Skip to content
conftrace_

Itai Gat

19 papers · 2020–2025 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+12 more ↓ πŸ—ΊοΈ Taxonomy Completionist (36) 🌍 Conference Polyglot Β· Silver πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Silver 🐣 Hot Topic Early Bird
🧬 Topic Evolution πŸ† Grand Slam πŸ‘‘ Triple Crown πŸ† Keyword Champion (3) 🧭 Keyword Pioneer 🀝 Dynamic Duo (10) ⚑ Prolific Year Β· Productive πŸ”₯ Unstoppable Β· Bronze ❓ The Questioner (2) πŸ’Ž Century Club Β· Bronze 🌈 Renaissance Researcher (6) πŸ—ƒοΈ Keyword Collector (85)

Venues

NeurIPS (6) ICLR (4) AAAI (3) ACL (2) ICML (2) Interspeech (2)

Top co-authors

Yossi Adi (10) Felix Kreuk (6) Gabriel Synnaeve (6) Jade Copet (5) Tal Remez (5) Idan Schwartz (5) Tamir Hazan (5) Yaron Lipman (4) Alexandre Defossez (3) Ricky T. Q. Chen (3)

Research topics

Deep Learning (12) Machine Learning (12) Models (9) Artificial Intelligence (8) Core AI (8) Optimization & Theory (7) Learning Types (4) Application Areas (3) Core Methods (3) Techniques (3) Computer Vision (2) Natural Language Processing (2) Speech & Audio (2) Architectures (2) Generation (2)

Keywords

flow matching (4) log-sobolev inequality (3) visual question answering (3) fisher information (2) conditional generation (2) diffusion model (2) speech language model (2) probability path (2) functional entropy (2) multimodal learning (2) generative modeling (2) discrete diffusion (2) data augmentation (2) feature attribution (1) video synthesis (1) code generation (1) sequence generation (1) temporal alignment (1) model evaluation (1) video generation (1)

Papers

Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles ICLR 2025 Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective ICLR 2025 Generator Matching: Generative modeling with arbitrary Markov processes ICLR 2025 D-Flow: Differentiating through Flows for Controlled Generation ICML 2024 Discrete Flow Matching NeurIPS 2024 Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation AAAI 2024 Layer Collaboration in the Forward-Forward Algorithm AAAI 2024 Masked Audio Generation using a Single Non-Autoregressive Transformer ICLR 2024 Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation Interspeech 2023 Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling ACL 2023 Expresso: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis Interspeech 2023 Simple and Controllable Music Generation NeurIPS 2023 Textually Pretrained Speech Language Models NeurIPS 2023 A Functional Information Perspective on Model Interpretation ICML 2022 Latent Space Explanation by Intervention AAAI 2022 On the Importance of Gradient Norm in PAC-Bayesian Bounds NeurIPS 2022 Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions ACL 2021 Perceptual Score: What Data Modalities Does Your Model Perceive? NeurIPS 2021 Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies NeurIPS 2020