16 citations · 24 across the 11 of their papers we have counts for
5 papers · 1 filter
Contamination, Prior, or Evidence? Decomposing and Training Evidence Use in Whole-Slide Vision-Language Models
Wenhao Zhang, Zhongliang Zhou, Shiyuan Zhang +6
Pathology vision-language models (VLMs) are conventionally evaluated by accuracy, but accuracy alone does not measure evidence use: it may conflate dataset contamination, prior kno…
Auditing Data Leakage in Whole-Slide Image Multimodal Benchmarks
Wenhao Zhang, Zhongliang Zhou, John Kang +1
Recent vision-language models (VLMs) for computational pathology report striking zero-shot performance on whole-slide image (WSI) visual question answering (VQA) benchmarks. We aud…
Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
Mengxuan Hu, Vivek V. Datla, Anoop Kumar +4
Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have impro…
Are LLMs Ready for Neural-integrated Mechanistic Modeling? A Benchmark and Agentic Framework
Zihan Guan, Rituparna Datta, Mengxuan Hu +5
Large language models (LLMs) have shown promise in constructing mechanistic models from data. However, existing evaluations largely focus on simplified settings and fail to capture…
Enhanced Diagnostic Performance via Large-Resolution Inference Optimization for Pathology Foundation Models
Mengxuan Hu, Zihan Guan, John Kang +2
Despite their prominent performance on tasks such as ROI classification and segmentation, many pathology foundation models remain constrained by a specific input size e.g. 224 x 22…