Faithful Generation
Faithful generation focuses on creating outputs—text, images, audio, code, or other data—that accurately reflect a given input or prompt, prioritizing correctness and adherence to specifications. Current research emphasizes improving the fidelity and controllability of generation using various model architectures, including diffusion models, transformers, and variational autoencoders, often incorporating techniques like retrieval-augmented generation and multi-agent frameworks. This field is significant for advancing AI capabilities across numerous domains, from improving large language model evaluations and enhancing human-computer interaction to creating more realistic synthetic data for training and analysis in various scientific fields.
Papers
ChartLlama: A Multimodal LLM for Chart Understanding and Generation
Yucheng Han, Chi Zhang, Xin Chen, Xu Yang, Zhibin Wang, Gang Yu, Bin Fu, Hanwang Zhang
Generation of patient specific cardiac chamber models using generative neural networks under a Bayesian framework for electroanatomical mapping
Sunil Mathew, Jasbir Sra, Daniel B. Rowe
Decouple Content and Motion for Conditional Image-to-Video Generation
Cuifeng Shen, Yulu Gan, Chen Chen, Xiongwei Zhu, Lele Cheng, Tingting Gao, Jinzhi Wang
Paragraph-to-Image Generation with Information-Enriched Diffusion Model
Weijia Wu, Zhuang Li, Yefei He, Mike Zheng Shou, Chunhua Shen, Lele Cheng, Yan Li, Tingting Gao, Di Zhang, Zhongyuan Wang
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
Weixiang Yan, Haitian Liu, Yunkun Wang, Yunzhe Li, Qian Chen, Wen Wang, Tingyu Lin, Weishan Zhao, Li Zhu, Hari Sundaram, Shuiguang Deng
Diffusion-based generation of Histopathological Whole Slide Images at a Gigapixel scale
Robert Harb, Thomas Pock, Heimo Müller