10 papers
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…
LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models
Lu Liu, Huiyu Duan, Chenxin Zhu +6
Large-scale generative models have demonstrated remarkable capabilities across image generation and editing tasks. However, their performance in low-level vision tasks, which requi…
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…
D-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
Qian Zeng, Jie Song, Han Zheng +2
Diffusion models have achieved cutting-edge performance in image generation. However, their lengthy denoising process and computationally intensive score estimation network impede…
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…
Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models
Yi Wang, Mushui Liu, Wanggui He +13
Unified generative models have shown remarkable performance in text and image generation. For image synthesis tasks, they adopt straightforward text-to-image (T2I) generation. Howe…
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…
LG-CAV: Train Any Concept Activation Vector with Language Guidance
Qihan Huang, Jie Song, Mengqi Xue +6
Concept activation vector (CAV) has attracted broad research interest in explainable AI, by elegantly attributing model predictions to specific concepts. However, the training of C…
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…
On the Evaluation Consistency of Attribution-based Explanations
Jiarui Duan, Haoling Li, Haofei Zhang +5
Attribution-based explanations are garnering increasing attention recently and have emerged as the predominant approach towards \textit{eXplanable Artificial Intelligence}~(XAI). H…