5 papers · 1 filter
A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle
Guancheng Zhou, Yisi Luo, Zhengfu He +5
Most current paradigms in visual mechanistic interpretability (MI) remain confined to interpreting internal units of the vision model via heuristic methods (e.g., top- activatio…
TenExp: Mixture-of-Experts-Based Tensor Decomposition Structure Search Framework
Ting-Wei Zhou, Xi-Le Zhao, Sheng Liu +3
Recently, tensor decompositions continue to emerge and receive increasing attention. Selecting a suitable tensor decomposition to exactly capture the low-rank structures behind the…
Continuous Representation Methods, Theories, and Applications: An Overview and Perspectives
Yisi Luo, Xile Zhao, Deyu Meng
Recently, continuous representation methods emerge as novel paradigms that characterize the intrinsic structures of real-world data through function representations that map positi…
Cross-Frequency Implicit Neural Representation with Self-Evolving Parameters
Chang Yu, Yisi Luo, Kai Ye +2
Implicit neural representation (INR) has emerged as a powerful paradigm for visual data representation. However, classical INR methods represent data in the original space mixed wi…
NeurTV: Total Variation on the Neural Domain
Yisi Luo, Xile Zhao, Kai Ye +1
Recently, we have witnessed the success of total variation (TV) for many imaging applications. However, traditional TV is defined on the original pixel domain, which limits its pot…