activity
20242026
collaborators

10 papers

cs.CV2026

Autoregressive Visual Generation Needs a Prologue

Bowen Zheng, Weijian Luo, Guang Yang +2

In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy…

cs.CV2026

Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation

Bowen Zheng, Weijian Luo, Guang Yang +2

Most discrete visual tokenizers rely on a default design: every position in the sequence shares the same codebook. Researchers try to scale the codebook size to get better reco…

cs.CV2026

TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward

Yihong Luo, Tianyang Hu, Weijian Luo +1

While few-step generative models have enabled powerful image and video generation at significantly lower cost, generic reinforcement learning (RL) paradigms for few-step models rem…

cs.CV2025

Self-Guidance: Boosting Flow and Diffusion Generation on Their Own

Tiancheng Li, Weijian Luo, Zhiyang Chen +2

Proper guidance strategies are essential to achieve high-quality generation results without retraining diffusion and flow-based text-to-image models. Existing guidance either requi…

cs.CV2025

Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation

Yihong Luo, Tianyang Hu, Weijian Luo +2

This paper addresses the challenge of achieving high-quality and fast image generation that aligns with complex human preferences. While recent advancements in diffusion models and…

cs.CV2025

David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training

Weijian Luo, Colin Zhang, Debing Zhang +1

We propose Diff-Instruct* (DI*), a data-efficient post-training approach for one-step text-to-image generative models to improve its human preferences without requiring image data.…