activity
20242026
collaborators

6 papers

cs.LG2026

High Rank Matrix Completion via Grassmannian Proxy Fusion

Huanran Li, Jeremy Johnson, Daniel Pimentel-Alarcón

This paper approaches high-rank matrix completion (HRMC) by filling missing entries in a data matrix where columns lie near a union of subspaces, clustering these columns, and iden…

cs.CV2026

Subspace Clustering on Incomplete Data with Self-Supervised Contrastive Learning

Huanran Li, Daniel Pimentel-Alarcón

Subspace clustering aims to group data points that lie in a union of low-dimensional subspaces and finds wide application in computer vision, hyperspectral imaging, and recommendat…

cs.LG2025

Semi-Supervised Contrastive Learning with Orthonormal Prototypes

Huanran Li, Manh Nguyen, Daniel Pimentel-Alarcón

Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. Ho…

cs.CV2025

From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling

Jinhong Lin, Cheng-En Wu, Huanran Li +3

Masked Image Modeling (MIM) has emerged as a powerful self-supervised learning paradigm for visual representation learning, enabling models to acquire rich visual representations b…

cs.LG2024

Preventing Collapse in Contrastive Learning with Orthonormal Prototypes (CLOP)

Huanran Li, Manh Nguyen, Daniel Pimentel-Alarcón

Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. Ho…

cs.LG2024

Deep Fusion: Capturing Dependencies in Contrastive Learning via Transformer Projection Heads

Huanran Li, Daniel Pimentel-Alarcón

Contrastive Learning (CL) has emerged as a powerful method for training feature extraction models using unlabeled data. Recent studies suggest that incorporating a linear projectio…