10 papers
VIScore: Diagnosing Planning-Relevant Quality in Latent World Models
Haiyu Wu, Randall Balestriero, Morgan Levine
Regulating the latent space to an isotropic Gaussian distribution provides a stable and information-maximized landscape for world model planning. However, the latent space property…
ScaleErasure: Inference-Time Minimal Intervention for Precise Concept Erasure in Next-Scale Autoregressive Image Generation
Cong Wang, Haiyu Wu, Zhiwei Jiang +4
Concept erasure aims to prevent image generative models from producing unsafe content while preserving their general generative capability. Meanwhile, next-scale autoregressive (AR…
VISReg: Variance-Invariance-Sketching Regularization for JEPA training
Haiyu Wu, Randall Balestriero, Morgan Levine
Self-supervised learning methods prevent embedding collapse via modeling heuristics or explicit regularization of the embedding space. Among the latter, VICReg decomposes regulariz…
On the Illusion of Gender Bias in Face Recognition: Explaining the Fairness Issue Through Non-demographic Attributes
Paul Jonas Kurz, Haiyu Wu, Rouqaiah Al-Refai +2
Face recognition systems (FRS) exhibit significant accuracy differences based on the user's gender. Since such a gender gap reduces the trustworthiness of FRS, more recent efforts…
Goldilocks Test Sets for Face Verification
Haiyu Wu, Sicong Tian, Aman Bhatta +6
Reported face verification accuracy has reached a plateau on current well-known test sets. As a result, some difficult test sets have been assembled by reducing the image quality o…
Restricted Receptive Fields for Face Verification
Kagan Ozturk, Aman Bhatta, Haiyu Wu +2
Understanding how deep neural networks make decisions is crucial for analyzing their behavior and diagnosing failure cases. In computer vision, a common approach to improve interpr…