image editing holds immense potential for a variety of applications, as it enables users to perform any editing operation using a natural language instruction. Ho…

cs.LG2021

Topo2vec: Topography Embedding Using the Fractal Effect

Jonathan Kavitzky, Jonathan Zarecki, Idan Brusilovsky +1

Recent advances in deep learning have transformed many fields by introducing generic embedding spaces, capable of achieving great predictive performance with minimal labeling effor…

cs.CV2022

KNN-Diffusion: Image Generation via Large-Scale Retrieval

Shelly Sheynin, Oron Ashual, Adam Polyak +4

Recent text-to-image models have achieved impressive results. However, since they require large-scale datasets of text-image pairs, it is impractical to train them on new domains w…

cs.CV2025

VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models

Hila Chefer, Uriel Singer, Amit Zohar +5

Despite tremendous recent progress, generative video models still struggle to capture real-world motion, dynamics, and physics. We show that this limitation arises from the convent…

cs.LG2022

tBDFS: Temporal Graph Neural Network Leveraging DFS

Uriel Singer, Haggai Roitman, Ido Guy +1

Temporal graph neural networks (temporal GNNs) have been widely researched, reaching state-of-the-art results on multiple prediction tasks. A common approach employed by most previ…

cs.LG2021

EqGNN: Equalized Node Opportunity in Graphs

Uriel Singer, Kira Radinsky

Graph neural networks (GNNs), has been widely used for supervised learning tasks in graphs reaching state-of-the-art results. However, little work was dedicated to creating unbiase…

cs.CV2022

Make-A-Video: Text-to-Video Generation without Text-Video Data

Uriel Singer, Adam Polyak, Thomas Hayes +10

We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: le…

cs.CV2023

Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation

Yuval Kirstain, Adam Polyak, Uriel Singer +3

The ability to collect a large dataset of human preferences from text-to-image users is usually limited to companies, making such datasets inaccessible to the public. To address th…

q-bio.BM2026

GOProteinGNN: Leveraging Protein Knowledge Graphs for Protein Representation Learning

Dan Kalifa, Uriel Singer, Kira Radinsky

Proteins play a vital role in biological processes and are indispensable for living organisms. Accurate representation of proteins is crucial, especially in drug development. Recen…

cs.LG2025

Corrector Sampling in Language Models

Itai Gat, Neta Shaul, Uriel Singer +1

Autoregressive language models accumulate errors due to their fixed, irrevocable left-to-right token generation. To address this, we propose a new sampling method called Resample-P…

cs.CV2024

Video Editing via Factorized Diffusion Distillation

Uriel Singer, Amit Zohar, Yuval Kirstain +4

We introduce Emu Video Edit (EVE), a model that establishes a new state-of-the art in video editing without relying on any supervised video editing data. To develop EVE we separate…

cs.CV2023

Text-To-4D Dynamic Scene Generation

Uriel Singer, Shelly Sheynin, Adam Polyak +8

We present MAV3D (Make-A-Video3D), a method for generating three-dimensional dynamic scenes from text descriptions. Our approach uses a 4D dynamic Neural Radiance Field (NeRF), whi…

cs.LG2024

D-Flow: Differentiating through Flows for Controlled Generation

Heli Ben-Hamu, Omri Puny, Itai Gat +3

Taming the generation outcome of state of the art Diffusion and Flow-Matching (FM) models without having to re-train a task-specific model unlocks a powerful tool for solving inver…

cs.IR2021

Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce

Uriel Singer, Haggai Roitman, Yotam Eshel +5

In e-commerce, the watchlist enables users to track items over time and has emerged as a primary feature, playing an important role in users' shopping journey. Watchlist items typi…

cs.CL2022

Learning to Diversify for Product Question Generation

Haggai Roitman, Uriel Singer, Yotam Eshel +2

We address the product question generation task. For a given product description, our goal is to generate questions that reflect potential user information needs that are either mi…