3 papers
cs.CV2026
Head-Aware Key-Value Compression for Efficient Autoregressive Image Generation
Guotao Liang, Baoquan Zhang, Zhiyuan Wen +1
Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching previously generated visual…
cs.CV2025
Improved Masked Image Generation with Knowledge-Augmented Token Representations
Guotao Liang, Baoquan Zhang, Zhiyuan Wen +2
Masked image generation (MIG) has demonstrated remarkable efficiency and high-fidelity images by enabling parallel token prediction. Existing methods typically rely solely on the m…
cs.CV2025
Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text
Guotao Liang, Baoquan Zhang, Zhiyuan Wen +4
Image quantization is a crucial technique in image generation, aimed at learning a codebook that encodes an image into a discrete token sequence. Recent advancements have seen rese…