2 citations · 3 across the 17 of their papers we have counts for
20 papers
CapField-OPD: Learning Continuous Capability Fields via Joint-Anchored Multi-Teacher On-Policy Distillation for Flow Models
Pengyang Ling, Yujie Zhou, Jiazi Bu +6
Reward-specialized post-training produces strong experts for flow-based generative models, while multi-teacher on-policy distillation (OPD) consolidates their capabilities into a s…
WorldReward: Reward Modeling for Camera-Conditioned World Models
Yibin Wang, Zehan Wang, Junshu Tang +13
Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected scene changes while appearance, geometry, and temporal dynamics re…
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…
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…
Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition
Pengyang Ling, Jiazi Bu, Yujie Zhou +6
Group Relative Policy Optimization(GRPO) has emerged as an effective paradigm for aligning flow-based generative models with human preferences. However, the high cost of group roll…
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…
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…
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…
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…
DiCache: Let Diffusion Model Determine Its Own Cache
Jiazi Bu, Pengyang Ling, Yujie Zhou +4
Recent years have witnessed the rapid development of acceleration techniques for diffusion models, especially caching-based acceleration methods. These studies seek to answer two f…
HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
Jiazi Bu, Pengyang Ling, Yujie Zhou +7
Text-to-image (T2I) diffusion/flow models have drawn considerable attention recently due to their remarkable ability to deliver flexible visual creations. Still, high-resolution im…
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
Yujie Zhou, Jiazi Bu, Pengyang Ling +10
Recent advancements in image relighting models, driven by large-scale datasets and pre-trained diffusion models, have enabled the imposition of consistent lighting. However, video…
ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way
Jiazi Bu, Pengyang Ling, Pan Zhang +6
The text-to-video (T2V) generation models, offering convenient visual creation, have recently garnered increasing attention. Despite their substantial potential, the generated vide…
Single Image Dehazing Using Scene Depth Ordering
Pengyang Ling, Huaian Chen, Xiao Tan +2
Images captured in hazy weather generally suffer from quality degradation, and many dehazing methods have been developed to solve this problem. However, single image dehazing probl…
MotionClone: Training-Free Motion Cloning for Controllable Video Generation
Pengyang Ling, Jiazi Bu, Pan Zhang +6
Motion-based controllable video generation offers the potential for creating captivating visual content. Existing methods typically necessitate model training to encode particular…
ReasonPix2Pix: Instruction Reasoning Dataset for Advanced Image Editing
Ying Jin, Pengyang Ling, Xiaoyi Dong +3
Instruction-based image editing focuses on equipping a generative model with the capacity to adhere to human-written instructions for editing images. Current approaches typically c…
Seed Optimization with Frozen Generator for Superior Zero-shot Low-light Enhancement
Yuxuan Gu, Yi Jin, Ben Wang +6
In this work, we observe that the generators, which are pre-trained on massive natural images, inherently hold the promising potential for superior low-light image enhancement agai…
Masked Pre-training Enables Universal Zero-shot Denoiser
Xiaoxiao Ma, Zhixiang Wei, Yi Jin +5
In this work, we observe that model trained on vast general images via masking strategy, has been naturally embedded with their distribution knowledge, thus spontaneously attains t…
Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement
Zhixiang Wei, Lin Chen, Tao Tu +3
Most prior semantic segmentation methods have been developed for day-time scenes, while typically underperforming in night-time scenes due to insufficient and complicated lighting…
FreeDrag: Feature Dragging for Reliable Point-based Image Editing
Pengyang Ling, Lin Chen, Pan Zhang +3
To serve the intricate and varied demands of image editing, precise and flexible manipulation in image content is indispensable. Recently, Drag-based editing methods have gained im…