Bryan Catanzaro

Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset

AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy

Music Flamingo: Scaling Music Understanding in Audio Language Models

UALM: Unified Audio Language Model for Understanding, Generation and Reasoning

RLP: Reinforcement as a Pretraining Objective

Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning

Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data

TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

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

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning

Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities

NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

ETTA: Elucidating the Design Space of Text-to-Audio Models

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data

Fugatto 1: Foundational Generative Audio Transformer Opus 1

FeatSharp: Your Vision Model Features, Sharper

MM-EMBED: UNIVERSAL MULTIMODAL RETRIEVAL WITH MULTIMODAL LLMS

Elucidating the Design Space of Text-to-Audio Models

OMCAT: Omni Context Aware Transformer

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

MIND: Math Informed syNthetic Dialogues for Pretraining LLMs

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

A$^2$-Flow: Alignment-Aware Pre-training for Speech Synthesis with Flow Matching

PHI-S: Distribution Balancing for Agglomerative Models

LLM Pruning and Distillation in Practice

Nemotron-CORTEXA: Enhancing LLM Agents for Software Engineering Tasks via Improved Localization and Solution Diversity