activity
20242026
most citedGhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models

8 citations · 8 across the 3 of their papers we have counts for

collaborators

10 papers

cs.CR20268 cited

GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models

Zuyao Xu, Yuqi Qiu, Lu Sun +14

Citations provide the basis for trusting scientific claims; when they are invalid or fabricated, this trust collapses. With the advent of Large Language Models (LLMs), this risk ha…

cs.LG2026

Co-Evolving Latent Action World Models

Yucen Wang, Fengming Zhang, De-Chuan Zhan +3

Adapting pretrained video generation models into controllable world models via latent actions is a promising step towards creating generalist world models. The dominant paradigm ad…

cs.CV2026

A Semantic Decoupling-Based Two-Stage Rainy-Day Attack for Revealing Weather Robustness Deficiencies in Vision-Language Models

Chengyin Hu, Xiang Chen, Zhe Jia +4

Vision-Language Models (VLMs) are trained on image-text pairs collected under canonical visual conditions and achieve strong performance on multimodal tasks. However, their robustn…

cs.CV2025

RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events

Zhenyuan Chen, Chenxi Wang, Ningyu Zhang +1

Remote sensing is critical for disaster monitoring, yet existing datasets lack temporal image pairs and detailed textual annotations. While single-snapshot imagery dominates curren…

cs.CL2025

Online-PVLM: Advancing Personalized VLMs with Online Concept Learning

Huiyu Bai, Runze Wang, Zhuoyun Du +6

Personalized Visual Language Models (VLMs) are gaining increasing attention for their formidable ability in user-specific concepts aligned interactions (e.g., identifying a user's…

cs.CV2025

Thinking with Programming Vision: Towards a Unified View for Thinking with Images

Zirun Guo, Minjie Hong, Feng Zhang +2

Multimodal large language models (MLLMs) that think with images can interactively use tools to reason about visual inputs, but current approaches often rely on a narrow set of tool…