7 citations · 11 across the 8 of their papers we have counts for
9 papers
Spherical Leech Quantization for Visual Tokenization and Generation
Yue Zhao, Hanwen Jiang, Zhenlin Xu +3
Non-parametric quantization has received much attention due to its efficiency on parameters and scalability to a large codebook. In this paper, we present a unified formulation of…
Ordinal Label-Distribution Learning with Constrained Asymmetric Priors for Imbalanced Retinal Grading
Nagur Shareef Shaik, Teja Krishna Cherukuri, Adnan Masood +2
Diabetic retinopathy grading is inherently ordinal and long-tailed, with minority stages being scarce, heterogeneous, and clinically critical to detect accurately. Conventional met…
Artist-Created Mesh Generation from Raw Observation
Yao He, Youngjoong Kwon, Wenxiao Cai +1
We present an end-to-end framework for generating artist-style meshes from noisy or incomplete point clouds, such as those captured by real-world sensors like LiDAR or mobile RGB-D…
Curriculum-Guided Layer Scaling for Language Model Pretraining
Karanpartap Singh, Neil Band, Ehsan Adeli
As the cost of pretraining large language models grows, there is continued interest in strategies to improve learning efficiency during this core training stage. Motivated by cogni…
SOE: SO(3)-Equivariant 3D MRI Encoding
Shizhe He, Magdalini Paschali, Jiahong Ouyang +3
Representation learning has become increasingly important, especially as powerful models have shifted towards learning latent representations before fine-tuning for downstream task…
A Gentle Approach to Multi-Sensor Fusion Data Using Linear Kalman Filter
Parsa Veysi, Mohsen Adeli, Nayerosadat Peirov Naziri +1
This research paper delves into the Linear Kalman Filter (LKF), highlighting its importance in merging data from multiple sensors. The Kalman Filter is known for its recursive solu…
Enforcing Conditional Independence for Fair Representation Learning and Causal Image Generation
Jensen Hwa, Qingyu Zhao, Aditya Lahiri +3
Conditional independence (CI) constraints are critical for defining and evaluating fairness in machine learning, as well as for learning unconfounded or causal representations. Tra…
Combining Counterfactuals With Shapley Values To Explain Image Models
Aditya Lahiri, Kamran Alipour, Ehsan Adeli +1
With the widespread use of sophisticated machine learning models in sensitive applications, understanding their decision-making has become an essential task. Models trained on tabu…
Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces
Kamran Alipour, Aditya Lahiri, Ehsan Adeli +2
Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfact…