9 papers
ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Models
Rusali Saha, Nitya Khurana, Ruihong Huang +1
Cultural attitudes and social norms evolve over time, yet most cultural benchmarks for large language models (LLMs) treat culture as a static attribute of a country or region. We i…
From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation
Xingjian Wang, Zhao Wang, Taihang Hu +17
Large-scale image generation has benefited from advances in data scale, quality, rebalancing, and recaptioning, yet conventional pipelines typically optimize task-specific datasets…
Exploring the Performance Frontier of Compact Unified Image Generation Models
Taihang Hu, Zhao Wang, Zuan Gao +20
We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore how far a relatively small visua…
CPI-Bench: A Comprehensive, Practical and Intelligent Benchmark for Real-World Image Editing
Qinye Zhou, Jun Zheng, Yongchao Du +17
With the rapid advancement of image editing models and their widespread application across various domains, there is an increasingly urgent need to deploy these model capabilities…
Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items
Mengting Chen, Zhengrui Chen, Yongchao Du +16
Recent advances in image generation and editing have opened new opportunities for virtual try-on. However, existing methods still struggle to meet complex real-world demands. We pr…
CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness
Zhihang Liu, Chen-Wei Xie, Bin Wen +9
Visual captioning benchmarks have become outdated with the emergence of modern multimodal large language models (MLLMs), as the brief ground-truth sentences and traditional metrics…
How Control Information Influences Multilingual Text Image Generation and Editing?
Boqiang Zhang, Zuan Gao, Yadong Qu +1
Visual text generation has significantly advanced through diffusion models aimed at producing images with readable and realistic text. Recent works primarily use a ControlNet-based…
Self-Supervised Pre-training with Symmetric Superimposition Modeling for Scene Text Recognition
Zuan Gao, Yuxin Wang, Yadong Qu +4
In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual…
Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing
Boqiang Zhang, Hongtao Xie, Zuan Gao +1
Scene text images contain not only style information (font, background) but also content information (character, texture). Different scene text tasks need different information, bu…