Chao Zhang

WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM

YuE: Scaling Open Foundation Models for Long-Form Music Generation

End-to-end Listen, Look, Speak and Act

SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations

UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities

SciTS: Scientific Time Series Understanding and Generation with LLMs

sleep2vec: Unified Cross-Modal Alignment for Heterogeneous Nocturnal Biosignals

video-SALMONN S: Streaming Audio-Visual LLMs Beyond Length Limits via Memory

video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models

Bayesian Speech Synthesisers Can Learn from Multiple Teachers

SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation

BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals

Audio Large Language Models Can Be Descriptive Speech Quality Evaluators

Bayesian WeakS-to-Strong from Text Classification to Generation

Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback

video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model

Improving LLM Video Understanding with 16 Frames Per Second

Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization

SALMONN-omni: A Speech Understanding and Generation LLM in a Codec-free Full-duplex Framework