Text-to-Image (T2I) diffusion models have achieved remarkable success in image generation. Despite their progress, challenges remain in both prompt-following ability, image quality and lack of high-quality datasets, which are essential for refining these models. As acquiring labeled data is costly, we introduce AGFSync, a framework that enhances T2I diffusion models through Direct Preference Optimization (DPO) in a fully AI-driven approach. AGFSync utilizes Vision-Language Models (VLM) to assess image quality across style, coherence, and aesthetics, generating feedback data within an AI-driven loop. By applying AGFSync to leading T2I models such as SD v1.4, v1.5, and SDXL-base, our extensive experiments on the TIFA dataset demonstrate notable improvements in VQA scores, aesthetic evaluations, and performance on the HPS v2 benchmark, consistently outperforming the base models. AGFSync's method of refining T2I diffusion models paves the way for scalable alignment techniques.

In recent years, large language models (LLMs) have developed rapidly and revolutionized natural language processing. However, high storage overhead and computing costs limit LLM deployment in resource-constrained environments. Quantization algorithms can effectively compress LLMs and accelerate inference, but they lead to loss in precision, especially in low-bit scenarios. In this paper, we find that the discarded weight values caused by quantization in fact contain treasures to improve LLMs' accuracy. To excavate those hidden treasures, we construct search spaces around these discarded weights and those weights within the search space can seamlessly be incorporated into the original quantization weights. To determine which weights should be merged, we design a plug-and-play weight compensation framework to capture global information and keep the weights with the highest potential benefits. Our framework can be combined with various LLM quantization algorithms to achieve higher precision without additional inference overhead. We validate the effectiveness of our approach on widely used benchmark datasets for LLMs.

Current delta compression methods struggle to achieve ultra-high compression, failing to minimize the deployment costs of multiple full-parameter fine-tuned large language models. To address this issue, we propose a novel distribution-driven delta compression framework SQ-Delta, which utilizes joint sparsification-quantization to maximize the compression ratio. We have observed that the matrix-computed intermediate results for the delta weight exhibit small variance and min-max range characteristics. Exploiting this distribution phenomenon, we introduce Group-wise Dropout to perform dropout on the delta weight using an optimal group size. Furthermore, using Separate Quantization, the sparse delta weight is quantized and decomposed to achieve a lower bit. Experimental results show that SQ-Delta achieves 16× compression with improved accuracy compared to baselines for WizardMath and WizardCoder models across different parameter scales. Moreover, SQ-Delta demonstrates the ability for ultra-high compression, achieving 128× compression for the WizardMath-7B model and 512× compression for the WizardMath-70B model. Our code is available at https://github.com/llwx593/SQ-Delta.

Automating the synthesis of User Interfaces (UIs) plays a crucial role in enhancing productivity and accelerating the development lifecycle, reducing both development time and manual effort. Recently, the rapid development of Multimodal Large Language Models (MLLMs) has made it possible to generate front-end Hypertext Markup Language (HTML) code directly from webpage designs. However, real-world webpages encompass not only a diverse array of HTML tags but also complex stylesheets, resulting in significantly lengthy code. The lengthy code poses challenges for the performance and efficiency of MLLMs, especially in capturing the structural information of UI designs. To address these challenges, this paper proposes UICopilot, a novel approach to automating UI synthesis via hierarchical code generation from webpage designs. To validate the effectiveness of UICopilot, we conduct experiments on a real-world dataset, i.e., WebCode2M. Experimental results demonstrate that UICopilot significantly outperforms existing baselines in both automatic evaluation metrics and human evaluations. Specifically, statistical analysis reveals that the majority of human annotators prefer the webpages generated by UICopilot over those produced by GPT-4V.

Automatically generating webpage code from webpage designs can significantly reduce the workload of front-end developers, and recent Multimodal Large Language Models (MLLMs) have shown promising potential in this area. However, our investigation reveals that most existing MLLMs are constrained by the absence of high-quality, large-scale, real-world datasets, resulting in inadequate performance in automated webpage code generation. To fill this gap, this paper introduces WebCode2M, a new dataset comprising 2.56 million instances, each containing a design image along with the corresponding webpage code and layout details. Sourced from real-world web resources, WebCode2M offers a rich and valuable dataset for webpage code generation across a variety of applications. The dataset quality is ensured by a scoring model that filters out instances with aesthetic deficiencies or other incomplete elements. To validate the effectiveness of WebCode2M, we introduce a baseline model based on the Vision Transformer (ViT), named WebCoder, and establish a benchmark for fair comparison. Additionally, we introduce a new metric, TreeBLEU, to measure the structural hierarchy recall. The benchmarking results demonstrate that our dataset significantly improves the ability of MLLMs to generate code from webpage designs, confirming its effectiveness and usability for future applications in front-end design tools. Finally, we highlight several practical challenges introduced by our dataset, calling for further research. The code and dataset are publicly available at our project homepage: https://webcode2m.github.io.

Recently, object detection in static images has achieved great success thanks to the application of deep convolutional neural networks. Nevertheless, extending object detectors from image to video is not trivial. Video object detection often suffers from deteriorated object appearances, such as motion blur, video defocus, rare poses or partial occlusion. This paper presents a novel end-to-end Feature Aligned Recurrent Network (FARN) for video object detection with the following two key modules. The first one is a motion guided feature alignment module, which aligns feature maps of past frames with that of the current frame using optical flow fields derived by a subnetwork. The second one is a spatial aware recurrent module, which consists of an attention unit to adaptively weight feature maps from different frames according to learned image quality, and a recurrent unit to leverage spatio-temporal coherence. FARN works causally in the sense that no future frame is used for object detection in the current frame. As evaluated on the ImageNet VID dataset, FARN demonstrated promising performance for causal video object detection compared to state-of-the-art non-causal detectors.