Metalenses have been widely recognized as a key building block of next-generation optical systems, offering unprecedented advantages in compactness, lightweight design, and scalable manufacturing compared to traditional refractive optics. Despite this promise, practical use is limited by optical aberrations, blur, and illumination sensitivity, which degrade both visual quality and machine perception. In this demonstration, we present an end-to-end metalens vision system—from hardware sensing with a custom-built RGB metalens camera, to physics-informed imaging and real-time restoration, and finally to downstream vision applications such as object detection and depth estimation. By integrating spatially-aware attention enhancement and reinforcement learning-based illumination control into a real-time system, our solution transforms degraded raw captures into high-fidelity images that are both visually interpretable and functionally reliable for machine vision. This AI-powered pipeline highlights metalenses as a cornerstone for next-generation imaging, where advances in optics and machine intelligence jointly drive the future of visual perception.

Despite being trained on balanced datasets, existing AI-generated image detectors often exhibit systematic bias at test time, frequently misclassifying fake images as real. We hypothesize that this behavior stems from distributional shift in fake samples and implicit priors learned during training. Specifically, models tend to overfit to superficial artifacts that do not generalize well across different generation methods, leading to a misaligned decision threshold when faced with test-time distribution shift. To address this, we propose a theoretically grounded post-hoc calibration framework based on Bayesian decision theory. In particular, we introduce a learnable scalar correction to the model’s logits, optimized on a small validation set from the target distribution while keeping the backbone frozen. This parametric adjustment compensates for distributional shift in model output, realigning the decision boundary even without requiring ground-truth labels. Experiments on challenging benchmarks show that our approach significantly improves robustness without retraining, offering a lightweight and principled solution for reliable and adaptive AI-generated image detection in the open world.

The out-of-distribution (OOD) property in data is deemed as one main challenge hindering the generalization ability of machine learning algorithms. However, the underlying reasons for this property remain an intriguing and open question that has yet to be fully understood. In this paper, we seek to enhance our understanding of the OOD phenomenon by framing it as a problem of distribution shift and addressing it through two complementary causal perspectives. The first is a generative causal view that elucidates the data generation process. We introduce a novel three-dimensional coordinate system to represent three fundamental distribution shifts, illustrating their role in various OOD generalization problems. The second is an anti-causal view that focuses on the model learning process. We develop an effective approach dubbed Counterfactual Risk Minimization (CRM) to address arbitrary distribution shifts in a unified framework. Additionally, we introduce a new multi-domain visual recognition dataset called CONA to facilitate further exploration of OOD generalization. We conduct evaluations of CRM alongside several state-of-the-art competitors on four benchmark datasets under the three distribution shifts. The results not only affirm CRM's superiority but also shed light on potential future directions. Code and data: https://github.com/muliyangm/CRM.

This fact sheet describes our proposed method for the video track of Challenge on Learned Image Compression (CLIC) 2024. Our scheme follows the typical hybrid coding framework with advanced techniques in motion estimation, context mining, and spatial-temporal super-resolution to enhance rate-distortion performance, particularly at low bitrates.

Aspect-based sentiment analysis (ABSA) has attracted broad attention due to its commercial value.Natural Language Generation-based (NLG) approaches dominate the recent advance in ABSA tasks.However, current NLG practices are inefficient because most of them directly employ an autoregressive generation framework that cannot efficiently generate location information and semantic representations of ABSA targets.In this paper, we propose a novel framework, namely Efficient Hybrid Generation (EHG) to revolutionize traditions.Specifically, we leverage an Efficient Hybrid Transformer to generate the location and semantic information of ABSA targets in parallel.Besides, we design a novel global hybrid loss function in combination with bipartite matching to achieve end-to-end model training.Extensive experiments demonstrate that our proposed EHG framework greatly improves the efficiency of NLG-based methods and outperforms the competitive baselines in almost all cases.

Compositional Zero-Shot Learning (CZSL) aims to imitate the powerful generalization ability of human beings to recognize novel compositions of known primitive concepts that correspond to a state and an object, e.g., purple apple. To fully capture the intra- and inter-class correlations between compositional concepts, in this paper, we propose to learn them in a hierarchical manner. Specifically, we set up three hierarchical embedding spaces that respectively model the states, the objects, and their compositions, which serve as three “experts” that can be combined in inference for more accurate predictions. We achieve this based on the recent success of large-scale pretrained vision-language models, e.g., CLIP, which provides a strong initial knowledge of image-text relationships. To better adapt this knowledge to CZSL, we propose to learn three hierarchical prompts by explicitly fixing the unrelated word tokens in the three embedding spaces. Despite its simplicity, our proposed method consistently yields superior performance over current state-of-the-art approaches on three widely-used CZSL benchmarks.

Light field, as a new data representation format in multimedia, has the ability to capture both intensity and direction of light rays. However, the additional angular information also brings a large volume of data. Classical coding methods are not effective to describe the relationship between different views, leading to redundancy left. To address this problem, we propose a novel light field compression scheme based on implicit neural representation to reduce redundancies between views. We store the information of a light field image implicitly in an neural network and adopt model compression methods to further compress the implicit representation. Extensive experiments have demonstrated the effectiveness of our proposed method, which achieves comparable rate-distortion performance as well as superior perceptual quality over traditional methods.

BACKGROUD: DNA methylation is an epigenetic modification that plays important roles on gene regulation. Study of whole-genome bisulfite sequencing and reduced representation bisulfite sequencing brings the availability of DNA methylation at single CpG resolution. The main interest of study on DNA methylation data is to test the methylation difference under two conditions of biological samples. However, the high cost and complexity of this sequencing experiment limits the number of biological replicates, which brings challenges to the development of statistical methods. RESULTS: Bayesian modeling is well known to be able to borrow strength across the genome, and hence is a powerful tool for high-dimensional-low-sample-size data. In order to provide accurate identification of methylation loci, especially for low coverage data, we propose a full Bayesian partition model to detect differentially methylated loci under two conditions of scientific study. Since hypo-methylation and hyper-methylation have distinct biological implication, it is desirable to differentiate these two types of differential methylation. The advantage of our Bayesian model is that it can produce one-step output of each locus being either equal-, hypo- or hyper-methylated locus without further post-hoc analysis. An R package named as MethyBayes implementing the proposed full Bayesian partition model will be submitted to the bioconductor website upon publication of the manuscript. CONCLUSIONS: The proposed full Bayesian partition model outperforms existing methods in terms of power while maintaining a low false discovery rate based on simulation studies and real data analysis including bioinformatics analysis.

Existing route recommendation systems have two main weaknesses. First, they usually recommend the same route for all users and cannot help control traffic jam. Second, they do not take full advantage of real-time traffic to recommend the best routes. To address these two problems, we develop a real-time route recommendation system, called R3, aiming to provide users with the real-time-traffic-aware routes. R3 recommends diverse routes for different users to alleviate the traffic pressure. R3 utilizes historical taxi driving data and real-time traffic data and integrates them together to provide users with real-time route recommendation.