activity
20242026
collaborators

12 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

Aligning Large Vision-Language Models at Test Time: A Trajectory-Guided Structured Sampling Approach

Tianbao Jiang, Weicong Ni, Gerard de Melo +1

Post-training reinforcement learning (RL) algorithms are commonly used to align large vision-language models (LVLMs) with human intent and the requirements of visual reasoning task…

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.CL2026

SURGENT: A Surgical Multi-Agent Assistance System Across the Perioperative Workflow

Dongsheng Shi, Yue Li, Xin Yi +3

The intricate nature of modern surgical care necessitates intelligent systems that can synthesize extensive patient records, support collaborative decision-making, and provide tran…

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…

cs.CL2025

Unified Defense for Large Language Models against Jailbreak and Fine-Tuning Attacks in Education

Xin Yi, Yue Li, Dongsheng Shi +3

Large Language Models (LLMs) are increasingly integrated into educational applications. However, they remain vulnerable to jailbreak and fine-tuning attacks, which can compromise s…