8 papers
What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration
Cencen Liu, Wen Yin, Dongyang Zhang +6
All-in-one image restoration aims to handle diverse degradations within a unified framework. Existing methods commonly encode heterogeneous degradation conditions in a shared laten…
Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences
Mingyang Li, Yurou Liu, Jieping Ye +3
In this report, we present LOGOS (Language Of Generative Objects in Science), a scientific generative language model that unifies heterogeneous tasks across the natural sciences wi…
One Model, Two Minds: Task-Conditioned Reasoning for Unified Image Quality and Aesthetic Assessment
Wen Yin, Cencen Liu, Dingrui Liu +3
Unifying Image Quality Assessment (IQA) and Image Aesthetic Assessment (IAA) in a single multimodal large language model is appealing, yet existing methods adopt a task-agnostic re…
Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment
Ying Ba, Tianyu Zhang, Yalong Bai +4
Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have fai…
Regulatory DNA sequence Design with Reinforcement Learning
Zhao Yang, Bing Su, Chuan Cao +1
Cis-regulatory elements (CREs), such as promoters and enhancers, are relatively short DNA sequences that directly regulate gene expression. The fitness of CREs, measured by their a…
Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing
Wenyi Mo, Tianyu Zhang, Yalong Bai +2
Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to p…
Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training
Jinxia Yang, Bing Su, Wayne Xin Zhao +1
Medical vision-language pre-training methods mainly leverage the correspondence between paired medical images and radiological reports. Although multi-view spatial images and tempo…
Dynamic Prompt Optimizing for Text-to-Image Generation
Wenyi Mo, Tianyu Zhang, Yalong Bai +3
Text-to-image generative models, specifically those based on diffusion models like Imagen and Stable Diffusion, have made substantial advancements. Recently, there has been a surge…