8 papers
APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation
Sirui Zhang, Fangyun Wei, Dong Chen +5
Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training distributions. We introduce…
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Dong Chen, Fangyun Wei, Ziyu Wan +18
We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters acro…
VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer
Yanning Hou, Peiyuan Li, Zirui Liu +4
Zero-shot anomaly detection (ZSAD) requires detecting and localizing anomalies without access to target-class anomaly samples. Mainstream methods rely on vision-language models (VL…
Real, Fake, or Manipulated? Detecting Machine-Influenced Text
Yitong Wang, Zhongping Zhang, Margherita Piana +3
Large Language Model (LLMs) can be used to write or modify documents, presenting a challenge for understanding the intent behind their use. For example, benign uses may involve usi…
OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning
Yuan Gong, Xionghui Wang, Jie Wu +3
In this paper, we introduce OneReward, a unified reinforcement learning framework that enhances the model's generative capabilities across multiple tasks under different evaluation…
DreamFuse: Adaptive Image Fusion with Diffusion Transformer
Junjia Huang, Pengxiang Yan, Jiyang Liu +5
Image fusion seeks to seamlessly integrate foreground objects with background scenes, producing realistic and harmonious fused images. Unlike existing methods that directly insert…
ByteEdit: Boost, Comply and Accelerate Generative Image Editing
Yuxi Ren, Jie Wu, Yanzuo Lu +11
Recent advancements in diffusion-based generative image editing have sparked a profound revolution, reshaping the landscape of image outpainting and inpainting tasks. Despite these…
LLMGA: Multimodal Large Language Model based Generation Assistant
Bin Xia, Shiyin Wang, Yingfan Tao +2
In this paper, we introduce a Multimodal Large Language Model-based Generation Assistant (LLMGA), leveraging the vast reservoir of knowledge and proficiency in reasoning, comprehen…