← Search

Guoming Liu

2 accepted papers

2026

End-to-End Contrastive Language-Speech Pretraining Model for Long-Form Spoken Question Answering

AAAI 2026technical

Significant progress has been made in spoken question answering (SQA) in recent years. However, many existing methods, including large audio language models, struggle with processing long audio. Follow the success of retrieval augmented generation, a speech-related retriever shows promising in help

Cited by 0SourcePDFScholar
2026

Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios

AAAI 2026technical

Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of available computing power, then generate a complex and massive draft tree using a sma

Cited by 0SourcePDFScholar