3 papers
cs.AI2026
DI-Bench: Systematically Generating In-Domain Data Intelligence Benchmarks for Enterprise Agents
Jiangyun Zhang, Kristen Surrao, Torpong Nitayanont +10
Evaluating enterprise agents on domain-specific benchmarks is critical, yet public benchmarks rarely evaluate whether agents can integrate business knowledge with analytical comput…
cs.LG2025
An Effective Flow-based Method for Positive-Unlabeled Learning: 2-HNC
Dorit Hochbaum, Torpong Nitayanont
In many scenarios of binary classification, only positive instances are provided in the training data, leaving the rest of the data unlabeled. This setup, known as positive-unlabel…
cs.LG2025
Confidence HNC: A Network Flow Technique for Binary Classification with Noisy Labels
Dorit Hochbaum, Torpong Nitayanont
We consider here a classification method that balances two objectives: large similarity within the samples in the cluster, and large dissimilarity between the cluster and its compl…