Fan Wu

The paper introduces FedRAG, a novel federated RAG framework that enables privacy-preserving cross-institutional knowledge collaboration by decoupling the self-attention mechanism from data localization using a specialized scrambling protocol.

The paper introduces WebIGBench, a novel benchmark designed to rigorously evaluate multimodal LLMs' ability to generate code for complex, interactive webpages, addressing the limitations of existing static evaluation methods.

The paper introduces WebIGBench, a novel benchmark designed to rigorously evaluate multimodal LLMs' ability to generate code for complex, interactive webpages, addressing the limitations of existing static evaluation methods.

This paper introduces a new benchmark for evaluating the performance of large language models in generating slide decks that consider the target audience.

The paper proposes methods for detecting training instability in large language models using internal monitors based on the functional role of critical modules and earliest computational sites.

This paper proposes Gleam, a framework for efficient GPU sharing across local-area CUDA devices, reducing bandwidth overhead, improving API call latency, and ensuring context consistency.

This paper introduces a benchmark for evaluating document parsing systems that output HTML, which is more suitable for editable and reusable documents.