collaborators

5 papers

cs.LG2026

Hidden Boundary Motion in Transformer Optimization: Function-Space Orthogonalization of Affine Weight and Bias Updates

Zhang Gongyue, Sheng Yixuan, Liu donghan +3

Weights and biases are normally optimized as separate parameter tensors, yet they do not represent separate functions when the input to an affine layer has nonzero mean. For an aff…

cs.LG2026

The Anatomy of Implicit Bias: Information Allocation in Neural Network Training

Zhang Gongyue, Wang Zhiyong, Liu Donghan +3

Implicit bias is usually explained as the preference of an optimization process for certain final solutions and their geometry. This view helps explain where a model finally stops.…

cs.CV2026

Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation

Haoyu Ji, Bowen Chen, Zhihao Yang +6

Skeleton-based Temporal Action Segmentation (STAS) seeks to densely segment and classify diverse actions within long, untrimmed skeletal motion sequences. However, existing STAS me…

cs.CV2026

LaDy: Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal Modulation

Haoyu Ji, Xueting Liu, Yu Gao +5

Skeleton-based Temporal Action Segmentation (STAS) aims to densely parse untrimmed skeletal sequences into frame-level action categories. However, existing methods, while proficien…

cs.CV2025

Text-Derived Relational Graph-Enhanced Network for Skeleton-Based Action Segmentation

Haoyu Ji, Bowen Chen, Weihong Ren +4

Skeleton-based Temporal Action Segmentation (STAS) aims to segment and recognize various actions from long, untrimmed sequences of human skeletal movements. Current STAS methods ty…