4 papers · 1 filter
Parallel Jacobi Decoding for Fast Autoregressive Image Generation
Boya Liao, Ying Li, Siyong Jian +1
Autoregressive (AR) models have demonstrated remarkable performance in generating high-fidelity images. However, their inherently sequential next-token prediction leads to signific…
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
Siyong Jian, Siyuan Li, Luyuan Zhang +5
Discrete autoregressive (AR) text-to-image (T2I) models pair a VQ tokenizer with an AR policy, and current post-training pipelines optimize only the policy while keeping the VQ dec…
SSD: Spatial-Semantic Head Decoupling for Efficient Autoregressive Image Generation
Siyong Jian, Huan Wang
Autoregressive image generation models like Janus-Pro produce high-quality images, but at the significant cost of high memory and ever-growing computational demands due to the larg…
MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
Xin Jin, Siyuan Li, Siyong Jian +2
Vision-language alignment in multi-modal large language models (MLLMs) relies on supervised fine-tuning (SFT) or reinforcement learning (RL). To align multi-modal large language mo…