From the 1 of 16 linked papers with an AI index.
16 papers
QV-PIC: Query-Aware Visual Position-Independent Caching for Efficient RAG Serving
Yilin Liu, Rui Meng, Wangze Ni +5
Retrieval-Augmented Generation (RAG) repeatedly prefills identical text chunks across queries, incurring redundant computations. Position-Independent Caching (PIC) mitigates it by…
ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents
Hongwei Yao, Yiming Liu, Meihui Chen +6
Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavioral safety and introduce ActBe…
MERIT: Efficient In-Place Deletion for Dynamic Graph-Based Approximate Nearest Neighbor Indexes
Zekai Wu, Jiabao Jin, Peng Cheng +6
Graph-based indexes have become the dominant approach to approximate nearest neighbor search (ANNS) over high-dimensional data and play a crucial role in real-world applications su…
DREvo: Distilling Recalibrated Historical Experience for Harness Self-Evolution
Hanghui Guo, Weijie Shi, Zhangze Chen +6
The paper introduces DREvo, a method that improves the self‑evolution of large‑language‑model agents by dynamically reassessing and recalibrating historical trial experience to gui…
From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs
Zhiyi Mou, Wangze Ni, Tianfang Xiao +6
LLMs are increasingly deployed in real-world applications, making inference efficiency and service reliability critical concerns due to their substantial computational costs. Howev…
Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization
Heng Cao, Fan Zhang, Jian Yao +8
Personalizing large language models requires adapting model behavior to individual users while preserving robustness and deployment-scale efficiency. Existing approaches typically…