works on

From the 1 of 24 linked papers with an AI index.

collaborators

24 papers

cs.CV2026

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs

Zhongjie Ba, Shengwang Xu, Peng Cheng +4

Embodied intelligence and world models require video understanding systems to go beyond recognizing objects and actions and develop an understanding of physical regularities. Howev…

cs.CR2026

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference

Shuaifan Jin, Zhibo Wang, Qiyuan Wang +5

Collaborative inference deploys Large Vision-Language Models (LVLMs) by partitioning computation between edge devices and the cloud. While withholding raw inputs supposedly ensures…

cs.CR2026

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…

cs.CV2026

Attention-Free and Lightweight Token Reduction for Efficient Vision-Language Models

Xuanyi Hao, Zuoyuan Zhang, Zhibo Wang +4

The paper introduces a plug‑and‑play, attention‑free token reduction module for vision‑language models that selects informative and diverse visual tokens using an entropy‑based imp…

cs.CR2026

LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models

Yaopeng Wang, Qingliang Wang, Zhibo Wang +5

Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing text-to-image diffusion models, enabling lightweight modules that are shared, reused, and commercializ…

cs.CR2026

RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry

Bo Lv, Zhiheng Xu, KeDong Xiu +4

As Mixture-of-Experts (MoE) architectures are increasingly adopted for scaling Large Language Models (LLMs), safety auditing becomes necessary to verify whether these models produc…