Xixin Cao

Jiquan Yuan, Xinyan Cao, Changjin Li et al.

As image generation technology advances, AI-based image generation has been applied in various fields and Artificial Intelligence Generated Content (AIGC) has garnered widespread attention. However, the development of AI-based image generative models also brings new problems and challenges. A significant challenge is that AI-generated images (AIGI) may exhibit unique distortions compared to natural images, and not all generated images meet the requirements of the real world. Therefore, it is of great significance to evaluate AIGIs more comprehensively. Although previous work has established several human perception-based AIGC image quality assessment (AIGCIQA) databases for text-generated images, the AI image generation technology includes scenarios like text-to-image and image-to-image, and assessing only the images generated by text-to-image models is insufficient. To address this issue, we establish a human perception-based image-to-image AIGCIQA database, named PKU-I2IQA. We conduct a well-organized subjective experiment to collect quality labels for AIGIs and then conduct a comprehensive analysis of the PKU-I2IQA database. Furthermore, we have proposed two benchmark models: NR-AIGCIQA based on the no-reference image quality assessment method and FR-AIGCIQA based on the full-reference image quality assessment method. Finally, leveraging this database, we conduct benchmark experiments and compare the performance of the proposed benchmark models. The PKU-I2IQA database and benchmarks will be released to facilitate future research on \url{https://github.com/jiquan123/I2IQA}.

Fanyi Yang, Jianfeng Liu, Xin Zhang et al.

Instruction tuning has empowered large language models (LLMs) to achieve remarkable performance, yet its success heavily depends on the availability of large-scale, high-quality instruction-response pairs. To meet this demand, various methods have been developed to synthesize data at scale. However, current methods for scaling up data generation often overlook a crucial aspect: the alignment between instructions and responses. We hypothesize that the quality of instruction-response pairs is determined not by the individual quality of each component, but by the degree of mutual alignment. To address this, we propose a Mutual Alignment Framework (MAIN) which enforces coherence between instructions and responses through mutual constraints. We demonstrate that MAIN generalizes well across model architectures and sizes, achieving state-of-the-art performance on LLaMA, Mistral, and Qwen models across diverse benchmarks. This work underscores the critical role of instruction-response alignment in enabling generalizable and high-quality instruction tuning for LLMs. All code is available from our repository.

Jiquan Yuan, Xinyan Cao, Linjing Cao et al.

In recent years, Artificial Intelligence Generated Content (AIGC) has gained widespread attention beyond the computer science community. Due to various issues arising from continuous creation of AI-generated images (AIGI), AIGC image quality assessment (AIGCIQA), which aims to evaluate the quality of AIGIs from human perception perspectives, has emerged as a novel topic in the field of computer vision. However, most existing AIGCIQA methods directly regress predicted scores from a single generated image, overlooking the inherent differences among AIGIs and scores. Additionally, operations like resizing and cropping may cause global geometric distortions and information loss, thus limiting the performance of models. To address these issues, we propose a patches sampling-based contrastive regression (PSCR) framework. We suggest introducing a contrastive regression framework to leverage differences among various generated images for learning a better representation space. In this space, differences and score rankings among images can be measured by their relative scores. By selecting exemplar AIGIs as references, we also overcome the limitations of previous models that could not utilize reference images on the no-reference image databases. To avoid geometric distortions and information loss in image inputs, we further propose a patches sampling strategy. To demonstrate the effectiveness of our proposed PSCR framework, we conduct extensive experiments on three mainstream AIGCIQA databases including AGIQA-1K, AGIQA-3K and AIGCIQA2023. The results show significant improvements in model performance with the introduction of our proposed PSCR framework. Code will be available at \url{https://github.com/jiquan123/PSCR}.

Tianhao Fu, Xinxin Xu, Weichen Xu et al.

Market making (MM) through Reinforcement Learning (RL) has attracted significant attention in financial trading. With the development of Large Language Models (LLMs), more and more attempts are being made to apply LLMs to financial areas. A simple, direct application of LLM as an agent shows significant performance. Such methods are hindered by their slow inference speed, while most of the current research has not studied LLM distillation for this specific task. To address this, we first propose the normalized fluorescent probe to study the mechanism of the LLM's feature. Based on the observation found by our investigation, we propose Cooperative Market Making (CMM), a novel framework that decouples LLM features across three orthogonal dimensions: layer, task, and data. Various student models collaboratively learn simple LLM features along with different dimensions, with each model responsible for a distinct feature to achieve knowledge distillation. Furthermore, CMM introduces an Hájek-MoE to integrate the output of the student models by investigating the contribution of different models in a kernel function-generated common feature space. Extensive experimental results on four real-world market datasets demonstrate the superiority of CMM over the current distillation method and RL-based market-making strategies.

Jiquan Yuan, Xinyan Cao, Jinming Che et al.

Recently, AIGC image quality assessment (AIGCIQA), which aims to assess the quality of AI-generated images (AIGIs) from a human perception perspective, has emerged as a new topic in computer vision. Unlike common image quality assessment tasks where images are derived from original ones distorted by noise, blur, and compression, \textit{etc.}, in AIGCIQA tasks, images are typically generated by generative models using text prompts. Considerable efforts have been made in the past years to advance AIGCIQA. However, most existing AIGCIQA methods regress predicted scores directly from individual generated images, overlooking the information contained in the text prompts of these images. This oversight partially limits the performance of these AIGCIQA methods. To address this issue, we propose a text-image encoder-based regression (TIER) framework. Specifically, we process the generated images and their corresponding text prompts as inputs, utilizing a text encoder and an image encoder to extract features from these text prompts and generated images, respectively. To demonstrate the effectiveness of our proposed TIER method, we conduct extensive experiments on several mainstream AIGCIQA databases, including AGIQA-1K, AGIQA-3K, and AIGCIQA2023. The experimental results indicate that our proposed TIER method generally demonstrates superior performance compared to baseline in most cases.

Jiquan Yuan, Fanyi Yang, Jihe Li et al.

In recent years, image generation technology has rapidly advanced, resulting in the creation of a vast array of AI-generated images (AIGIs). However, the quality of these AIGIs is highly inconsistent, with low-quality AIGIs severely impairing the visual experience of users. Due to the widespread application of AIGIs, the AI-generated image quality assessment (AIGIQA), aimed at evaluating the quality of AIGIs from the perspective of human perception, has garnered increasing interest among scholars. Nonetheless, current research has not yet fully explored this field. We have observed that existing databases are limited to images generated from single scenario settings. Databases such as AGIQA-1K, AGIQA-3K, and AIGCIQA2023, for example, only include images generated by text-to-image generative models. This oversight highlights a critical gap in the current research landscape, underscoring the need for dedicated databases catering to image-to-image scenarios, as well as more comprehensive databases that encompass a broader range of AI-generated image scenarios. Addressing these issues, we have established a large scale perceptual quality assessment database for both text-to-image and image-to-image AIGIs, named PKU-AIGIQA-4K. We then conduct a well-organized subjective experiment to collect quality labels for AIGIs and perform a comprehensive analysis of the PKU-AIGIQA-4K database. Regarding the use of image prompts during the training process, we propose three image quality assessment (IQA) methods based on pre-trained models that include a no-reference method NR-AIGCIQA, a full-reference method FR-AIGCIQA, and a partial-reference method PR-AIGCIQA. Finally, leveraging the PKU-AIGIQA-4K database, we conduct extensive benchmark experiments and compare the performance of the proposed methods and the current IQA methods.

Guo Pu, Shiyao Xu, Xixin Cao et al. · pku

How to automatically transfer the dynamic texture of a given video to the target still image is a challenging and ongoing problem. In this paper, we propose to handle this task via a simple yet effective model that utilizes both PatchMatch and Transformers. The key idea is to decompose the task of dynamic texture transfer into two stages, where the start frame of the target video with the desired dynamic texture is synthesized in the first stage via a distance map guided texture transfer module based on the PatchMatch algorithm. Then, in the second stage, the synthesized image is decomposed into structure-agnostic patches, according to which their corresponding subsequent patches can be predicted by exploiting the powerful capability of Transformers equipped with VQ-VAE for processing long discrete sequences. After getting all those patches, we apply a Gaussian weighted average merging strategy to smoothly assemble them into each frame of the target stylized video. Experimental results demonstrate the effectiveness and superiority of the proposed method in dynamic texture transfer compared to the state of the art.

Jihe Li, Xiang Liu, Fabian Zhang et al.

Deformable Image Registration (DIR) is essential for aligning medical images that exhibit anatomical variations, facilitating applications such as disease tracking and radiotherapy planning. While classical iterative methods and deep learning approaches have achieved success in DIR, they are often hindered by computational inefficiency or poor generalization. In this paper, we introduce GaussianDIR, a novel, case-specific optimization DIR method inspired by 3D Gaussian splatting. In general, GaussianDIR represents image deformations using a sparse set of mobile and flexible Gaussian primitives, each defined by a center position, covariance, and local rigid transformation. This compact and explicit representation reduces noise and computational overhead while improving interpretability. Furthermore, the movement of individual voxel is derived via blending the local rigid transformation of the neighboring Gaussian primitives. By this, GaussianDIR captures both global smoothness and local rigidity as well as reduces the computational burden. To address varying levels of deformation complexity, GaussianDIR also integrates an adaptive density control mechanism that dynamically adjusts the density of Gaussian primitives. Additionally, we employ multi-scale Gaussian primitives to capture both coarse and fine deformations, reducing optimization to local minima. Experimental results on brain MRI, lung CT, and cardiac MRI datasets demonstrate that GaussianDIR outperforms existing DIR methods in both accuracy and efficiency, highlighting its potential for clinical applications. Finally, as a training-free approach, it challenges the stereotype that iterative methods are inherently slow and transcend the limitations of poor generalization.

Yuxuan Zhao, Xinyan Cao, Jinlong Lin et al.

There has been an encouraging progress in the affective states recognition models based on the single-modality signals as electroencephalogram (EEG) signals or peripheral physiological signals in recent years. However, multimodal physiological signals-based affective states recognition methods have not been thoroughly exploited yet. Here we propose Multiscale Convolutional Neural Networks (Multiscale CNNs) and a biologically inspired decision fusion model for multimodal affective states recognition. Firstly, the raw signals are pre-processed with baseline signals. Then, the High Scale CNN and Low Scale CNN in Multiscale CNNs are utilized to predict the probability of affective states output for EEG and each peripheral physiological signal respectively. Finally, the fusion model calculates the reliability of each single-modality signals by the Euclidean distance between various class labels and the classification probability from Multiscale CNNs, and the decision is made by the more reliable modality information while other modalities information is retained. We use this model to classify four affective states from the arousal valence plane in the DEAP and AMIGOS dataset. The results show that the fusion model improves the accuracy of affective states recognition significantly compared with the result on single-modality signals, and the recognition accuracy of the fusion result achieve 98.52% and 99.89% in the DEAP and AMIGOS dataset respectively.