Raghu Machiraju

Debargha Ganguly, Sreehari Sankar, Biyao Zhang et al.

Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust safety comes not from enumerating what is harmful, but from deeply understanding what is safe. We introduce Trust The Typical (T3), a framework that operationalizes this principle by treating safety as an out-of-distribution (OOD) detection problem. T3 learns the distribution of acceptable prompts in a semantic space and flags any significant deviation as a potential threat. Unlike prior methods, it requires no training on harmful examples, yet achieves state-of-the-art performance across 18 benchmarks spanning toxicity, hate speech, jailbreaking, multilingual harms, and over-refusal, reducing false positive rates by up to 40x relative to specialized safety models. A single model trained only on safe English text transfers effectively to diverse domains and over 14 languages without retraining. Finally, we demonstrate production readiness by integrating a GPU-optimized version into vLLM, enabling continuous guardrailing during token generation with less than 6% overhead even under dense evaluation intervals on large-scale workloads.

Veronica Thai, Rui Li, Meng Ling et al.

Interpretation of giga-pixel whole-slide images (WSIs) is an important but difficult task for pathologists. Their diagnostic accuracy is estimated to average around 70%. Adding a second pathologist does not substantially improve decision consistency. The field lacks adequate behavioral data to explain diagnostic errors and inconsistencies. To fill in this gap, we present PathoGaze1.0, a comprehensive behavioral dataset capturing the dynamic visual search and decision-making processes of the full diagnostic workflow during cancer diagnosis. The dataset comprises 18.69 hours of eye-tracking, mouse interaction, stimulus tracking, viewport navigation, and diagnostic decision data (EMSVD) collected from 19 pathologists interpreting 397 WSIs. The data collection process emphasizes ecological validity through an application-grounded testbed, called PTAH. In total, we recorded 171,909 fixations, 263,320 saccades, and 1,867,362 mouse interaction events. In addition, such data could also be used to improve the training of both pathologists and AI systems that might support human experts. All experiments were preregistered at https://osf.io/hj9a7, and the complete dataset along with analysis code is available at https://go.osu.edu/pathogaze.

Vishal Dey, Raghu Machiraju, Xia Ning

Recent advances in molecular machine learning, especially deep neural networks such as Graph Neural Networks (GNNs) for predicting structure activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neural networks are limited by the requirement of large amounts of training data. In order to cope with limited training data for a target task, transfer learning for SAR modeling has been recently adopted to leverage information from data of related tasks. In this work, in contrast to the popular parameter-based transfer learning such as pretraining, we develop novel deep transfer learning methods TAc and TAc-fc to leverage source domain data and transfer useful information to the target domain. TAc learns to generate effective molecular features that can generalize well from one domain to another, and increase the classification performance in the target domain. Additionally, TAc-fc extends TAc by incorporating novel components to selectively learn feature-wise and compound-wise transferability. We used the bioassay screening data from PubChem, and identified 120 pairs of bioassays such that the active compounds in each pair are more similar to each other compared to its inactive compounds. Our experiments clearly demonstrate that TAc achieves significant improvement over all baselines across a large number of target tasks. Furthermore, although TAc-fc achieves slightly worse ROC-AUC on average compared to TAc, TAc-fc still achieves the best performance on more tasks in terms of PR-AUC and F1 compared to other methods. In summary, TAc-fc is also found to be a strong model with competitive or even better performance than TAc on a notable number of target tasks.

Chaitanya Kulkarni, Wei Xu, Alan Ritter et al.

We describe an effort to annotate a corpus of natural language instructions consisting of 622 wet lab protocols to facilitate automatic or semi-automatic conversion of protocols into a machine-readable format and benefit biological research. Experimental results demonstrate the utility of our corpus for developing machine learning approaches to shallow semantic parsing of instructional texts. We make our annotated Wet Lab Protocol Corpus available to the research community.

Hao Ding, Chao Wang, Kun Huang et al.

Background: Cancers are highly heterogeneous with different subtypes. These subtypes often possess different genetic variants, present different pathological phenotypes, and most importantly, show various clinical outcomes such as varied prognosis and response to treatment and likelihood for recurrence and metastasis. Recently, integrative genomics (or panomics) approaches are often adopted with the goal of combining multiple types of omics data to identify integrative biomarkers for stratification of patients into groups with different clinical outcomes. Results: In this paper we present a visual analytic system called Interactive Genomics Patient Stratification explorer (iGPSe) which significantly reduces the computing burden for biomedical researchers in the process of exploring complicated integrative genomics data. Our system integrates unsupervised clustering with graph and parallel sets visualization and allows direct comparison of clinical outcomes via survival analysis. Using a breast cancer dataset obtained from the The Cancer Genome Atlas (TCGA) project, we are able to quickly explore different combinations of gene expression (mRNA) and microRNA features and identify potential combined markers for survival prediction. Conclusions: Visualization plays an important role in the process of stratifying given population patients. Visual tools allowed for the selection of possibly features across various datasets for the given patient population. We essentially made a case for visualization for a very important problem in translational informatics.