FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders Paper • 2609.31620 • Published 9 days ago • 159
VIScore: Diagnosing Planning-Relevant Quality in Latent World Models Paper • 2608.11174 • Published Aug 11
VISReg: Variance-Invariance-Sketching Regularization for JEPA training Paper • 2606.02572 • Published Jun 1 • 4
LogicNet: A Logical Consistency Embedded Face Attribute Learning Network Paper • 2311.11208 • Published Nov 19, 2023
DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models Paper • 2505.09655 • Published May 14, 2025
Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors Paper • 2409.02979 • Published Sep 4, 2024 • 1