23 citations · 26 across the 4 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.CV2024
ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs
Yin Xie, Kaicheng Yang, Peirou Liang +7
Large Multimodal Models (LMMs) often face a modality representation gap during pretraining: while language embeddings remain stable, visual representations are highly sensitive to…
cs.CV2024
VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling
Qian Zhang, Xiangzi Dai, Ninghua Yang +3
VAR is a new generation paradigm that employs 'next-scale prediction' as opposed to 'next-token prediction'. This innovative transformation enables auto-regressive (AR) transformer…