Parents with visual impairments (PVI) encounter unique challenges in engaging their sighted children in outdoor informal learning, yet little is known about how to address these barriers. We first conducted interviews with 11 mixed-ability families to uncover the perceptual, knowledge, and interactional challenges that limit parental participation. Building on these findings, we explored design opportunities across device form factors, interaction mechanisms, and modes of AI mediation through a design consultation, which led to the development of Bond, a distributed Wizard-of-Oz prototype. Bond combines a lightweight child-worn camera with parent-facing prompts to deliver timely, context-aware support for joint attention and conversation. A field study with 14 families demonstrated increased parental responsiveness, deepened parent–child dialogue, and strengthened parents’ confidence, while fostering children’s curiosity and co-exploration. We introduce Symbiotic Learning as a conceptual lens that reframes AI as a relational mediator bridging perceptual asymmetry, offering design considerations for inclusive, co-constructed learning in mixed-ability families.

OBJECTIVE: Introduce the task of wound care multimodal multilingual visual question answering, provide baseline performances, and identify areas of future study. METHODS: A dataset of wound care multimodal multilingual visual question answering (VQA) was created using consumer health questions asked online. Practicing US medical doctors were tasked with providing metadata and expert responses labels. Several instruct-enabled, multilingual visual question answering models (GPT-4o, Gemini-1.5-Pro, and Qwen-VL) were tested to benchmark performances. Finally, automatic evaluations were tested against domain expert response ratings. RESULTS: A multilingual dataset of 477 wound care cases, 768 responses, 748 images, 3k structured data labels, 1362 translation instances, and 10k judgments was constructed (https://osf.io/xsj5u/). Metadata scores ranged from 0.32-0.78 accuracy depending on classification type; response generation performances 0.06 BLEU, 0.66 BERTScore, 0.45 ROUGE-L in English and 0.12 BLEU, 0.69 BERTScore, and 0.50 ROUGE-L in Chinese. CONCLUSION: We construct and explore the tasks of multimodal, multilingual VQA. We hope the work here can inspire further research in wound care metadata classification, VQA response generation, and open response automatic evaluation.

Drug discovery faces challenges due to the vast chemical space and complex drug-target interactions. This paper proposes a novel deep learning framework TD-GPT for targeted drug molecule generation. TD-GPT comprises a linear Transformer for drug-target affinity prediction, an affinity-enhanced protein encoder using sequences, and a target-specific attention module in the molecular Transformer decoder. Experiments demonstrate TD-GPT’s efficiency in generating valid, novel molecules with high affinity and specificity for desired targets without target fine-tuning. The model provides a new paradigm for accelerated, cost-effective drug discovery.

Seasonal influenza epidemics which annually cause substantial diseases and deaths in high-risk population groups are a major public health concern around the world. Considering the hysteresis of traditional flu surveillance systems, this work aims to present a methodology capable of forecasting influenza activity of a city in China precisely 1 week ahead of the official publication. To that end, exogenous information collected from different sources were separately tested with historical influenza-like illness reports for the ability of detecting influenza activity, including climate surveillance, Internet users’ search activity, twitter and health inquiry on an online health consultation platform. Moreover, an ensemble model combining a time series analysis model and a tree boosting model based on those multisource data was applied to improve the accuracy and generalizability of influenza forecasting, in which a model fusion method based on the Kalman Filter was proposed. The validation experiments in this work were performed on the influenza-like illness reports collected from Chongqing city over 4 influenza seasons within 2014–2017. The results show that the proposed model outperformed other tested models by not only taking the periodic law of influenza into consideration but also incorporating information from diverse data sources. The mean absolute percentage error of the validation data set decreased to about 10%. This work provides a viable suggestion for improving the influenza activity forecasting of a city at its early stage.

Product identity can affect a new mobile phone's acceptance and an enterprise's succession. This paper, from the identity of features and styles, studied the mobile phone's computer-supported cooperative design. To solve the disagreements appearing in this cooperative process objectively, we introduced the methods of cognitive psychology and Kansei engineering and conducted an Internet/intranet recognition experiment. The experiment results confirmed the differences quantitatively among manufacturers, industrial designers and consumers on the recognition of mobile phone's features and styles, and expressed the differences in a visual way. Based on the experiment results, by communicating with each other, industrial designers generated the accepted solutions, which proved the positive function of ours methods in cooperative design