Rafael Valle

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

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

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

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

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

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

Fugatto 1: Foundational Generative Audio Transformer Opus 1

OMCAT: Omni Context Aware Transformer

Elucidating the Design Space of Text-to-Audio Models

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

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