172 citations · 1.1k across the 55 of their papers we have counts for
64 papers
Muse Glimmer 30B: An On-Device Agentic Model
Arash Ebrahim Abtahizadeh, Muna Aghamelu, Adil Ahmed +327
We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hardware. Muse Glimmer…
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,…
Space Group Conditional Flow Matching
Omri Puny, Yaron Lipman, Benjamin Kurt Miller
Inorganic crystals are periodic, highly-symmetric arrangements of atoms in three-dimensional space. Their structures are constrained by the symmetry operations of a crystallographi…
Set Block Decoding is a Language Model Inference Accelerator
Itai Gat, Heli Ben-Hamu, Marton Havasi +6
Autoregressive next token prediction language models offer powerful capabilities but face significant challenges in practical deployment due to the high computational and memory co…
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…
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…
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…
Flow Matching Guide and Code
Yaron Lipman, Marton Havasi, Peter Holderrieth +7
Flow Matching (FM) is a recent framework for generative modeling that has achieved state-of-the-art performance across various domains, including image, video, audio, speech, and b…
Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective
Neta Shaul, Itai Gat, Marton Havasi +6
The design space of discrete-space diffusion or flow generative models are significantly less well-understood than their continuous-space counterparts, with many works focusing onl…
Generator Matching: Generative modeling with arbitrary Markov processes
Peter Holderrieth, Marton Havasi, Jason Yim +6
We introduce Generator Matching, a modality-agnostic framework for generative modeling using arbitrary Markov processes. Generators characterize the infinitesimal evolution of a Ma…
Discrete Flow Matching
Itai Gat, Tal Remez, Neta Shaul +5
Despite Flow Matching and diffusion models having emerged as powerful generative paradigms for continuous variables such as images and videos, their application to high-dimensional…
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…
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…
Guided Flows for Generative Modeling and Decision Making
Qinqing Zheng, Matt Le, Neta Shaul +3
Classifier-free guidance is a key component for enhancing the performance of conditional generative models across diverse tasks. While it has previously demonstrated remarkable imp…
Mosaic-SDF for 3D Generative Models
Lior Yariv, Omri Puny, Natalia Neverova +2
Current diffusion or flow-based generative models for 3D shapes divide to two: distilling pre-trained 2D image diffusion models, and training directly on 3D shapes. When training a…
Bespoke Solvers for Generative Flow Models
Neta Shaul, Juan Perez, Ricky T. Q. Chen +3
Diffusion or flow-based models are powerful generative paradigms that are notoriously hard to sample as samples are defined as solutions to high-dimensional Ordinary or Stochastic…
Generalized Schrödinger Bridge Matching
Guan-Horng Liu, Yaron Lipman, Maximilian Nickel +3
Modern distribution matching algorithms for training diffusion or flow models directly prescribe the time evolution of the marginal distributions between two boundary distributions…
On Kinetic Optimal Probability Paths for Generative Models
Neta Shaul, Ricky T. Q. Chen, Maximilian Nickel +2
Recent successful generative models are trained by fitting a neural network to an a-priori defined tractable probability density path taking noise to training examples. In this pap…
Multisample Flow Matching: Straightening Flows with Minibatch Couplings
Aram-Alexandre Pooladian, Heli Ben-Hamu, Carles Domingo-Enrich +3
Simulation-free methods for training continuous-time generative models construct probability paths that go between noise distributions and individual data samples. Recent works, su…
VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids
Albert Pumarola, Artsiom Sanakoyeu, Lior Yariv +2
Surface reconstruction has been seeing a lot of progress lately by utilizing Implicit Neural Representations (INRs). Despite their success, INRs often introduce hard to control ind…
MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
Omer Bar-Tal, Lior Yariv, Yaron Lipman +1
Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fa…
Equivariant Polynomials for Graph Neural Networks
Omri Puny, Derek Lim, Bobak T. Kiani +2
Graph Neural Networks (GNN) are inherently limited in their expressive power. Recent seminal works (Xu et al., 2019; Morris et al., 2019b) introduced the Weisfeiler-Lehman (WL) hie…
Flow Matching on General Geometries
Ricky T. Q. Chen, Yaron Lipman
We propose Riemannian Flow Matching (RFM), a simple yet powerful framework for training continuous normalizing flows on manifolds. Existing methods for generative modeling on manif…
Flow Matching for Generative Modeling
Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu +2
We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the not…