Jianzhong Qi

Speculative Decoding (SD) reduces inference latency for Large Language Models (LLMs) by leveraging an efficient draft model to generate candidate tokens, which are subsequently verified by the target model. To enhance acceleration while reducing the LLM usage costs, we propose Serial and Parallel...

Misinformation spreading over the Internet poses a significant threat to both societies and individuals, necessitating robust and scalable fact-checking that relies on retrieving accurate and trustworthy evidence. Previous methods rely on semantic and social-contextual patterns learned from train...

Digitisation in the cultural heritage sector has produced large but fragmented repositories of museum collection data, spanning structured catalogue records, images, and unstructured descriptions. Existing museum information systems often make it difficult to integrate these sources into a unifie...