activity
20222026
most citedGroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compression

20 citations · 22 across the 9 of their papers we have counts for

collaborators
Showing 2025Show all

1 paper · 1 filter

cs.CV2025

Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation

Daxin Li, Yuanchao Bai, Kai Wang +3

Autoregressive (AR) models, the theoretical performance benchmark for learned lossless image compression, are often dismissed as impractical due to prohibitive computational cost.…