7 papers
Open-Ended CT Volume Segmentation with Weak Supervision from Language
Sanjay Subramanian, Junwei Yu, Zirui Wang +5
We introduce a method for training a text-conditioned segmentation model for CT scans, which combines voxel-level supervision with coarse but scalable slice-level supervision from…
Stateful Visual Encoders for Vision-Language Models
Zirui Wang, Junwei Yu, Adam Yala +3
Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in existing open-weight VLMs, vis…
PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation
Yichuan Wang, Zhifei Li, Zirui Wang +5
Augmenting large language models (LLMs) with retrieved web text has become a dominant paradigm, yet the web is not natively textual: existing systems depend on complex parsing pipe…
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images
Bo Zhang, Tzu-Yen Ma, Zichen Tang +18
We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS features three key advances: (1) D…
THEMIS: Towards Holistic Evaluation of MLLMs for Scientific Paper Fraud Forensics
Tzu-Yen Ma, Bo Zhang, Zichen Tang +20
We present THEMIS, a novel multi-task benchmark designed to comprehensively evaluate multimodal large language models (MLLMs) on visual fraud reasoning within real-world academic s…
Kestrel: Grounding Self-Refinement for LVLM Hallucination Mitigation
Jiawei Mao, Hardy Chen, Haoqin Tu +7
Large vision-language models (LVLMs) have become increasingly strong but remain prone to hallucinations in multimodal tasks, which significantly narrows their deployment. As traini…