7 papers
Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
Advaith Ravishankar, Serena Liu, Mingyang Wang +11
State-of-the-art text-to-image models produce high-quality images, but inference remains expensive as generation requires several sequential ODE or denoising steps. Native one-step…
MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts
Weiyue Li, Ruizhi Qian, Yi Li +5
Large language models (LLMs) are widely explored for reasoning-intensive research tasks, yet resources for testing whether they can infer scientific conclusions from structured bio…
On Demographic Group Fairness Guarantees in Deep Learning
Yan Luo, Congcong Wen, Min Shi +3
We present a theoretical framework analyzing the relationship between data distributions and fairness guarantees in equitable deep learning. We establish novel bounds that account…
CurveFlow: Curvature-Guided Flow Matching for Image Generation
Yan Luo, Drake Du, Hao Huang +2
Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the imag…
FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRA
Minghan Li, Congcong Wen, Yu Tian +5
Fairness remains a critical concern in healthcare, where unequal access to services and treatment outcomes can adversely affect patient health. While Federated Learning (FL) presen…
FairDiffusion: Enhancing Equity in Latent Diffusion Models via Fair Bayesian Perturbation
Yan Luo, Muhammad Osama Khan, Congcong Wen +6
Recent progress in generative AI, especially diffusion models, has demonstrated significant utility in text-to-image synthesis. Particularly in healthcare, these models offer immen…