Author

Po-Yi Lu

Observed name: Lu, Po-Yi

Institutions: National Taiwan University, Texas A&M University

Observed institutions: National Taiwan University, Texas A&M University

OpenAlex ID: A5111335431

The Unexplored Potential of Vision-Language Models for Generating Large-Scale Complementary-Label Learning Data

2025 · Tan-Ha Mai, Nai-Xuan Ye, et al. · Lecture notes in computer science · 7

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks

2024 · Chew, Oscar, Lu, Po-Yi, et al. · arXiv (Cornell University) · 5

An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasets

2023 · Lu, Po-Yi, Cheng, Yi-Jie, et al. · arXiv (Cornell University) · 4

Are We Really Measuring Forgetting? Pitfalls in Evaluating Machine Unlearning for Multimodal LLMs

2026 · Chew, Oscar, Lu, Po-Yi, et al. · arXiv (Cornell University)

TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals

2026 · Xue, Zihan, Lu, Po-Yi, et al. · arXiv (Cornell University)

Works count: 5

Citation count: 16

H-index: 3

I10-index: