Vision-Language-Action (VLA) models have advanced general-purpose robotic manipulation by leveraging pretrained visual and linguistic representations. However, they struggle with contact-rich tasks that require fine-grained control involving force, especially under visual occlusion or dynamic uncertainty. To address these limitations, we propose \textbf{ForceVLA}, a novel end-to-end manipulation framework that treats external force sensing as a first-class modality within VLA systems. ForceVLA introduces \textbf{FVLMoE}, a force-aware Mixture-of-Experts fusion module that dynamically integrates pretrained visual-language embeddings with real-time 6-axis force feedback during action decoding. This enables context-aware routing across modality-specific experts, enhancing the robot's ability to adapt to subtle contact dynamics. We also introduce \textbf{ForceVLA-Data}, a new dataset comprising synchronized vision, proprioception, and force-torque signals across five contact-rich manipulation tasks. ForceVLA improves average task success by 23.2\% over strong $\pi_0$-based baselines, achieving up to 80\% success in tasks such as plug insertion. Our approach highlights the importance of multimodal integration for dexterous manipulation and sets a new benchmark for physically intelligent robotic control. Code and data will be released at https://sites.google.com/view/forcevla2025/.

Existing pulmonary nodule detection methods often train models in a fully-supervised setting that requires strong labels (i.e., bounding box labels) as label information. However, manual annotation of bounding boxes in CT images is very time-consuming and labor-intensive. To alleviate the annotation burden, in this paper, we investigate pulmonary nodule detection by leveraging both strong labels and weak labels (i.e., center point labels) for training, and propose a novel hybrid-supervised pulmonary nodule detection (HND) method. The training of HND involves a heterogeneous teacher-student learning framework in two stages. In the first stage, we design a point-based consistency calibration network (PCC-Net) as a teacher, which is pre-trained to generate high-quality pseudo bounding box labels given point-augmented CT images as inputs. In the second stage, we develop an information bottleneck-guided pulmonary nodule detection network (IBD-Net) as a student to perform pulmonary nodule detection. In particular, we introduce information bottleneck to learn reliable pulmonary nodule-specific heatmaps under the guidance of PCC-Net, largely enhancing the model’s interpretability and improving the final detection performance. Based on the above designs, our method can effectively detect pulmonary nodule regions with only a limited number of bounding box labels. Experimental results on the public pulmonary nodule detection dataset LUNA16 show that our HND method achieves an excellent balance between the annotation cost and the detection performance.

In this paper, we study facial expression recognition (FER) in the class-incremental learning (CIL) setting, which defines the classification of well-studied and easily-accessible basic expressions as an initial task while learning new compound expressions gradually. Motivated by the fact that compound expressions are meaningful combinations of basic expressions, we treat basic expressions as attributes (i.e., semantic descriptors), and thus compound expressions are represented in terms of attributes. To this end, we propose a novel visual-textual attribute learning network (VTA-Net), mainly consisting of a textual-guided visual module (TVM) and a textual compositional module (TCM), for class-incremental FER. Specifically, TVM extracts textual-aware visual features and classifies expressions by incorporating the textual information into visual attribute learning. Meanwhile, TCM generates visual-aware textual features and predicts expressions by exploiting the dependency between textual attributes and category names of old and new expressions based on a textual compositional graph. In particular, a visual-textual distillation loss is introduced to calibrate TVM and TCM during incremental learning. Finally, the outputs from TVM and TCM are fused to make a final prediction. On the one hand, at each incremental task, the representations of visual attributes are enhanced since visual attributes are shared across old and new expressions. This increases the stability of our method. On the other hand, the textual modality, which involves rich prior knowledge of the relevance between expressions, facilitates our model to identify subtle visual distinctions between compound expressions, improving the plasticity of our method. Experimental results on both in-the-lab and in-the-wild facial expression databases show the superiority of our method against several state-of-the-art methods for class-incremental FER.

In the past three years, global COVID-19 pandemic not only impacted people’s physical health but also significantly affected their mental health, which resulting in rapid increase of psychological problems. Emotions are a common manifestation of psychological changes, and some services (such as music, video, or psychological counseling services) can help users to adjust their emotions in a timely manner, thus to avoid bringing extreme events (e.g., running away from home or committing suicide). Therefore, how to perceive users’ real-time emotions and then recommend the most appropriate services to users has become a challenge. To address this issue, this work proposes an approach for proactive services recommendation driven-by multimodal emotion recognition (named as PSRMER). Specifically, PSRMER first actively identifies a user’s emotion with a multimodal emotion recognition model based on BiGRU and Transformer; Then, considering the user’s emotion and preferences, PSRMER selects the optimal services based on an index-graph linking different emotions and various services; Finally, PSRMER proactively recommends the selected optimal service to the user. Extensive experiments have been conducted and the effectiveness of our proposed method have been proved. Moreover, the proposed method can also be used in smart education, smart transportation, smart elderly care and other modern industry fields.

Single-cell multiomics techniques have been widely applied to detect the key signature of cells. These methods have achieved a single-molecule resolution and can even reveal spatial localization. These emerging methods provide insights elucidating the features of genomic, epigenomic and transcriptomic heterogeneity in individual cells. However, they have given rise to new computational challenges in data processing. Here, we describe Single-cell Single-molecule multiple Omics Pipeline (ScSmOP), a universal pipeline for barcode-indexed single-cell single-molecule multiomics data analysis. Essentially, the C language is utilized in ScSmOP to set up spaced-seed hash table-based algorithms for barcode identification according to ligation-based barcoding data and synthesis-based barcoding data, followed by data mapping and deconvolution. We demonstrate high reproducibility of data processing between ScSmOP and published pipelines in comprehensive analyses of single-cell omics data (scRNA-seq, scATAC-seq, scARC-seq), single-molecule chromatin interaction data (ChIA-Drop, SPRITE, RD-SPRITE), single-cell single-molecule chromatin interaction data (scSPRITE) and spatial transcriptomic data from various cell types and species. Additionally, ScSmOP shows more rapid performance and is a versatile, efficient, easy-to-use and robust pipeline for single-cell single-molecule multiomics data analysis.

Recently, occluded person re-identification (Re-ID) has received significant interest due to its widespread real-world applications. However, most existing occluded person Re-ID methods ignore semantic granularities that indicate different levels of occluded information of the human body, leading to sub-optimal performance. To address this, we propose a Multi-Semantic Feature Learning Network (MSFL-Net) for occluded person Re-ID. Specifically, MSFL-Net involves a backbone network and a Multi-branch Feature Learning sub-network (MFL). MFL consists of two local-global branches and a global branch to learn multisemantic features in a multi-branch deep network architecture. In each local-global branch, we design a local subbranch and a semantic-guided global sub-branch to extract discriminative features at a certain level of feature granularity and semantic granularity. In the global branch, we learn global features at the largest level of semantic granularity. In particular, a patch contrastive loss is developed to explicitly encourage the semantic feature maps to capture the information from specific body parts. By extracting multi-semantic features, our method is effective in dealing with person Re-ID at different occlusion levels. Experimental results on an occluded person Re-ID dataset (Occluded-REID) and two partial person Re-ID datasets (Partial-iLIDS and Partial-REID) show the superiority of our method against state-of-the-art person Re-ID methods.

The emerging ligation-free three-dimensional (3D) genome mapping technologies can identify multiplex chromatin interactions with single-molecule precision. These technologies not only offer new insight into high-dimensional chromatin organization and gene regulation, but also introduce new challenges in data visualization and analysis. To overcome these challenges, we developed MCIBox, a toolkit for multi-way chromatin interaction (MCI) analysis, including a visualization tool and a platform for identifying micro-domains with clustered single-molecule chromatin complexes. MCIBox is based on various clustering algorithms integrated with dimensionality reduction methods that can display multiplex chromatin interactions at single-molecule level, allowing users to explore chromatin extrusion patterns and super-enhancers regulation modes in transcription, and to identify single-molecule chromatin complexes that are clustered into micro-domains. Furthermore, MCIBox incorporates a two-dimensional kernel density estimation algorithm to identify micro-domains boundaries automatically. These micro-domains were stratified with distinctive signatures of transcription activity and contained different cell-cycle-associated genes. Taken together, MCIBox represents an invaluable tool for the study of multiple chromatin interactions and inaugurates a previously unappreciated view of 3D genome structure.