activity
20242026
collaborators

10 papers

cs.CV2026

HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models

Jiazi Bu, Pengyang Ling, Yujie Zhou +10

Text-Image-to-Video (TI2V) models are an emerging unified architecture, where a single model simultaneously supports text-to-video (T2V) and image-to-video (I2V) generation. Given…

cs.CV2026

AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO

Jiazi Bu, Pengyang Ling, Yujie Zhou +8

Group Relative Policy Optimization (GRPO) has demonstrated remarkable success in aligning text-to-image (T2I) flow models with human preferences. However, we have identified that t…

cs.CV2026

Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance Classifier

Yujie Zhou, Pengyang Ling, Jiazi Bu +2

In practical AI workflows, complex tasks often involve chaining multiple generative models, such as using a video or 3D generation model after a 2D image generator. However, distri…

cs.CV2026

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

Jiazi Bu, Pengyang Ling, Yujie Zhou +8

Group Relative Policy Optimization (GRPO) has emerged as a powerful framework for preference alignment in text-to-image (T2I) flow models. However, we observe that the standard par…

cs.LG2025

Fine-Grained GRPO for Precise Preference Alignment in Flow Models

Yujie Zhou, Pengyang Ling, Jiazi Bu +5

The incorporation of online reinforcement learning (RL) into diffusion and flow-based generative models has recently gained attention as a powerful paradigm for aligning model beha…

cs.CV2025

Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy

Xiaoxiao Ma, Feng Zhao, Pengyang Ling +6

In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower informat…