collaborators

6 papers

cs.CL2026

Predictive Prefetching for Retrieval-Augmented Generation

Wuyang Zhang, Shichao Pei

Retrieval-Augmented Generation (RAG) improves factual grounding in large language models but suffers from substantial latency due to synchronous retrieval. While recent work explor…

cs.CV2026

PushupBench: Your VLM is not good at counting pushups

Shengzhi Li, Jiarun Chen, Karun Sharma +2

Large vision-language models (VLMs) can recognize \textit{what} happens in video but fail to count \textit{how many} times. We introduce \textbf{PushupBench}, 446 long-form clips (…

cs.CR2026

Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways

Guanjie Lin, Yinxin Wan, Shichao Pei +3

Third-party Large Language Model (LLM) API gateways are rapidly emerging as unified access points to models offered by multiple vendors. However, the internal routing, caching, and…

cs.CR2026

Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use

Wuyang Zhang, Shichao Pei

Tool-use large language model (LLM) agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory ma…

cs.CL2024

Abstract2Appendix: Academic Reviews Enhance LLM Long-Context Capabilities

Shengzhi Li, Kittipat Kampa, Rongyu Lin +2

Large language models (LLMs) have shown remarkable performance across various tasks, yet their ability to handle long-context reading remains challenging. This study explores the e…

cs.CL2024

Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models

Shengzhi Li, Rongyu Lin, Shichao Pei

Multi-modal large language models (MLLMs) are expected to support multi-turn queries of interchanging image and text modalities in production. However, the current MLLMs trained wi…