2 5 1

Itai Gat

itaigat

https://itaigat.com/

AI & ML interests

None yet

Recent Activity

upvoted a paper 9 days ago

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning

upvoted a paper 10 months ago

Discrete Flow Matching

authored a paper 11 months ago

Discrete Flow Matching

View all activity

Organizations

itaigat's activity

upvoted a paper 9 days ago

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning

Paper • 2505.17813 • Published 14 days ago • 54

upvoted a paper 10 months ago

Discrete Flow Matching

Paper • 2407.15595 • Published Jul 22, 2024 • 13

authored a paper 11 months ago

Discrete Flow Matching

Paper • 2407.15595 • Published Jul 22, 2024 • 13

authored 2 papers over 1 year ago

Speaker Normalization for Self-supervised Speech Emotion Recognition

Paper • 2202.01252 • Published Feb 2, 2022

D-Flow: Differentiating through Flows for Controlled Generation

Paper • 2402.14017 • Published Feb 21, 2024 • 8

upvoted a paper over 1 year ago

D-Flow: Differentiating through Flows for Controlled Generation

Paper • 2402.14017 • Published Feb 21, 2024 • 8

authored a paper over 1 year ago

SpiRit-LM: Interleaved Spoken and Written Language Model

Paper • 2402.05755 • Published Feb 8, 2024 • 15

upvoted a paper over 1 year ago

Masked Audio Generation using a Single Non-Autoregressive Transformer

Paper • 2401.04577 • Published Jan 9, 2024 • 44

authored 2 papers over 1 year ago

Masked Audio Generation using a Single Non-Autoregressive Transformer

Paper • 2401.04577 • Published Jan 9, 2024 • 44

Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation

Paper • 2309.16429 • Published Sep 28, 2023 • 11

upvoted a paper over 1 year ago

Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation

Paper • 2309.16429 • Published Sep 28, 2023 • 11

authored 2 papers almost 2 years ago

Code Llama: Open Foundation Models for Code

Paper • 2308.12950 • Published Aug 24, 2023 • 26

Simple and Controllable Music Generation

Paper • 2306.05284 • Published Jun 8, 2023 • 156

liked a Space almost 2 years ago

4.98k

MusicGen

🎵

Generate music from text descriptions

authored 6 papers almost 2 years ago

Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies

Paper • 2010.10802 • Published Oct 21, 2020

Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions

Paper • 2106.04484 • Published Jun 8, 2021

Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling

Paper • 2209.15483 • Published Sep 30, 2022