Whole slide images, with their gigapixel-scale panoramas of tissue samples, are pivotal for precise disease diagnosis. However, their analysis is hindered by immense data size and scarce annotations. Existing MIL methods face challenges due to the fundamental imbalance where a single bag-level label must guide the learning of numerous patch-level features. This sparse supervision makes it difficult to reliably identify discriminative patches during training, leading to unstable optimization and suboptimal solutions. We propose a spatially regularized MIL framework that leverages inherent spatial relationships among patch features as label-independent regularization signals. Our approach learns a shared representation space by jointly optimizing feature-induced spatial reconstruction and label-guided classification objectives, enforcing consistency between intrinsic structural patterns and supervisory signals. Experimental results on multiple public datasets demonstrate significant improvements over state-of-the-art methods, offering a promising direction. The code is available at https://github.com/wwyi1828/SRMIL.

Visual Question Answering (VQA) is increasingly used in diverse applications ranging from general visual reasoning to safety-critical domains such as medical imaging and autonomous systems, where models must provide not only accurate answers but also explanations that humans can easily understand and verify.Prototype-based modeling has shown promise for interpretability by grounding predictions in semantically meaningful regions for purely visual reasoning tasks, yet remains underexplored in the context of VQA.We present ProtoVQA, a unified prototypical framework that (i) learns question-aware prototypes that serve as reasoning anchors, connecting answers to discriminative image regions, (ii) applies spatially constrained matching to ensure that the selected evidence is coherent and semantically relevant, and (iii) supports both answering and grounding tasks through a shared prototype backbone.To assess explanation quality, we propose the Visual-Linguistic Alignment Score (VLAS), which measures how well the model's attended regions align with ground-truth evidence.Experiments on Visual7W show that ProtoVQA yields faithful, fine-grained explanations while maintaining competitive accuracy, advancing the development of transparent and trustworthy VQA systems.

Xingjian Diao, Chunhui Zhang, Keyi Kong, Weiyi Wu, Chiyu Ma, Zhongyu Ouyang, Peijun Qing, Soroush Vosoughi, Jiang Gui. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

The role of Camouflaged Object Detection (COD) is to identify the objects that integrate seamlessly with the surrounding environment. Due to the high intrinsic similarity between the objects and their background, this task presents greater challenges than traditional object detection. Most existing COD methods often have a large number of parameters and high computational complexity in the pursuit of detection accuracy, which hinders the application of COD in practical scenarios. To address this issue, we propose a UNet-like Transformer Network for COD, termed UTNet, which achieves competitive detection accuracy with a smaller parameter set. Specifically, we propose a Camouflaged Region Awareness Module (CRAM) consisting of a Hierarchical Attention Mechanism (HAM) that groups features to reveal intrinsic consistency between sub-features. This CRAM can be embedded into the backbone network, giving it powerful modeling capabilities. And, we present a Contextual Knowledge Collector (CKC) that exploits a cross-aggregation approach for neighboring feature layers, promoting the flow of semantic information from high-level to low-level features, and ensuring the integrity of camouflaged objects at each level of features. Furthermore, we introduce a progressive decoder that utilizes a cascade of attention units to filter noise and explores knowledge aggregation to emphasize features from different levels, ensuring that camouflaged objects have complete spatial details at the local level. Extensive experimental results show that UTNet achieves competitive results compared to 20 state-of-the-art methods. Codes and results are released onhttps://github.com/hjy0518/UTNet.

Recent advances in whole-slide image (WSI) scanners and computational capabilities have significantly propelled the application of artificial intelligence in histopathology slide analysis. While these strides are promising, current supervised learning approaches for WSI analysis come with the challenge of exhaustively labeling high-resolution slides-a process that is both labor-intensive and timeconsuming. In contrast, self-supervised learning (SSL) pretraining strategies are emerging as a viable alternative, given that they don't rely on explicit data annotations. These SSL strategies are quickly bridging the performance disparity with their supervised counterparts. In this context, we introduce an SSL framework. This framework aims for transferable representation learning and semantically meaningful clustering by synergizing invariance loss and clustering loss in WSI analysis. Notably, our approach outperforms common SSL methods in downstream classification and clustering tasks, as evidenced by tests on the Camelyon16 and a pancreatic cancer dataset. The code and additional details are accessible at https://github.com/wwyi1828/CluSiam.

We describe a highly scalable parallel arithmetic coder for Markov inputs suitable for implementation on modern multi-core processors. The algorithm divides the input into interleaved sub-sequences which can be then processed independently on different processing units using LDPC-based Slepian-Wolf coding. Experimental simulations show good scalability of the proposed algorithm while also maintaining good compression performance. Notably, when compared with traditional parallel arithmetic coding, the proposed method maintains a much higher efficiency both respect to the entropy limit as well as in terms of the ability to distribute computations across multiple cores without performance loss.

Multi-core architectures have become mainstream. Trends suggest that the number of cores integrated on a single chip will increase continuously. However, lock contention in operating systems can limit the parallel scalability on multi-cores so significantly that the speedup decreases with the increasing number of cores (thrashing). Although the phenomenon can be easily reproduced experimentally, most existing lock models are not able to do so. To overcome this challenge, this paper develops a discrete event simulation model which has the capability of capturing both the sequential execution in critical sections and the contention for shared hardware resources. The model is evaluated using a series of typical parameter configurations which can represent different degrees of lock contention. Experimental results suggest that the thrashing phenomenon can be observed when the model parameters are selected properly. To further understand this phenomenon, statistics such as the percentage of time spent waiting for locks and the number of cores waiting for a lock are exploited to characterize the lock thrashing. In addition, the model sensitivity to changes in memory latency and hardware architectures are also examined. Finally, we use this model to compare three methods which are proposed for preventing the lock thrashing.

Multi-core architectures have become mainstream. Trends suggest that the number of cores integrated on a single chip will continue to increase. However, lock contention in applications or kernels can degrade the scalability so significantly that the speedup decreases with the increasing number of cores (thrashing). Although the phenomenon can be easily reproduced on real multi-core platforms, existing lock models are not able to do so. To overcome the disadvantage, this paper proposes an analysis model which has the capability of capturing both the sequential execution of critical sections and the overhead of lock implementation. Numerical results indicate that thrashing can be observed by using the proposed model. Furthermore, this model can also be exploited to compare different mechanisms designed for avoiding the lock thrashing.