Over-smoothing in Graph Neural Networks (GNNs) causes collapse in distinct node features, particularly on heterophilic graphs where adjacent nodes often have dissimilar labels. Although sheaf neural networks partially mitigate this problem, they typically rely on static or heavily parameterized sheaf structures that hinder generalization and scalability. Existing sheaf-based models either predefine restriction maps or introduce excessive complexity, yet fail to provide rigorous stability guarantees. In this paper, we introduce a novel scheme called SGPC (Sheaf GNNs with PAC-Bayes Calibration), a unified architecture that combines cellular-sheaf message passing with several mechanisms, including optimal transport-based lifting, variance-reduced diffusion, and PAC-Bayes spectral regularization for robust semi-supervised node classification. We establish performance bounds theoretically and demonstrate that end-to-end training in linear computational complexity can achieve the resulting bound-aware objective. Experiments on nine homophilic and heterophilic benchmarks show that SGPC outperforms state-of-the-art spectral and sheaf-based GNNs while providing certified confidence intervals on unseen nodes.

Automating scientific poster generation requires hierarchical document understanding and coherent content-layout planning. Existing methods often rely on flat summarization or optimize content and layout separately. As a result, they often suffer from information loss, weak logical flow, and poor visual balance. We present PosterForest, a training-free framework for scientific poster generation. Our method introduces the Poster Tree, a structured intermediate representation that captures document hierarchy and visual-textual semantics across multiple levels. Building on this representation, content and layout agents perform hierarchical reasoning and recursive refinement, progressively optimizing the poster from global organization to local composition. This joint optimization improves semantic coherence, logical flow, and visual harmony. Experiments show that PosterForest outperforms prior methods in both automatic and human evaluations, without additional training or domain-specific supervision.

Video Moment Retrieval (MR) aims to localize moments within a video based on a given natural language query. Given the prevalent use of platforms like YouTube for information retrieval, the demand for MR techniques is significantly growing. Recent DETR-based models have made notable advances in performance but still struggle with accurately localizing short moments. Through data analysis, we identified limited feature diversity in short moments, which motivated the development of MomentMix. MomentMix generates new short-moment samples by employing two augmentation strategies: ForegroundMix and BackgroundMix, each enhancing the ability to understand the query-relevant and irrelevant frames, respectively. Additionally, our analysis of prediction bias revealed that short moments particularly struggle with accurately predicting their center positions and length of moments. To address this, we propose a Length-Aware Decoder, which conditions length through a novel bipartite matching process. Our extensive studies demonstrate the efficacy of our length-aware approach, especially in localizing short moments, leading to improved overall performance. Our method surpasses state-of-the-art DETR-based methods on benchmark datasets, achieving the highest R1 and mAP on QVHighlights and the highest [email protected] on TACoS and Charades-STA (such as a 9.62% gain in [email protected] and an 16.9% gain in mAP average for QVHighlights). The code is available at https://github.com/sjpark5800/LA-DETR.

Open-Vocabulary Part Segmentation (OVPS) is an emerging field for recognizing fine-grained parts in unseen categories. We identify two primary challenges in OVPS: (1) the difficulty in aligning part-level image-text correspondence, and (2) the lack of structural understanding in segmenting object parts. To address these issues, we propose Part-CATSeg, a novel framework that integrates object-aware part-level cost aggregation, compositional loss, and structural guidance from DINO. Our approach employs a disentangled cost aggregation strategy that handles object and part-level costs separately, enhancing the precision of part-level segmentation. We also introduce a compositional loss to better capture part-object relationships, compensating for the limited part annotations. Additionally, structural guidance from DINO features improves boundary delineation and inter-part understanding. Extensive experiments on Pascal-Part-116, ADE20K-Part-234, and PartImageNet datasets demonstrate that our method significantly outperforms state-of-the-art approaches, setting a new baseline for robust generalization to unseen part categories.

Recent advancements in text-to-image diffusion models have shown impressive results but often fail to fully capture user’s intent. Existing methods combining textual inputs with bounding boxes or region masks lack precise spatial guidance, leading to misaligned or unintended object orientations. To address these issues, we propose Scribble-Guided Diffusion (ScribbleDiff), a training-free approach that employs user-provided scribbles as visual prompts for image generation. However, incorporating scribbles poses challenges due to their sparse and thin nature, which complicates accurate alignment. To resolve this, we introduce moment alignment and scribble propagation, enabling effective and flexible alignment between generated images and scribble inputs. Experiments on the PASCAL-Scribble dataset demonstrate notable improvements in spatial control and consistency, validating the effectiveness of our method in scribble-guidance.

Score distillation sampling (SDS) has emerged as an effective framework in text-driven 3D editing tasks, leveraging diffusion models for 3D-consistent editing. However, existing SDS-based 3D editing methods suffer from long training times and produce low-quality results. We identify that the root cause of this performance degradation is their conflict with the sampling dynamics of diffusion models. Addressing this conflict allows us to treat SDS as a diffusion reverse process for 3D editing via sampling from data space. In contrast, existing methods naively distill the score function using diffusion models. From these insights, we propose DreamCatalyst, a novel framework that considers these sampling dynamics in the SDS framework. Specifically, we devise the optimization process of our DreamCatalyst to approximate the diffusion reverse process in editing tasks, thereby aligning with diffusion sampling dynamics. As a result, DreamCatalyst successfully reduces training time and improves editing quality. Our method offers two modes: (1) a fast mode that edits Neural Radiance Fields (NeRF) scenes approximately 23 times faster than current state-of-the-art NeRF editing methods, and (2) a high-quality mode that produces superior results about 8 times faster than these methods. Notably, our high-quality mode outperforms current state-of-the-art NeRF editing methods in terms of both speed and quality. DreamCatalyst also surpasses the state-of-the-art 3D Gaussian Splatting (3DGS) editing methods, establishing itself as an effective and model-agnostic 3D editing solution.

Graph Neural Networks (GNNs) thrive on message passing (MP) but are vulnerable when the graph carries many heterophilic or misclassified edges. Prior analyses suggest that signed propagation can mitigate over-smoothing under low edge-error rates, yet they implicitly assume perfect edge labels and the presence of self-loops. We revisit this setting and show that, under high edge uncertainty, propagating any information may harm node separability even with signed weights. Our key insight is to decide not to propagate along uncertain edges adaptively. Concretely, we intentionally omit self-loops to isolate pure neighbor influence for a clearer theoretical analysis, adopt a row-stochastic (asymmetric) operator that matches the Markov-chain view of MP and simplifies spectral-radius proofs, and dynamically estimate the local homophily $b_i$ and edge-classification error $e_t$ during training via an EM procedure. We prove that our selective blocking yields a sub-stochastic propagation matrix whose joint spectral radius exceeds that of signed GNNs under high $e_t$, guaranteeing reduced over-smoothing, and we supply a lemma showing that class-discriminative signals survive even when the operator is rank-deficient. Extensive experiments on seven homophilic and heterophilic benchmarks confirm that the proposed adaptive blocking outperforms strong baselines.

Message-passing neural networks are widely employed in various graph mining applications. However, these methods are susceptible to the scarcity of labeled data, which often leads to overfitting. Our observations suggest that sparse initial vectors further exacerbate this issue by failing to fully represent the range of learnable parameters. This sparsity can hinder the optimization of specific dimensions in the initial projection matrix, as the training samples may not adequately span these parameters. To overcome this challenge, we propose a novel perturbation technique that introduces variability to the initial features and the projection hyperplane. Notably, even without employing grid search, we demonstrate that shifting with a small estimated value mitigates this problem more effectively than other perturbation methods. Experimental results on real-world datasets reveal that our technique significantly enhances node classification accuracy in semi-supervised scenarios.

The issue of data sparsity poses a significant challenge to recommender systems. In response to this, algorithms that leverage side information such as review texts have been proposed. Furthermore, Cross-Domain Recommendation (CDR), which captures domain-shareable knowledge and transfers it from a richer domain (source) to a sparser one (target) has emerged recently. Nevertheless, existing methodologies assume an Euclidean embedding space, encountering difficulties in accurately representing richer text information and managing complex user-item interactions. This paper advocates a hyperbolic CDR approach for modeling review-based user-item relationships. We first emphasize that conventional distance-based domain alignment techniques may cause problems because small modifications in hyperbolic geometry result in magnified perturbations, ultimately leading to the collapse of hierarchical structures. To address this challenge, we propose hierarchy-aware embedding and domain alignment schemes that adjust the scale to extract domain-shareable information without disrupting structural forms. Extensive experiments substantiate the efficiency, robustness, and scalability of the proposed model. The source code is given here https://github.com/ChoiYoonHyuk/HEAD.

Graph Neural Networks (GNNs) exhibit satisfactory performance on homophilic networks, where most edges connect two nodes with the same label. However, their effectiveness diminishes as the graphs become heterophilic (low homophily), prompting the exploration of various message-passing schemes. In particular, assigning negative weights to heterophilic edges (signed propagation) for message-passing has gained significant attention, and some studies theoretically confirm its effectiveness. Nevertheless, prior theorems assume binary classification scenarios, which may not hold well for graphs with multiple classes. To solve this limitation, we offer new theoretical insights into GNNs in multi-class environments and identify the drawbacks of employing signed propagation from two perspectives: message-passing and parameter update. We found that signed propagation without considering feature distribution can degrade the separability of dissimilar neighbors, which also increases prediction uncertainty (e.g., conflicting evidence) that can cause instability. To address these limitations, we introduce two novel calibration strategies aiming to improve discrimination power while reducing entropy in predictions. Through theoretical and extensive experimental analysis, we demonstrate that the proposed schemes enhance the performance of both signed and general message-passing neural networks (Choi et al. 2023).

Graph neural networks (GNNs) that collect information from neighbors are commonly utilized in semi-supervised learning contexts. In particular, a significant body of research has been dedicated to developing effective graph filters and aggregation methods to filter the information from adjacent nodes. Despite their efficacy, these approaches may encounter challenges due to the sparsity of training nodes, especially when their features are represented as sparse vectors (e.g., bag-of-words). This condition can lead to the overfitting of certain dimensions within the first projection matrix (hyperplane), as the training samples may not adequately represent the full spectrum of learnable parameters. To solve this limitation, we propose an innovative perturbation technique. Specifically, we introduce additional training variability by modifying both the initial features and the hyperplane, which contributes to the reduction of prediction variance by updating the entire dimensions. To the best of our knowledge, our approach is the first to address the overfitting issue in GNNs precipitated by sparse node features. Comprehensive experiments on real-world datasets and ablation studies affirm that our proposed method significantly enhances node classification performance, with improvements of up to 46.5% in GNN algorithms.

Global food security is increasingly at risk due to factors like climate change and population growth, necessitating advancements in agricultural technology. Digital breeding, a method centered around genotype-phenotype selection using next-generation sequencing (NGS), offers a solution by enabling the identification of genetic mutations and predicting crop traits with greater speed and precision compared to traditional approaches. This automated breeding process efficiently gathers and analyzes genotype and phenotype data, improving key traits such as growth, yield, and tolerance while minimizing human intervention. Despite advancements in sequencing technologies, challenges remain due to the high cost and impracticality of acquiring extensive genomic datasets. To address these limitations, this study explores data augmentation strategies using deep learning techniques, focusing on their success in other fields like computer vision. Unlike conventional Generative Adversarial Networks (GANs), which face stability issues, we present a novel approach using a stacked convolutional and LSTM architecture. This model leverages SNP position information to capture correlations within genomic regions and introduces a specialized metric to evaluate the quality of augmented data. The effectiveness of the proposed phenotype prediction model is demonstrated through real-world testing on a collection of 192 tomato varieties, highlighting its potential to revolutionize breeding processes and improve agricultural outcomes.

Open-vocabulary part segmentation (OVPS) is an emerging research area focused on segmenting fine-grained entities using diverse and previously unseen vocabularies. Our study highlights the inherent complexities of part segmentation due to intricate boundaries and diverse granularity, reflecting the knowledge-based nature of part identification. To address these challenges, we propose PartCLIPSeg, a novel framework utilizing generalized parts and object-level contexts to mitigate the lack of generalization in fine-grained parts. PartCLIPSeg integrates competitive part relationships and attention control, alleviating ambiguous boundaries and underrepresented parts. Experimental results demonstrate that PartCLIPSeg outperforms existing state-of-the-art OVPS methods, offering refined segmentation and an advanced understanding of part relationships within images. Through extensive experiments, our model demonstrated a significant improvement over the state-of-the-art models on the Pascal-Part-116, ADE20K-Part-234, and PartImageNet datasets.

Food shortages, driven by population growth and climate change, pose a significant global challenge. Addressing this issue requires a dual focus on increasing food production and optimizing land use efficiency. Rather than expanding farmland, current efforts emphasize enhancing crop productivity through plant breeding. Especially, plant breeding research has emerged as a critical solution to the escalating challenges posed by a rapidly growing population and unpredictable climate changes. While plant breeding has a history of contributing to improved crop productivity, addressing current food problems requires the application of innovative technologies. Therefore, digital breeding, which incorporates new technologies, has gained prominence recently. Digital breeding uses high-throughput sequencing technology known as next-generation sequencing (NGS) to decode genome sequences and collect mutation information from diverse individuals. This method selects individuals with specific traits by analyzing the relationship between genotype and phenotype. By leveraging genotype information, digital breeding accurately pinpoints individuals with desired characteristics, significantly expediting the breeding process compared with traditional or molecular breeding methods. The distinctive advantages of digital breeding, such as precise genome selection, make it a promising approach for addressing food security challenges arising from population growth and climate change. Consequently, ongoing research in this domain, particularly combining big data and artificial intelligence technology, further underscores the significance of these advancements. This study explores the significance of artificial intelligence-based genome selection techniques, and associated technologies and outlines future research.

Numerous studies have investigated image classification. In particular, recent methods based on deep learning have exhibited high accuracies. However, various existing state-of-the-art methods based on deep learning show different accuracies depending on the database and environment. Accordingly, different deep learning models need to be used in image classification studies according to the database, environment, and research field. This study investigated a technique to increase the accuracy of the existing deep learning-based models. The proposed method was applied to various existing state-of-the-art methods. In the proposed method, a convolution neural network (CNN) is trained using the classification activation map (CAM) to focus on specific areas in the input image. The CAM image is used as the ground-truth image. Furthermore, the concept of the CAM-based categorical adversarial network (CAM-CAN), in which the CNN is trained based on a generative adversarial network, is proposed in this paper. An action recognition experiment was performed using the self-collected Dongguk thermal image database (DTh-DB) and open database, and the results revealed that the accuracies of the existing state-of-the-art methods significantly increased after applying the proposed method. For instance, the accuracies obtained using the DTh-DB, TPR, PPV, ACC, and F1 with the conventional DenseNet201 model were 80.14%, 75.28%, 96.0%, and 75.91%, respectively. After applying the proposed method, the accuracies increased to 86.53%, 89.90%, 97.64%, and 85.84%, respectively.

Graph Neural Networks (GNNs) have proven to be powerful in many graph-based applications. However, they fail to generalize well under heterophilic setups, where neighbor nodes have different labels. To address this challenge, we employ a confidence ratio as a hyper-parameter, assuming that some of the edges are disassortative (heterophilic). Here, we propose a two-phased algorithm. Firstly, we determine edge coefficients through subgraph matching using a supplementary module. Then, we apply GNNs with a modified label propagation mechanism to utilize the edge coefficients effectively. Specifically, our supplementary module identifies a certain proportion of task-irrelevant edges based on a given confidence ratio. Using the remaining edges, we employ the widely used optimal transport to measure the similarity between two nodes with their subgraphs. Finally, using the coefficients as supplementary information on GNNs, we improve the label propagation mechanism which can prevent two nodes with smaller weights from being closer. The experiments on benchmark datasets show that our model alleviates over-smoothing and improves performance.

A cross-domain recommendation has shown promising results in solving data-sparsity and cold-start problems. Despite such progress, existing methods focus on domain-shareable information (overlapped users or same contexts) for a knowledge transfer, and they fail to generalize well without such requirements. To deal with these problems, we suggest utilizing review texts that are general to most e-commerce systems. Our model (named SER) uses three text analysis modules, guided by a single domain discriminator for disentangled representation learning. Here, we suggest a novel optimization strategy that can enhance the quality of domain disentanglement, and also debilitates detrimental information of a source domain. Also, we extend the encoding network from a single to multiple domains, which has proven to be powerful for review-based recommender systems. Extensive experiments and ablation studies demonstrate that our method is efficient, robust, and scalable compared to the state-of-the-art single and cross-domain recommendation methods.

Scripting languages' inferior performance stems from compilers lacking enough static information. To address this limitation, they use JIT compilers organized into multiple tiers, with higher tiers using profiling information to generate high-performance code. Checks are inserted to detect incorrect assumptions and, when a check fails, execution transfers to a lower tier. The points of potential transfer between tiers are called Stack Map Points (SMPs). They require a consistent state in both tiers and, hence, limit code optimization across SMPs in the higher tier. This paper examines the code generated by a state-of-theart JavaScript compiler and finds that the code has a high frequency of SMPs. These SMPs rarely cause execution to transfer to lower tiers. However, both the optimization-limiting effect of the SMPs, and the overhead of the SMP-guarding checks contribute to scripting languages' low performance. To tackle this problem, we extend the compiler to generate hardware transactions around SMPs, and perform simple within-transaction optimizations enabled by transactions. We target emerging lightweight HTM systems and call our changes NoMap. We evaluate NoMap on the SunSpider and Kraken suites. We find that NoMap lowers the instruction count by an average of 14.2% and 11.5%, and the execution time by an average of 16.7% and 8.9%, for SunSpider and Kraken, respectively.

No abstract available.

JavaScript performance is paramount to a user’s browsing experience. Browser vendors have gone to great lengths to improve JavaScript’s steady-state performance. This has led to sophisticated web applications. However, as users increasingly expect instantaneous page load times, another important goal for JavaScript engines is to attain minimal startup times.

Reference counting (RC) is one of the two fundamental approaches to garbage collection. It has the desirable characteristics of low memory overhead and short pause times, which are key in today's interactive mobile platforms. However, RC has a higher execution time overhead than its counterpart, tracing garbage collection. The reason is that RC implementations maintain per-object counters, which must be continually updated. In particular, the execution time overhead is high in environments where low memory overhead is critical and, therefore, non-deferred RC is used. This is because the counter updates need to be performed atomically.

Hardware speculation offers a major surface for micro-architectural covert and side channel attacks. Unfortunately, defending against speculative execution attacks is challenging. The reason is that speculations destined to be squashed execute incorrect instructions, outside the scope of what programmers and compilers reason about. Further, any change to micro-architectural state made by speculative execution can leak information. In this paper, we propose InvisiSpec, a novel strategy to defend against hardware speculation attacks in multiprocessors by making speculation invisible in the data cache hierarchy. InvisiSpec blocks micro-architectural covert and side channels through the multiprocessor data cache hierarchy due to speculative loads. In InvisiSpec, unsafe speculative loads read data into a speculative buffer, without modifying the cache hierarchy. When the loads become safe, InvisiSpec makes them visible to the rest of the system. InvisiSpec identifies loads that might have violated memory consistency and, at this time, forces them to perform a validation step. We propose two InvisiSpec designs: one to defend against Spectre-like attacks and another to defend against futuristic attacks, where any speculative load may pose a threat. Our simulations with 23 SPEC and 10 PARSEC workloads show that InvisiSpec is effective. Under TSO, using fences to defend against Spectre attacks slows down execution by 74% relative to a conventional, insecure processor; InvisiSpec reduces the execution slowdown to only 21%. Using fences to defend against futuristic attacks slows down execution by 208%; InvisiSpec reduces the slowdown to 72%.

The same flexibility that makes dynamic scripting languages appealing to programmers is also the primary cause of their low performance. To access objects of potentially different types, the compiler creates a dispatcher with a series of if statements, each performing a comparison to a type and a jump to a handler. This induces major overhead in instructions executed and branches mispredicted.

Increased focus on JavaScript performance has resulted in vast performance improvements for many benchmarks. However, for actual code used in websites, the attained improvements often lag far behind those for popular benchmarks.

In a rapidly growing information-oriented society, people with disabilities are faced with serious inconveniences in accessing products due to the increasingly complicated use of technology-oriented but poorly designed devices. To solve these problems, we designed a customized computer input device (mouse) to be used by physically impaired people. The users performed better with the customized computer mouse than with the traditional computer mouse.

We designed a gesture-based interface with a personal ID tag that interacts with an ambient information system. An ID tag is equipped with a vibrator, an embedded accelerometer sensor, and an RFID tag. In the suggested system, users can not only retrieve and store information, but customize interaction patterns with the ID tag that can be best suited to personal preferences. Patterns of gesture-based interaction are classified with a probabilistic algorithm developed in the study that use signal data from five different axes of the accelerometer sensor.