With the rapid development of multimodal large language models (MLLMs), deploying them on low-resource devices remains challenging. Beyond the model size, long multimodal inputs cause substantial memory overhead in the KV cache, making efficient cache management critical. In this paper, we propose DAVID, a KV cache eviction strategy that adapts to the degree of modality fusion across layers. By analyzing the feature distributions of vision and text tokens, we observe low fusion in early layers and high fusion in deeper layers. Based on this observation, DAVID adopts a decoupled eviction strategy in shallow layers and a super-modal eviction strategy in deeper layers. To support this dynamic switching, we design a lightweight metric that quantifies cross-modal fusion and uses a threshold to determine which layers require decoupling. Experimental results show that DAVID achieves state-of-the-art performance on multiple benchmarks and offers a new perspective on KV cache eviction for MLLMs.

During communication, people inadvertently express emotions through facial animations, with emotion constantly fluctuating throughout the conversation. Existing speech-driven facial animation works predominantly rely on sentence-level coarse-grained emotion labels to impart emotional expression information, thereby overlooking temporal emotion variations. How to make 3D talking heads articulate fluently while adeptly expressing mood fluctuations is the problem addressed by our work. We propose a framework, named SiaTalker, which exquisitely refines emotions of facial animations from coarse-grained levels to dual-perspective interactive fine-grained levels, resulting in highly coordinated and fluid emotional expressions. Specifically, we propose the coarse-to-fine dual granularity fusion decoding framework to connect global and local emotional aspects, allowing nuanced shifts within a consistent emotional tone. The pseudo-siamese cross-perspective submodule is embedded to interact with siamese fine-grained emotions across perspectives, further capturing subtle emotional fluctuations and amplifying the authenticity of facial movements. Furthermore, to comprehensively evaluate our work, the CREMA-D dataset is reconstructed into a 3D emotional talking face dataset with the largest number of subjects, serving as a valuable experimental supplement. Extensive experiments and user studies demonstrate that our approach outperforms state-of-the-art methods and exhibits superior emotional agility and expressiveness in facial movements.

Prolonged Electrocardiogram (ECG) monitoring through the Internet of Medical Things (IoMT) is vital for cardiac diagnosis yet generates prohibitive data volumes, posing significant challenges to storage and transmission. However, conventional ECG compression paradigms have plateaued, failing to push compression ratios higher under stringent fidelity constraints. To address these limitations, we propose an end-to-end architecture that synergizes a multi-granularity temporal-convolutional auto-encoder with Residual Vector Quantization (RVQ). The design introduces three complementary components: (1) RVQ integrated in the encoder-decoder pipeline to boost compression ratios; (2) a codebook-projection layer that increases codebook utilization and reconstruction fidelity; (3) periodicity-aware modeling that captures intrinsic ECG dynamics and further suppresses distortion. Extensive experiments on the MIT-BIH Arrhythmia Database show that the proposed method attains a compression ratio of 88× and Quality Score (QS) of 42.7, while keeping the Percentage Root Mean Difference (PRD) at 2.36% and the Percentage Root mean Difference Normalized (PRDN) at 17.56%, clearly surpassing existing techniques. Generalization is further assessed via zero-shot evaluation on the PhysioNet-2017 dataset. Overall, this paper presents an effective end-to-end compression framework, and experimental results corroborate its efficacy.

Due to the development of text-image multimodal methods, text is used to guide the style transfer of images, which has attracted growing attention. Notably, The existing text-guided image style methods are limited to expressing specific artistic style through simple text. It can only accept coarse-grained text input such as “Van Gogh” and “White Cloud”, and cannot understand fine-grained text input such as “The Night Café by Vincent van Gogh”. To this end, this paper proposes a novel artistic style transfer network based on the fine-grained text guidance and the contrastive semantics similarity, named as TCStyler. It can accept images or texts as style guidance, which is more suitable for fine-grained content understanding stylization. In this network, to address the issue of text-image cross-modal discrepancy, the residual attention feature mapper (RAFM) is introduced to constrain the differences between different modalities in feature space. Then, the global cascading style-sharing module (GCSM) is proposed for performing content-style feature fusion and image-text modality fusion by adopting a global feature-sharing strategy. Furthermore, the contrastive semantics similarity loss is designed to address the problem of multimodal universality. Quantitative and visualization experiments demonstrate that our TCStyler can handle fine-grained artistic text inputs and maintain consistency in the style transfer results guided by different modalities.

Falling is characterized by high incidence and great harm among the elderly. Timely assessing falling risk in daily life is helpful for reducing the occurrence of severe health outcomes. Establishing dataset for falling risk assessment based on wearable devices in the elderly is important work. However, current existing datasets might not reflect the natural gait of the subject due to the discomfort in wearing. Relevant data processing methods based on these datasets have limited practicability and might not be applied to real scenes in daily life. To make daily falling risk assessment possible, we proposed a novel approach to set up a continuous and wearable plantar pressure dataset of 48 older adults along with falling risk labels. The dataset was collected by plantar pressure monitoring shoes which were suitable for daily living spaces. Moreover, the Conv-LSTM algorithm was applied on the dataset, and the average classification result was up to 95.57%, reflecting the effectiveness of this dataset. The dataset is helpful for the studies of falling risk assessment and health monitoring among the elderly.

The dictionary response usually affects the recognition results directly as it represents the original data and usually serves as the input of the classifier. However, the over-complete dictionary usually results in high dimensional response and redundancy. The application of the linear discriminant analysis (LDA)-based mapping method transforms the original dictionary response to be more discriminative for compact dictionary learning, resulting in high intra-class similarity and high inter-class dissimilarity in the response domain for better classification. By analyzing the recognition rate, the compactness and the purity, the proposed method can learn a small size of compact and discriminative dictionary with global optimization, and it can get a comparable or even better performance than the over-complete dictionary with much less computation cost. Experimental results demonstrate that the proposed approach also outperforms several recently proposed compact dictionary learning methods on human action recognition and object classification.