FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders Paper • 2609.31620 • Published 11 days ago • 160
Swift Parameter-free Attention Network for Efficient Super-Resolution Paper • 2311.12770 • Published Nov 21, 2023 • 2
PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection Paper • 2510.23594 • Published Oct 27, 2025 • 6