PSO-Merging is an innovative deep model fusion method that uses particle swarm optimization algorithm to automatically find optimal model fusion weights.

FastLongSpeech is a novel framework designed to extend the capabilities of Large Speech-Language Models for efficient long-speech processing without necessitating dedicated long-speech training data.

This is the official repository for Auto-RAG.

StreamUni is a framework that efficiently enables unified Large Speech-Language Models to accomplish streaming speech translation in a cohesive manner.

LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.

FlexRAG: A RAG Framework for Information Retrieval and Generation.

Streamable Text-to-Speech model using a language modeling approach, without vector quantization

Code for ICML25 Paper "Overcoming Non-monotonicity in Transducer-based Streaming Generation"