collaborators

9 papers

cs.CL2026

Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

Wenhui Zhu, Xuanzhao Dong, Xiwen Chen +7

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled pri…

cs.CV2026

Bridging Restoration and Diagnosis: A Comprehensive Benchmark for Retinal Fundus Enhancement

Xuanzhao Dong, Wenhui Zhu, Xiwen Chen +8

Over the past decade, generative models have demonstrated success in enhancing fundus images. However, the evaluation of these models remains a challenge. A benchmark for fundus im…

cs.CV2026

OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport

Xiwen Chen, Wenhui Zhu, Gen Li +9

Multi-modal large language models (MLLMs) achieve strong visual-language reasoning but suffer from high inference cost due to redundant visual tokens. Recent work explores visual t…

cs.HC2026

EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent

Hao Wang, Wenhui Zhu, Shao Tang +8

As a cornerstone of the modern digital economy, 3D modeling and rendering demand substantial resources and manual effort when scene editing is performed in the traditional manner.…

cs.CV2025

VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement

Xuanzhao Dong, Wenhui Zhu, Yujian Xiong +8

Color fundus photography (CFP) is central to diagnosing and monitoring retinal disease, yet its acquisition variability (e.g., illumination changes) often degrades image quality, w…

cs.AI2025

Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs

Siyu Zhu, Yanbin Jiang, Hejian Sang +6

We investigated Agentic RL with large language models on the \textsc{TravelPlanner} benchmark. Our approach, \textsc{Planner-R1}, achieved a \textbf{56.9\%} final-pass rate with on…