works on

From the 1 of 9 linked papers with an AI index.

collaborators

9 papers

cs.DB2026

Evaluating LLMs in Database Scenarios: A Lifecycle Benchmark for Assessing Their Potential in Core Database Tasks

Shunfan Zheng, Dongsheng Shi, Yue Li +3

Large Language Models (LLMs) are transforming database interaction paradigms, evolving from simple query translators to autonomous database administrators (DBAs). However, current…

cs.CL2026

Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models

Yongyi Cui, Yue Li, Tianbao Jiang +1

The paper introduces a unified framework that creates code‑mixing fingerprints from low‑resource languages and injects them into large language models using null‑space projection a…

cs.CL2026

Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results

Yanyu Chen, Yue Li, Yongyi Cui +2

Retrieval-augmented large language models frequently face contexts that interleave useful evidence with misleading statements or instruction-like content. Blanket refusal discards…

cs.CL2026

From Construction to Injection: Edit-Based Fingerprints for Large Language Models

Yue Li, Xin Yi, Dongsheng Shi +3

Reliable model fingerprints are essential for protecting large language models (LLMs) against unauthorized redistribution and commercial misuse. In black-box deployment, verificati…

cs.CV2026

From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration

Jiaqi Shi, Yuechan Li, Xulong Zhang +2

High-resolution Multimodal Large Language Models (MLLMs) face prohibitive computational costs during inference due to the explosion of visual tokens. Existing acceleration strategi…

cs.CV2026

AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models

Yue Li, Xin Yi, Dongsheng Shi +3

Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs). However, vision-agnostic water…