Wei Wang

Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms

Rethinking Consistent Multi-Label Classification Under Inexact Supervision

Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning

Learning from Label Proportions via Proportional Value Classification

Learning Robust Diffusion Models from Imprecise Supervision

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers

Realistic Evaluation of Deep Partial-Label Learning Algorithms

Delving into Weakly Supervised Learning with Pre-Trained Models