4 papers
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
Dongsheng Ma, Jiayu Li, Zhengren Wang +8
Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting ev…
AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Units
Xinzi Cao, Jianyang Zhai, Pengfei Li +17
To meet the ever-increasing demand for computational efficiency, Neural Processing Units (NPUs) have become critical in modern AI infrastructure. However, unlocking their full pote…
AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
Zhengren Wang, Dongsheng Ma, Huaping Zhong +4
The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports. Whil…
HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
Jiangwen Dong, Jiayu Li, Tianhang Zheng +1
Edge-cloud collaborative inference is becoming a practical necessity for LLM-powered edge devices: on-device models often cannot afford the required reasoning capability, while clo…