Bryan Catanzaro

papers

1,540

total citations

papers (18)

Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models

ICCV 2023arXiv

302

citations

Factuality Enhanced Language Models for Open-Ended Text Generation

NEURIPS 2022arXiv

277

citations

Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

ICML 2024arXiv

168

citations

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

NEURIPS 2022arXiv

citations

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

ICML 2024arXiv

citations

Dual Contrastive Loss and Attention for GANs

ICCV 2021arXiv

citations

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models

CVPR 2025arXiv

citations

Panoptic-Based Image Synthesis

CVPR 2020arXiv

citations

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities

ICLR 2025arXiv

citations

Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?

NEURIPS 2020arXiv

citations

View Generalization for Single Image Textured 3D Models

CVPR 2021arXiv

citations

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

NEURIPS 2025arXiv

citations

UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation

ICLR 2025arXiv

citations

Neural FFTs for Universal Texture Image Synthesis

NEURIPS 2020

citations

P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting

NEURIPS 2023

citations

Bryan Catanzaro

papers (18)

Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models

Factuality Enhanced Language Models for Open-Ended Text Generation

Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

Long-Short Transformer: Efficient Transformers for Language and Vision

ODIN: Disentangled Reward Mitigates Hacking in RLHF

MM-EMBED: UNIVERSAL MULTIMODAL RETRIEVAL WITH MULTIMODAL LLMS

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

Dual Contrastive Loss and Attention for GANs

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models

Panoptic-Based Image Synthesis

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities

Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?

View Generalization for Single Image Textured 3D Models

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation

Neural FFTs for Universal Texture Image Synthesis

P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting

papers (18)

Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models

Factuality Enhanced Language Models for Open-Ended Text Generation

Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

Long-Short Transformer: Efficient Transformers for Language and Vision

ODIN: Disentangled Reward Mitigates Hacking in RLHF

MM-EMBED: UNIVERSAL MULTIMODAL RETRIEVAL WITH MULTIMODAL LLMS

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

Dual Contrastive Loss and Attention for GANs

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models

Panoptic-Based Image Synthesis

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities

Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?

View Generalization for Single Image Textured 3D Models

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation

Neural FFTs for Universal Texture Image Synthesis

P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting