9 papers · 1 filter
Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher
Shiyi Zhang, Mushui Liu, Yunze Tong +8
On-policy distillation (OPD), which leverages a pre-trained, specialized teacher model to provide dense supervisory signals, has achieved significant success in Large Language Mode…
InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter
Yunze Tong, Mushui Liu, Canyu Zhao +9
With large pretrained models, existing methods have effectively improved instruction-based video editing. However, most of them rely on an in-place editing assumption. They align t…
LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing
Jianzong Wu, Hao Lian, Jiongfan Yang +12
Developing unified video generation and editing models capable of interpreting interleaved multimodal inputs is a promising yet challenging frontier field. Existing unified framewo…
DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
Peng Zhang, Guanghao Zhang, Wanggui He +10
Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video…
PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement Learning
Jinlong Liu, Wanggui He, Peng Zhang +3
Reinforcement learning (RL) can improve the prompt following capability of text-to-image (T2I) models, yet obtaining high-quality reward signals remains challenging: CLIP Score is…
Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
Yunze Tong, Mushui Liu, Canyu Zhao +7
Deploying GRPO on Flow Matching models has proven effective for text-to-image generation. However, existing paradigms typically propagate an outcome-based reward to all preceding d…
Boosting MLLM Reasoning with Text-Debiased Hint-GRPO
Qihan Huang, Weilong Dai, Jinlong Liu +6
MLLM reasoning has drawn widespread research for its excellent problem-solving capability. Current reasoning methods fall into two types: PRM, which supervises the intermediate rea…
PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
Qihan Huang, Weilong Dai, Jinlong Liu +4
Finetuning-free personalized image generation can synthesize customized images without test-time finetuning, attracting wide research interest owing to its high efficiency. Current…
Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation
Qihan Huang, Siming Fu, Jinlong Liu +3
Personalized text-to-image generation methods can generate customized images based on the reference images, which have garnered wide research interest. Recent methods propose a fin…