Bo Han
- Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective
- Detecting Generated Images by Fitting Natural Image Distributions
- Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples
- Epistemic Uncertainty for Generated Image Detection
- FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning
- Generative Model Inversion Through the Lens of the Manifold Hypothesis
- Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning
- Learning to Instruct for Visual Instruction Tuning
- Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection
- Practical Kernel Selection for Kernel-based Conditional Independence Test
- Unlocker: Disentangle the Deadlock of Learning between Label-noisy and Long-tailed Data