8 papers
Dynamic Pyramid Network for Efficient Multimodal Large Language Model
Hao Ai, Kunyi Wang, Zezhou Wang +7
Multimodal large language models (MLLMs) have demonstrated impressive performance in various vision-language (VL) tasks, but their expensive computations still limit the real-world…
InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention
Qiang Xiang, Shuang Sun, Binglei Li +6
Diffusion models have demonstrated remarkable capabilities in generating high-quality images. Recent advancements in Layout-to-Image (L2I) generation have leveraged positional cond…
Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation
Jiahao Cheng, Tiancheng Su, Jia Yuan +5
Large Language Models (LLMs) often exhibit \textit{hallucinations}, generating factually incorrect or semantically irrelevant content in response to prompts. Chain-of-Thought (CoT)…
Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model
Yuxuan Zhang, Yirui Yuan, Yiren Song +1
Current makeup transfer methods are limited to simple makeup styles, making them difficult to apply in real-world scenarios. In this paper, we introduce Stable-Makeup, a novel diff…
StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation
Zhengguang Zhou, Jing Li, Huaxia Li +2
Tuning-free personalized image generation methods have achieved significant success in maintaining facial consistency, i.e., identities, even with multiple characters. However, the…
Target-Driven Distillation: Consistency Distillation with Target Timestep Selection and Decoupled Guidance
Cunzheng Wang, Ziyuan Guo, Yuxuan Duan +4
Consistency distillation methods have demonstrated significant success in accelerating generative tasks of diffusion models. However, since previous consistency distillation method…