425 citations · 559 across the 29 of their papers we have counts for
17 papers · 1 filter
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…
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…
Edit Flows: Flow Matching with Edit Operations
Marton Havasi, Brian Karrer, Itai Gat +1
Autoregressive generative models naturally generate variable-length sequences, while non-autoregressive models struggle, often imposing rigid, token-wise structures. We propose Edi…
Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking
Heli Ben-Hamu, Itai Gat, Daniel Severo +2
Recent masked diffusion models (MDMs) have shown competitive performance compared to autoregressive models (ARMs) for language modeling. While most literature has focused on perfor…
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…
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…
Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation
Guy Yariv, Itai Gat, Sagie Benaim +3
We consider the task of generating diverse and realistic videos guided by natural audio samples from a wide variety of semantic classes. For this task, the videos are required to b…
Layer Collaboration in the Forward-Forward Algorithm
Guy Lorberbom, Itai Gat, Yossi Adi +2
Backpropagation, which uses the chain rule, is the de-facto standard algorithm for optimizing neural networks nowadays. Recently, Hinton (2022) proposed the forward-forward algorit…
On the Importance of Gradient Norm in PAC-Bayesian Bounds
Itai Gat, Yossi Adi, Alexander Schwing +1
Generalization bounds which assess the difference between the true risk and the empirical risk, have been studied extensively. However, to obtain bounds, current techniques use str…
A Functional Information Perspective on Model Interpretation
Itai Gat, Nitay Calderon, Roi Reichart +1
Contemporary predictive models are hard to interpret as their deep nets exploit numerous complex relations between input elements. This work suggests a theoretical framework for mo…
Speaker Normalization for Self-supervised Speech Emotion Recognition
Itai Gat, Hagai Aronowitz, Weizhong Zhu +2
Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find…
Latent Space Explanation by Intervention
Itai Gat, Guy Lorberbom, Idan Schwartz +1
The success of deep neural nets heavily relies on their ability to encode complex relations between their input and their output. While this property serves to fit the training dat…
Perceptual Score: What Data Modalities Does Your Model Perceive?
Itai Gat, Idan Schwartz, Alexander Schwing
Machine learning advances in the last decade have relied significantly on large-scale datasets that continue to grow in size. Increasingly, those datasets also contain different da…