Jinhui Zhu

In e-commerce platforms, visual content plays a pivotal role in capturing and retaining audience attention. A high-quality and aesthetically designed product background image can quickly grab consumers' attention, and increase their confidence in taking actions, such as making a purchase. Recently, diffusion models have achieved profound advancements, rendering product background generation a promising avenue for exploration. However, text-guided diffusion models require meticulously crafted prompts. The diverse range of products makes it challenging to compose prompts that result in visually appealing and semantically appropriate background scenes. Current work has made great efforts on creating prompts through expert-crafted rules or specialized fine-tuning of large language models, but it still relies on detailed human inputs and often falls short in generating desirable results by e-commerce standards. In this paper, we propose Product2Img, a novel prompt-free diffusion model with automatic training data refinement strategy for product background generation. Product2Img employs Contrastive Background Alignment (CBA) for the text encoder to enhance the relevant background perception ability in the diffusion generation process, without the need for specific background prompts. Meanwhile, we develope the Iterative Data Refinement with Self-improved Large Multimodal Model (IDR-LMM), a framework that iteratively enhances the data selection capability of LMM for diffusion model training, thereby yielding continuous performance improvements. Furthermore, we establish an E-commerce Product Background Dataset (EPBD) for the research in this paper and future work. Experimental results indicate that our approach significantly outperforms current prevalent methods in terms of automatic metrics and human evaluation, yielding improved background aesthetics and relevance.

In cross-lingual language understanding, machine translation is often utilized to enhance the transferability of models across languages, either by translating the training data from the source language to the target, or from the target to the source to aid inference. However, in cross-lingual machine reading comprehension (MRC), it is difficult to perform a deep level of assistance to enhance cross-lingual transfer because of the variation of answer span positions in different languages. In this paper, we propose X-STA, a new approach for cross-lingual MRC. Specifically, we leverage an attentive teacher to subtly transfer the answer spans of the source language to the answer output space of the target. A Gradient-Disentangled Knowledge Sharing technique is proposed as an improved cross-attention block. In addition, we force the model to learn semantic alignments from multiple granularities and calibrate the model outputs with teacher guidance to enhance cross-lingual transferability. Experiments on three multi-lingual MRC datasets show the effectiveness of our method, outperforming state-of-the-art approaches.

Recently, diffusion-based deep generative models (e.g., Stable Diffusion) have shown impressive results in text-to-image synthesis. However, current text-to-image models often require multiple passes of prompt engineering by humans in order to produce satisfactory results for real-world applications. We propose BeautifulPrompt, a deep generative model to produce high-quality prompts from very simple raw descriptions, which enables diffusion-based models to generate more beautiful images. In our work, we first fine-tuned the BeautifulPrompt model over low-quality and high-quality collecting prompt pairs. Then, to ensure that our generated prompts can generate more beautiful images, we further propose a Reinforcement Learning with Visual AI Feedback technique to fine-tune our model to maximize the reward values of the generated prompts, where the reward values are calculated based on the PickScore and the Aesthetic Scores. Our results demonstrate that learning from visual AI feedback promises the potential to improve the quality of generated prompts and images significantly. We further showcase the integration of BeautifulPrompt to a cloud-native AI platform to provide better text-to-image generation service in the cloud.

Tingfeng Cao, Chengyu Wang, Chuanqi Tan, Jun Huang, Jinhui Zhu. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.

Tingfeng Cao, Chengyu Wang, Bingyan Liu, Ziheng Wu, Jinhui Zhu, Jun Huang. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2023.