Kang Zhang

Chaoning Zhang, Kang Zhang, Chenshuang Zhang et al.

Adversarial training (AT) for robust representation learning and self-supervised learning (SSL) for unsupervised representation learning are two active research fields. Integrating AT into SSL, multiple prior works have accomplished a highly significant yet challenging task: learning robust representation without labels. A widely used framework is adversarial contrastive learning which couples AT and SSL, and thus constitute a very complex optimization problem. Inspired by the divide-and-conquer philosophy, we conjecture that it might be simplified as well as improved by solving two sub-problems: non-robust SSL and pseudo-supervised AT. This motivation shifts the focus of the task from seeking an optimal integrating strategy for a coupled problem to finding sub-solutions for sub-problems. With this said, this work discards prior practices of directly introducing AT to SSL frameworks and proposed a two-stage framework termed Decoupled Adversarial Contrastive Learning (DeACL). Extensive experimental results demonstrate that our DeACL achieves SOTA self-supervised adversarial robustness while significantly reducing the training time, which validates its effectiveness and efficiency. Moreover, our DeACL constitutes a more explainable solution, and its success also bridges the gap with semi-supervised AT for exploiting unlabeled samples for robust representation learning. The code is publicly accessible at https://github.com/pantheon5100/DeACL.

Axi Niu, Pham Xuan Trung, Kang Zhang et al.

Diffusion models have gained significant popularity in the field of image-to-image translation. Previous efforts applying diffusion models to image super-resolution (SR) have demonstrated that iteratively refining pure Gaussian noise using a U-Net architecture trained on denoising at various noise levels can yield satisfactory high-resolution images from low-resolution inputs. However, this iterative refinement process comes with the drawback of low inference speed, which strongly limits its applications. To speed up inference and further enhance the performance, our research revisits diffusion models in image super-resolution and proposes a straightforward yet significant diffusion model-based super-resolution method called ACDMSR (accelerated conditional diffusion model for image super-resolution). Specifically, our method adapts the standard diffusion model to perform super-resolution through a deterministic iterative denoising process. Our study also highlights the effectiveness of using a pre-trained SR model to provide the conditional image of the given low-resolution (LR) image to achieve superior high-resolution results. We demonstrate that our method surpasses previous attempts in qualitative and quantitative results through extensive experiments conducted on benchmark datasets such as Set5, Set14, Urban100, BSD100, and Manga109. Moreover, our approach generates more visually realistic counterparts for low-resolution images, emphasizing its effectiveness in practical scenarios.

Hong-Yu Zhou, Yizhou Yu, Chengdi Wang et al.

During the diagnostic process, clinicians leverage multimodal information, such as chief complaints, medical images, and laboratory-test results. Deep-learning models for aiding diagnosis have yet to meet this requirement. Here we report a Transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. Rather than learning modality-specific features, the model uses embedding layers to convert images and unstructured and structured text into visual tokens and text tokens, and bidirectional blocks with intramodal and intermodal attention to learn a holistic representation of radiographs, the unstructured chief complaint and clinical history, structured clinical information such as laboratory-test results and patient demographic information. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary diseases (by 12% and 9%, respectively) and in the prediction of adverse clinical outcomes in patients with COVID-19 (by 29% and 7%, respectively). Leveraging unified multimodal Transformer-based models may help streamline triage of patients and facilitate the clinical decision process.

Axi Niu, Kang Zhang, Trung X. Pham et al.

Diffusion probabilistic models (DPM) have been widely adopted in image-to-image translation to generate high-quality images. Prior attempts at applying the DPM to image super-resolution (SR) have shown that iteratively refining a pure Gaussian noise with a conditional image using a U-Net trained on denoising at various-level noises can help obtain a satisfied high-resolution image for the low-resolution one. To further improve the performance and simplify current DPM-based super-resolution methods, we propose a simple but non-trivial DPM-based super-resolution post-process framework,i.e., cDPMSR. After applying a pre-trained SR model on the to-be-test LR image to provide the conditional input, we adapt the standard DPM to conduct conditional image generation and perform super-resolution through a deterministic iterative denoising process. Our method surpasses prior attempts on both qualitative and quantitative results and can generate more photo-realistic counterparts for the low-resolution images with various benchmark datasets including Set5, Set14, Urban100, BSD100, and Manga109. Code will be published after accepted.

Qingpeng Zhu, Wenxiu Sun, Yuekun Dai et al.

Depth completion from RGB images and sparse Time-of-Flight (ToF) measurements is an important problem in computer vision and robotics. While traditional methods for depth completion have relied on stereo vision or structured light techniques, recent advances in deep learning have enabled more accurate and efficient completion of depth maps from RGB images and sparse ToF measurements. To evaluate the performance of different depth completion methods, we organized an RGB+sparse ToF depth completion competition. The competition aimed to encourage research in this area by providing a standardized dataset and evaluation metrics to compare the accuracy of different approaches. In this report, we present the results of the competition and analyze the strengths and weaknesses of the top-performing methods. We also discuss the implications of our findings for future research in RGB+sparse ToF depth completion. We hope that this competition and report will help to advance the state-of-the-art in this important area of research. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2023.

Chaoning Zhang, Chenshuang Zhang, Junha Song et al.

Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction (e.g., BERT) have become a de facto standard SSL practice in NLP. By contrast, early attempts at generative methods in vision have been buried by their discriminative counterparts (like contrastive learning); however, the success of mask image modeling has revived the masking autoencoder (often termed denoising autoencoder in the past). As a milestone to bridge the gap with BERT in NLP, masked autoencoder has attracted unprecedented attention for SSL in vision and beyond. This work conducts a comprehensive survey of masked autoencoders to shed insight on a promising direction of SSL. As the first to review SSL with masked autoencoders, this work focuses on its application in vision by discussing its historical developments, recent progress, and implications for diverse applications.

Trung Pham, Chaoning Zhang, Axi Niu et al.

Exponential Moving Average (EMA or momentum) is widely used in modern self-supervised learning (SSL) approaches, such as MoCo, for enhancing performance. We demonstrate that such momentum can also be plugged into momentum-free SSL frameworks, such as SimCLR, for a performance boost. Despite its wide use as a fundamental component in modern SSL frameworks, the benefit caused by momentum is not well understood. We find that its success can be at least partly attributed to the stability effect. In the first attempt, we analyze how EMA affects each part of the encoder and reveal that the portion near the encoder's input plays an insignificant role while the latter parts have much more influence. By monitoring the gradient of the overall loss with respect to the output of each block in the encoder, we observe that the final layers tend to fluctuate much more than other layers during backpropagation, i.e. less stability. Interestingly, we show that using EMA to the final part of the SSL encoder, i.e. projector, instead of the whole deep network encoder can give comparable or preferable performance. Our proposed projector-only momentum helps maintain the benefit of EMA but avoids the double forward computation.

Yilin Ye, Rong Huang, Kang Zhang et al.

The recent advances of AI technology, particularly in AI-Generated Content (AIGC), have enabled everyone to easily generate beautiful paintings with simple text description. With the stunning quality of AI paintings, it is widely questioned whether there still exists difference between human and AI paintings and whether human artists will be replaced by AI. To answer these questions, we develop a computational framework combining neural latent space and aesthetics features with visual analytics to investigate the difference between human and AI paintings. First, with categorical comparison of human and AI painting collections, we find that AI artworks show distributional difference from human artworks in both latent space and some aesthetic features like strokes and sharpness, while in other aesthetic features like color and composition there is less difference. Second, with individual artist analysis of Picasso, we show human artists' strength in evolving new styles compared to AI. Our findings provide concrete evidence for the existing discrepancies between human and AI paintings and further suggest improvements of AI art with more consideration of aesthetics and human artists' involvement.

Axi Niu, Kang Zhang, Joshua Tian Jin Tee et al.

It is well known the adversarial optimization of GAN-based image super-resolution (SR) methods makes the preceding SR model generate unpleasant and undesirable artifacts, leading to large distortion. We attribute the cause of such distortions to the poor calibration of the discriminator, which hampers its ability to provide meaningful feedback to the generator for learning high-quality images. To address this problem, we propose a simple but non-travel diffusion-style data augmentation scheme for current GAN-based SR methods, known as DifAugGAN. It involves adapting the diffusion process in generative diffusion models for improving the calibration of the discriminator during training motivated by the successes of data augmentation schemes in the field to achieve good calibration. Our DifAugGAN can be a Plug-and-Play strategy for current GAN-based SISR methods to improve the calibration of the discriminator and thus improve SR performance. Extensive experimental evaluations demonstrate the superiority of DifAugGAN over state-of-the-art GAN-based SISR methods across both synthetic and real-world datasets, showcasing notable advancements in both qualitative and quantitative results.

Axi Niu, Kang Zhang, Qingsen Yan et al.

Scene Text Image Super-Resolution (STISR) aims to restore high-resolution details in low-resolution text images, which is crucial for both human readability and machine recognition. Existing methods, however, often depend on external Optical Character Recognition (OCR) models for textual priors or rely on complex multi-component architectures that are difficult to train and reproduce. In this paper, we introduce DualTSR, a unified end-to-end framework that addresses both issues. DualTSR employs a single multimodal transformer backbone trained with a dual diffusion objective. It simultaneously models the continuous distribution of high-resolution images via Conditional Flow Matching and the discrete distribution of textual content via discrete diffusion. This shared design enables visual and textual information to interact at every layer, allowing the model to infer text priors internally instead of relying on an external OCR module. Compared with prior multi-branch diffusion systems, DualTSR offers a simpler end-to-end formulation with fewer hand-crafted components. Experiments on synthetic Chinese benchmarks and a curated real-world evaluation protocol show that DualTSR achieves strong perceptual quality and text fidelity.

Zhiliang Wu, Hanyu Xuan, Changchang Sun et al.

Deep learning-based video inpainting has yielded promising results and gained increasing attention from researchers. Generally, these methods usually assume that the corrupted region masks of each frame are known and easily obtained. However, the annotation of these masks are labor-intensive and expensive, which limits the practical application of current methods. Therefore, we expect to relax this assumption by defining a new semi-supervised inpainting setting, making the networks have the ability of completing the corrupted regions of the whole video using the annotated mask of only one frame. Specifically, in this work, we propose an end-to-end trainable framework consisting of completion network and mask prediction network, which are designed to generate corrupted contents of the current frame using the known mask and decide the regions to be filled of the next frame, respectively. Besides, we introduce a cycle consistency loss to regularize the training parameters of these two networks. In this way, the completion network and the mask prediction network can constrain each other, and hence the overall performance of the trained model can be maximized. Furthermore, due to the natural existence of prior knowledge (e.g., corrupted contents and clear borders), current video inpainting datasets are not suitable in the context of semi-supervised video inpainting. Thus, we create a new dataset by simulating the corrupted video of real-world scenarios. Extensive experimental results are reported to demonstrate the superiority of our model in the video inpainting task. Remarkably, although our model is trained in a semi-supervised manner, it can achieve comparable performance as fully-supervised methods.

Agus Gunawan, Xu Yin, Kang Zhang

Various normalization layers have been proposed to help the training of neural networks. Group Normalization (GN) is one of the effective and attractive studies that achieved significant performances in the visual recognition task. Despite the great success achieved, GN still has several issues that may negatively impact neural network training. In this paper, we introduce an analysis framework and discuss the working principles of GN in affecting the training process of the neural network. From experimental results, we conclude the real cause of GN's inferior performance against Batch normalization (BN): 1) \textbf{unstable training performance}, 2) \textbf{more sensitive} to distortion, whether it comes from external noise or perturbations introduced by the regularization. In addition, we found that GN can only help the neural network training in some specific period, unlike BN, which helps the network throughout the training. To solve these issues, we propose a new normalization layer built on top of GN, by incorporating the advantages of BN. Experimental results on the image classification task demonstrated that the proposed normalization layer outperforms the official GN to improve recognition accuracy regardless of the batch sizes and stabilize the network training.

Hee Suk Yoon, Eunseop Yoon, Joshua Tian Jin Tee et al.

Multimodal Dialogue Response Generation (MDRG) is a recently proposed task where the model needs to generate responses in texts, images, or a blend of both based on the dialogue context. Due to the lack of a large-scale dataset specifically for this task and the benefits of leveraging powerful pre-trained models, previous work relies on the text modality as an intermediary step for both the image input and output of the model rather than adopting an end-to-end approach. However, this approach can overlook crucial information about the image, hindering 1) image-grounded text response and 2) consistency of objects in the image response. In this paper, we propose BI-MDRG that bridges the response generation path such that the image history information is utilized for enhanced relevance of text responses to the image content and the consistency of objects in sequential image responses. Through extensive experiments on the multimodal dialogue benchmark dataset, we show that BI-MDRG can effectively increase the quality of multimodal dialogue. Additionally, recognizing the gap in benchmark datasets for evaluating the image consistency in multimodal dialogue, we have created a curated set of 300 dialogues annotated to track object consistency across conversations.

Sunan He, Yuxiang Nie, Hongmei Wang et al.

Generalist foundation models (GFMs) are renowned for their exceptional capability and flexibility in effectively generalizing across diverse tasks and modalities. In the field of medicine, while GFMs exhibit superior generalizability based on their extensive intrinsic knowledge as well as proficiency in instruction following and in-context learning, specialist models excel in precision due to their domain knowledge. In this work, for the first time, we explore the synergy between the GFM and specialist models, to enable precise medical image analysis on a broader scope. Specifically, we propose a cooperative framework, Generalist-Specialist Collaboration (GSCo), which consists of two stages, namely the construction of GFM and specialists, and collaborative inference on downstream tasks. In the construction stage, we develop MedDr, the largest open-source GFM tailored for medicine, showcasing exceptional instruction-following and in-context learning capabilities. Meanwhile, a series of lightweight specialists are crafted for downstream tasks with low computational cost. In the collaborative inference stage, we introduce two cooperative mechanisms, Mixture-of-Expert Diagnosis and Retrieval-Augmented Diagnosis, to harvest the generalist's in-context learning abilities alongside the specialists' domain expertise. For a comprehensive evaluation, we curate a large-scale benchmark featuring 28 datasets and about 250,000 images. Extensive results demonstrate that MedDr consistently outperforms state-of-the-art GFMs on downstream datasets. Furthermore, GSCo exceeds both GFMs and specialists across all out-of-domain disease diagnosis datasets. These findings indicate a significant paradigm shift in the application of GFMs, transitioning from separate models for specific tasks to a collaborative approach between GFMs and specialists, thereby advancing the frontiers of generalizable AI in medicine.

Zhijing Shao, Duotun Wang, Qing-Yao Tian et al.

Although neural rendering has made significant advances in creating lifelike, animatable full-body and head avatars, incorporating detailed expressions into full-body avatars remains largely unexplored. We present DEGAS, the first 3D Gaussian Splatting (3DGS)-based modeling method for full-body avatars with rich facial expressions. Trained on multiview videos of a given subject, our method learns a conditional variational autoencoder that takes both the body motion and facial expression as driving signals to generate Gaussian maps in the UV layout. To drive the facial expressions, instead of the commonly used 3D Morphable Models (3DMMs) in 3D head avatars, we propose to adopt the expression latent space trained solely on 2D portrait images, bridging the gap between 2D talking faces and 3D avatars. Leveraging the rendering capability of 3DGS and the rich expressiveness of the expression latent space, the learned avatars can be reenacted to reproduce photorealistic rendering images with subtle and accurate facial expressions. Experiments on an existing dataset and our newly proposed dataset of full-body talking avatars demonstrate the efficacy of our method. We also propose an audio-driven extension of our method with the help of 2D talking faces, opening new possibilities for interactive AI agents.

Kang Zhang, Suyeon Lee, Arda Senocak et al.

Cinematic Audio Source Separation (CASS) aims to decompose mixed film audio into speech, music, and sound effects, enabling applications like dubbing and remastering. Existing CASS approaches are audio-only, overlooking the inherent audio-visual nature of films, where sounds often align with visual cues. We present the first framework for audio-visual CASS (AV-CASS), leveraging visual context to enhance separation quality. Our method formulates CASS as a conditional generative modeling problem using conditional flow matching, enabling multimodal audio source separation. To address the lack of cinematic datasets with isolated sound tracks, we introduce a training data synthesis pipeline that pairs in-the-wild audio and video streams (e.g., facial videos for speech, scene videos for effects) and design a dedicated visual encoder for this dual-stream setup. Trained entirely on synthetic data, our model generalizes effectively to real-world cinematic content and achieves strong performance on synthetic, real-world, and audio-only CASS benchmarks. Code and demo are available at \url{https://cass-flowmatching.github.io}.

Joshua Tian Jin Tee, Kang Zhang, Hee Suk Yoon et al.

Diffusion models have recently emerged as a potent tool in generative modeling. However, their inherent iterative nature often results in sluggish image generation due to the requirement for multiple model evaluations. Recent progress has unveiled the intrinsic link between diffusion models and Probability Flow Ordinary Differential Equations (ODEs), thus enabling us to conceptualize diffusion models as ODE systems. Simultaneously, Physics Informed Neural Networks (PINNs) have substantiated their effectiveness in solving intricate differential equations through implicit modeling of their solutions. Building upon these foundational insights, we introduce Physics Informed Distillation (PID), which employs a student model to represent the solution of the ODE system corresponding to the teacher diffusion model, akin to the principles employed in PINNs. Through experiments on CIFAR 10 and ImageNet 64x64, we observe that PID achieves performance comparable to recent distillation methods. Notably, it demonstrates predictable trends concerning method-specific hyperparameters and eliminates the need for synthetic dataset generation during the distillation process. Both of which contribute to its easy-to-use nature as a distillation approach for Diffusion Models. Our code and pre-trained checkpoint are publicly available at: https://github.com/pantheon5100/pid_diffusion.git.

Trung X. Pham, Kang Zhang, Ji Woo Hong et al.

Diffusion Transformers have achieved state-of-the-art performance in class-conditional and multimodal generation, yet the structure of their learned conditional embeddings remains poorly understood. In this work, we present the first systematic study of these embeddings and uncover a notable redundancy: class-conditioned embeddings exhibit extreme angular similarity, exceeding 99\% on ImageNet-1K, while continuous-condition tasks such as pose-guided image generation and video-to-audio generation reach over 99.9\%. We further find that semantic information is concentrated in a small subset of dimensions, with head dimensions carrying the dominant signal and tail dimensions contributing minimally. By pruning low-magnitude dimensions--removing up to two-thirds of the embedding space--we show that generation quality and fidelity remain largely unaffected, and in some cases improve. These results reveal a semantic bottleneck in Transformer-based diffusion models, providing new insights into how semantics are encoded and suggesting opportunities for more efficient conditioning mechanisms.

Chenshuang Zhang, Kang Zhang, Joon Son Chung et al.

Distinguishing visually similar objects by their motion remains a critical challenge in computer vision. Although supervised trackers show promise, contemporary self-supervised trackers struggle when visual cues become ambiguous, limiting their scalability and generalization without extensive labeled data. We find that pre-trained video diffusion models inherently learn motion representations suitable for tracking without task-specific training. This ability arises because their denoising process isolates motion in early, high-noise stages, distinct from later appearance refinement. Capitalizing on this discovery, our self-supervised tracker significantly improves performance in distinguishing visually similar objects, an underexplored failure point for existing methods. Our method achieves up to a 6-point improvement over recent self-supervised approaches on established benchmarks and our newly introduced tests focused on tracking visually similar items. Visualizations confirm that these diffusion-derived motion representations enable robust tracking of even identical objects across challenging viewpoint changes and deformations.

Kang Zhang, Trung X. Pham, Suyeon Lee et al.

We present MGAudio, a novel flow-based framework for open-domain video-to-audio generation, which introduces model-guided dual-role alignment as a central design principle. Unlike prior approaches that rely on classifier-based or classifier-free guidance, MGAudio enables the generative model to guide itself through a dedicated training objective designed for video-conditioned audio generation. The framework integrates three main components: (1) a scalable flow-based Transformer model, (2) a dual-role alignment mechanism where the audio-visual encoder serves both as a conditioning module and as a feature aligner to improve generation quality, and (3) a model-guided objective that enhances cross-modal coherence and audio realism. MGAudio achieves state-of-the-art performance on VGGSound, reducing FAD to 0.40, substantially surpassing the best classifier-free guidance baselines, and consistently outperforms existing methods across FD, IS, and alignment metrics. It also generalizes well to the challenging UnAV-100 benchmark. These results highlight model-guided dual-role alignment as a powerful and scalable paradigm for conditional video-to-audio generation. Code is available at: https://github.com/pantheon5100/mgaudio

Chaoning Zhang, Philipp Benz, Adil Karjauv et al.

Existing works have identified the limitation of top-$1$ attack success rate (ASR) as a metric to evaluate the attack strength but exclusively investigated it in the white-box setting, while our work extends it to a more practical black-box setting: transferable attack. It is widely reported that stronger I-FGSM transfers worse than simple FGSM, leading to a popular belief that transferability is at odds with the white-box attack strength. Our work challenges this belief with empirical finding that stronger attack actually transfers better for the general top-$k$ ASR indicated by the interest class rank (ICR) after attack. For increasing the attack strength, with an intuitive interpretation of the logit gradient from the geometric perspective, we identify that the weakness of the commonly used losses lie in prioritizing the speed to fool the network instead of maximizing its strength. To this end, we propose a new normalized CE loss that guides the logit to be updated in the direction of implicitly maximizing its rank distance from the ground-truth class. Extensive results in various settings have verified that our proposed new loss is simple yet effective for top-$k$ attack. Code is available at: \url{https://bit.ly/3uCiomP}

Chaoning Zhang, Kang Zhang, Trung X. Pham et al.

Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free framework is often inferior because the negative sample size (NSS) is limited by its mini-batch size (MBS). To decouple the NSS from the MBS, a dynamic dictionary has been adopted in a large volume of CL frameworks, among which arguably the most popular one is MoCo family. In essence, MoCo adopts a momentum-based queue dictionary, for which we perform a fine-grained analysis of its size and consistency. We point out that InfoNCE loss used in MoCo implicitly attract anchors to their corresponding positive sample with various strength of penalties and identify such inter-anchor hardness-awareness property as a major reason for the necessity of a large dictionary. Our findings motivate us to simplify MoCo v2 via the removal of its dictionary as well as momentum. Based on an InfoNCE with the proposed dual temperature, our simplified frameworks, SimMoCo and SimCo, outperform MoCo v2 by a visible margin. Moreover, our work bridges the gap between CL and non-CL frameworks, contributing to a more unified understanding of these two mainstream frameworks in SSL. Code is available at: https://bit.ly/3LkQbaT.

Aven Le Zhou, Jiayi Ye, Tianchen Liu et al.

As a communication channel, body movements have been widely explored in behavioral studies and kinesics. Performing and visual arts share the same interests but focus on documenting and representing human body movements, such as for dance notation and visual work creation. This paper investigates body movements in oriental calligraphy and how to apply calligraphy principles to stimulate and archive body movements. Through an artwork (Wushu), the authors experiment with an interactive and generative approach to engage the audience's bodily participation and archive the body movements as a compendium of generated calligraphy. The audience assumes the role of both writers and readers; creating ("writing") and appreciating ("reading") the generated calligraphy becomes a cyclical process within this infinite "Book," which can motivate further attention and discussions concerning Chinese characters and calligraphy.

Yilin Ye, Qian Zhu, Shishi Xiao et al.

Image search is an essential and user-friendly method to explore vast galleries of digital images. However, existing image search methods heavily rely on proximity measurements like tag matching or image similarity, requiring precise user inputs for satisfactory results. To meet the growing demand for a contemporary image search engine that enables accurate comprehension of users' search intentions, we introduce an innovative user intent expansion framework. Our framework leverages visual-language models to parse and compose multi-modal user inputs to provide more accurate and satisfying results. It comprises two-stage processes: 1) a parsing stage that incorporates a language parsing module with large language models to enhance the comprehension of textual inputs, along with a visual parsing module that integrates an interactive segmentation module to swiftly identify detailed visual elements within images; and 2) a logic composition stage that combines multiple user search intents into a unified logic expression for more sophisticated operations in complex searching scenarios. Moreover, the intent expansion framework enables users to perform flexible contextualized interactions with the search results to further specify or adjust their detailed search intents iteratively. We implemented the framework into an image search system for NFT (non-fungible token) search and conducted a user study to evaluate its usability and novel properties. The results indicate that the proposed framework significantly improves users' image search experience. Particularly the parsing and contextualized interactions prove useful in allowing users to express their search intents more accurately and engage in a more enjoyable iterative search experience.

Dan-Lu Fei, Zi-Wei Wu, Kang Zhang

"Benefit Game: Alien Seaweed Swarms" combines artificial life art and interactive game with installation to explore the impact of human activity on fragile seaweed ecosystems. The project aims to promote ecological consciousness by creating a balance in digital seaweed ecologies. Inspired by the real species "Laminaria saccharina", the author employs Procedural Content Generation via Machine Learning technology to generate variations of virtual seaweeds and symbiotic fungi. The audience can explore the consequences of human activities through gameplay and observe the ecosystem's feedback on the benefits and risks of seaweed aquaculture. This Benefit Game offers dynamic and real-time responsive artificial seaweed ecosystems for an interactive experience that enhances ecological consciousness.

Aven-Le Zhou, Yu-Ao Wang, Wei Wu et al.

With the advancement of neural generative capabilities, the art community has actively embraced GenAI (generative artificial intelligence) for creating painterly content. Large text-to-image models can quickly generate aesthetically pleasing outcomes. However, the process can be non-deterministic and often involves tedious trial-and-error, as users struggle with formulating effective prompts to achieve their desired results. This paper introduces a prompting-free generative approach that empowers users to automatically generate personalized painterly content that incorporates their aesthetic preferences in a customized artistic style. This approach involves utilizing ``semantic injection'' to customize an artist model in a specific artistic style, and further leveraging a genetic algorithm to optimize the prompt generation process through real-time iterative human feedback. By solely relying on the user's aesthetic evaluation and preference for the artist model-generated images, this approach creates the user a personalized model that encompasses their aesthetic preferences and the customized artistic style.

Yingying Sun, Jun A, Zhiwei Liu et al.

Artificial intelligence (AI) is transforming scientific research, including proteomics. Advances in mass spectrometry (MS)-based proteomics data quality, diversity, and scale, combined with groundbreaking AI techniques, are unlocking new challenges and opportunities in biological discovery. Here, we highlight key areas where AI is driving innovation, from data analysis to new biological insights. These include developing an AI-friendly ecosystem for proteomics data generation, sharing, and analysis; improving peptide and protein identification and quantification; characterizing protein-protein interactions and protein complexes; advancing spatial and perturbation proteomics; integrating multi-omics data; and ultimately enabling AI-empowered virtual cells.

Chenshuang Zhang, Chaoning Zhang, Kang Zhang et al.

There is a growing concern about applying batch normalization (BN) in adversarial training (AT), especially when the model is trained on both adversarial samples and clean samples (termed Hybrid-AT). With the assumption that adversarial and clean samples are from two different domains, a common practice in prior works is to adopt Dual BN, where BN and BN are used for adversarial and clean branches, respectively. A popular belief for motivating Dual BN is that estimating normalization statistics of this mixture distribution is challenging and thus disentangling it for normalization achieves stronger robustness. In contrast to this belief, we reveal that disentangling statistics plays a less role than disentangling affine parameters in model training. This finding aligns with prior work (Rebuffi et al., 2023), and we build upon their research for further investigations. We demonstrate that the domain gap between adversarial and clean samples is not very large, which is counter-intuitive considering the significant influence of adversarial perturbation on the model accuracy. We further propose a two-task hypothesis which serves as the empirical foundation and a unified framework for Hybrid-AT improvement. We also investigate Dual BN in test-time and reveal that affine parameters characterize the robustness during inference. Overall, our work sheds new light on understanding the mechanism of Dual BN in Hybrid-AT and its underlying justification.

Kang Zhang, Osamu Yoshie, Lichao Sun et al.

Trading range breakout is a key method in the technical analysis of financial trading, widely employed by traders in financial markets such as stocks, futures, and foreign exchange. However, distinguishing between true and false breakout and providing the correct rationale cause significant challenges to investors. Traditional quantitative methods require large amounts of data and cannot directly present the reasoning process, making them less than perfect in this field. Recently, large language models have achieved success in various downstream applications, but their effectiveness in the domain of financial breakout detection has been subpar. The reason is that the unique data and specific knowledge are required in breakout detection. To address these issues, we create the first financial breakout dataset and introduce FinLLM-B, the premier large language model for financial breakout detection, which enhances the effectiveness of breakout trading strategies. Furthermore, we have developed a novel framework for large language models, namely multi-stage structure, effectively reducing mistakes in downstream applications. Experimental results indicate that compared to GPT-3.5, FinLLM-B improves the average accuracy of answers and rational by 49.97%, with the multi-stage structure contributing 9.72% to the improvement. Additionally, it outperforms ChatGPT-4 by 42.38%.

Hao Yang, Hong-Yu Zhou, Jiarun Liu et al.

Existing deep learning models for defining pathology from clinical imaging data rely on expert annotations and lack generalization capabilities in open clinical environments. Here, we present a generalizable vision-language model for Annotation-Free pathology Localization (AFLoc). The core strength of AFLoc is extensive multi-level semantic structure-based contrastive learning, which comprehensively aligns multi-granularity medical concepts with abundant image features to adapt to the diverse expressions of pathologies without the reliance on expert image annotations. We conduct primary experiments on a dataset of 220K pairs of image-report chest X-ray images and perform validation across eight external datasets encompassing 34 types of chest pathologies. The results demonstrate that AFLoc outperforms state-of-the-art methods in both annotation-free localization and classification tasks. Additionally, we assess the generalizability of AFLoc on other modalities, including histopathology and retinal fundus images. We show that AFLoc exhibits robust generalization capabilities, even surpassing human benchmarks in localizing five different types of pathological images. These results highlight the potential of AFLoc in reducing annotation requirements and its applicability in complex clinical environments.

Radhika Dua, Young Joon, Kwon et al.

Radiological imaging is central to diagnosis, treatment planning, and clinical decision-making. Vision-language foundation models have spurred interest in automated radiology report generation (RRG), but safe deployment requires reliable clinical evaluation of generated reports. Existing metrics often rely on surface-level similarity or behave as black boxes, lacking interpretability. We introduce ICARE (Interpretable and Clinically-grounded Agent-based Report Evaluation), an interpretable evaluation framework leveraging large language model agents and dynamic multiple-choice question answering (MCQA). Two agents, each with either the ground-truth or generated report, generate clinically meaningful questions and quiz each other. Agreement on answers captures preservation and consistency of findings, serving as interpretable proxies for clinical precision and recall. By linking scores to question-answer pairs, ICARE enables transparent, and interpretable assessment. Clinician studies show ICARE aligns significantly more with expert judgment than prior metrics. Perturbation analyses confirm sensitivity to clinical content and reproducibility, while model comparisons reveal interpretable error patterns.

Xu Yin, Min-Sung Yoon, Yuchi Huo et al.

Task execution for object rearrangement could be challenged by Task-Level Perturbations (TLP), i.e., unexpected object additions, removals, and displacements that can disrupt underlying visual policies and fundamentally compromise task feasibility and progress. To address these challenges, we present LangPert, a language-based framework designed to detect and mitigate TLP situations in tabletop rearrangement tasks. LangPert integrates a Visual Language Model (VLM) to comprehensively monitor policy's skill execution and environmental TLP, while leveraging the Hierarchical Chain-of-Thought (HCoT) reasoning mechanism to enhance the Large Language Model (LLM)'s contextual understanding and generate adaptive, corrective skill-execution plans. Our experimental results demonstrate that LangPert handles diverse TLP situations more effectively than baseline methods, achieving higher task completion rates, improved execution efficiency, and potential generalization to unseen scenarios.

Jiayang Huang, Lingjie Li, Kang Zhang et al.

This paper introduces the art project The Dream Within Huang Long Cave, an AI-driven interactive and immersive narrative experience. The project offers new insights into AI technology, artistic practice, and psychoanalysis. Inspired by actual geographical landscapes and familial archetypes, the work combines psychoanalytic theory and computational technology, providing an artistic response to the concept of the non-existence of the Big Other. The narrative is driven by a combination of a large language model (LLM) and a realistic digital character, forming a virtual agent named YELL. Through dialogue and exploration within a cave automatic virtual environment (CAVE), the audience is invited to unravel the language puzzles presented by YELL and help him overcome his life challenges. YELL is a fictional embodiment of the Big Other, modeled after the artist's real father. Through a cross-temporal interaction with this digital father, the project seeks to deconstruct complex familial relationships. By demonstrating the non-existence of the Big Other, we aim to underscore the authenticity of interpersonal emotions, positioning art as a bridge for emotional connection and understanding within family dynamics.

Axi Niu, Kang Zhang, Trung X. Pham et al.

Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-estimation-based methods may be inaccurate in estimating the degradation, making them less applicable to real-world LR images. On the other hand, blind-based methods are often limited by their fixed single perception information, which hinders their ability to handle diverse perceptual characteristics. To overcome this limitation, we propose a novel SR method called MPF-Net that leverages multiple perceptual features of input images. Our method incorporates a Multi-Perception Feature Extraction (MPFE) module to extract diverse perceptual information and a series of newly-designed Cross-Perception Blocks (CPB) to combine this information for effective super-resolution reconstruction. Additionally, we introduce a contrastive regularization term (CR) that improves the model's learning capability by using newly generated HR and LR images as positive and negative samples for ground truth HR. Experimental results on challenging real-world SR datasets demonstrate that our approach significantly outperforms existing state-of-the-art methods in both qualitative and quantitative measures.

Chaoning Zhang, Kang Zhang, Chenshuang Zhang et al.

To avoid collapse in self-supervised learning (SSL), a contrastive loss is widely used but often requires a large number of negative samples. Without negative samples yet achieving competitive performance, a recent work has attracted significant attention for providing a minimalist simple Siamese (SimSiam) method to avoid collapse. However, the reason for how it avoids collapse without negative samples remains not fully clear and our investigation starts by revisiting the explanatory claims in the original SimSiam. After refuting their claims, we introduce vector decomposition for analyzing the collapse based on the gradient analysis of the $l_2$-normalized representation vector. This yields a unified perspective on how negative samples and SimSiam alleviate collapse. Such a unified perspective comes timely for understanding the recent progress in SSL.

Axi Niu, Kang Zhang, Chaoning Zhang et al.

PGD-based and FGSM-based are two popular adversarial training (AT) approaches for obtaining adversarially robust models. Compared with PGD-based AT, FGSM-based one is significantly faster but fails with catastrophic overfitting (CO). For mitigating CO in such Fast AT, there are two popular existing strategies: random start (RandStart) and Gradient Alignment (GradAlign). The former works only for a relatively small perturbation 8/255 with the l_\infty constraint, and GradAlign improves it by extending the perturbation size to 16/255 (with the l_\infty constraint) but at the cost of being 3 to 4 times slower. How to avoid CO in Fast AT for a large perturbation size but without increasing the computation overhead remains as an unsolved issue, for which our work provides a frustratingly simple (yet effective) solution. Specifically, our solution lies in just noise augmentation (NoiseAug) which is a non-trivial byproduct of simplifying GradAlign. By simplifying GradAlign we have two findings: (i) aligning logit instead of gradient in GradAlign requires half the training time but achieves higher performance than GradAlign; (ii) the alignment operation can also be removed by only keeping noise augmentation (NoiseAug). Simplified from GradAlign, our NoiseAug has a surprising resemblance with RandStart except that we inject noise on the image instead of perturbation. To understand why injecting noise to input prevents CO, we verify that this is caused not by data augmentation effect (inject noise on image) but by improved local linearity. We provide an intuitive explanation for why NoiseAug improves local linearity without explicit regularization. Extensive results demonstrate that our NoiseAug achieves SOTA results in FGSM AT. The code will be released after accepted.

Yiming Qiu, Kang Zhang, Han Zhang et al.

Nowadays e-commerce search has become an integral part of many people's shopping routines. One critical challenge in today's e-commerce search is the semantic matching problem where the relevant items may not contain the exact terms in the user query. In this paper, we propose a novel deep neural network based approach to query rewriting, in order to tackle this problem. Specifically, we formulate query rewriting into a cyclic machine translation problem to leverage abundant click log data. Then we introduce a novel cyclic consistent training algorithm in conjunction with state-of-the-art machine translation models to achieve the optimal performance in terms of query rewriting accuracy. In order to make it practical in industrial scenarios, we optimize the syntax tree construction to reduce computational cost and online serving latency. Offline experiments show that the proposed method is able to rewrite hard user queries into more standard queries that are more appropriate for the inverted index to retrieve. Comparing with human curated rule-based method, the proposed model significantly improves query rewriting diversity while maintaining good relevancy. Online A/B experiments show that it improves core e-commerce business metrics significantly. Since the summer of 2020, the proposed model has been launched into our search engine production, serving hundreds of millions of users.

Han Zhang, Songlin Wang, Kang Zhang et al.

Nowadays e-commerce search has become an integral part of many people's shopping routines. Two critical challenges stay in today's e-commerce search: how to retrieve items that are semantically relevant but not exact matching to query terms, and how to retrieve items that are more personalized to different users for the same search query. In this paper, we present a novel approach called DPSR, which stands for Deep Personalized and Semantic Retrieval, to tackle this problem. Explicitly, we share our design decisions on how to architect a retrieval system so as to serve industry-scale traffic efficiently and how to train a model so as to learn query and item semantics accurately. Based on offline evaluations and online A/B test with live traffics, we show that DPSR model outperforms existing models, and DPSR system can retrieve more personalized and semantically relevant items to significantly improve users' search experience by +1.29% conversion rate, especially for long tail queries by +10.03%. As a result, our DPSR system has been successfully deployed into JD.com's search production since 2019.

Jinhui Yu, Kailin Wu, Kang Zhang et al.

Negative afterimage appears in our vision when we shift our gaze from an over stimulated original image to a new area with a uniform color. The colors of negative afterimages differ from the old stimulating colors in the original image when the color in the new area is either neutral or chromatic. The interaction between stimulating colors in the test and inducing field in the original image changes our color perception due to simultaneous contrast, and the interaction between changed colors perceived in the previously-viewed field and the color in the currently-viewed field also affects our perception of colors in negative afterimages due to successive contrast. Based on these observations we propose a computational model to estimate colors of negative afterimages in more general cases where the original stimulating color in the test field is chromatic, and the original stimulating color in the inducing field and the new stimulating color can be either neutral or chromatic. We validate our model with human experiments.

Devavrat Shah, Kang Zhang

In this paper, we discuss the method of Bayesian regression and its efficacy for predicting price variation of Bitcoin, a recently popularized virtual, cryptographic currency. Bayesian regression refers to utilizing empirical data as proxy to perform Bayesian inference. We utilize Bayesian regression for the so-called "latent source model". The Bayesian regression for "latent source model" was introduced and discussed by Chen, Nikolov and Shah (2013) and Bresler, Chen and Shah (2014) for the purpose of binary classification. They established theoretical as well as empirical efficacy of the method for the setting of binary classification. In this paper, instead we utilize it for predicting real-valued quantity, the price of Bitcoin. Based on this price prediction method, we devise a simple strategy for trading Bitcoin. The strategy is able to nearly double the investment in less than 60 day period when run against real data trace.

Kang Zhang, Yuqiang Fang, Dongbo Min et al.

Human beings process stereoscopic correspondence across multiple scales. However, this bio-inspiration is ignored by state-of-the-art cost aggregation methods for dense stereo correspondence. In this paper, a generic cross-scale cost aggregation framework is proposed to allow multi-scale interaction in cost aggregation. We firstly reformulate cost aggregation from a unified optimization perspective and show that different cost aggregation methods essentially differ in the choices of similarity kernels. Then, an inter-scale regularizer is introduced into optimization and solving this new optimization problem leads to the proposed framework. Since the regularization term is independent of the similarity kernel, various cost aggregation methods can be integrated into the proposed general framework. We show that the cross-scale framework is important as it effectively and efficiently expands state-of-the-art cost aggregation methods and leads to significant improvements, when evaluated on Middlebury, KITTI and New Tsukuba datasets.

Kang Zhang, Jiyang Li, Yijing Li et al.

In this paper, we propose a novel binary-based cost computation and aggregation approach for stereo matching problem. The cost volume is constructed through bitwise operations on a series of binary strings. Then this approach is combined with traditional winner-take-all strategy, resulting in a new local stereo matching algorithm called binary stereo matching (BSM). Since core algorithm of BSM is based on binary and integer computations, it has a higher computational efficiency than previous methods. Experimental results on Middlebury benchmark show that BSM has comparable performance with state-of-the-art local stereo methods in terms of both quality and speed. Furthermore, experiments on images with radiometric differences demonstrate that BSM is more robust than previous methods under these changes, which is common under real illumination.