arXiv subjects

Yuqi Hu

Publications and source records attributed to Yuqi Hu.

9 recordsLinked to original sources

arXiv2026

CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention

Accurate monocular depth estimation serves as a core enabler for single camera scene understanding. However, existing self-supervised monocular depth estimation methods generally suffer from the bottleneck of inefficient cross-scale information interaction and difficulty in balancing local and global spatial modeling. In this paper, we propose CMambaDepth, a self-supervised framework that achieves efficient multi-scale feature fusion and fine-grained contextual modeling via channel-wise selective state propagation. Specifically, Bidirectional Channel Mamba (Bi-CMamba) aligns encoder features across scales and enables bidirectional information exchange among ordered scale groups. Unidirectional Channel Mamba (Uni-CMamba) progressively aggregates decoder features and retains fine-grained scale groups through a group selection mechanism for subsequent fusion. Furthermore, a Hybrid Attention Module (HAM) is introduced to combine large-kernel local context and Manhattan self-attention for complementary spatial modeling. Experimental results demonstrate that our method achieves highly competitive performance. Specifically, our model achieves an AbsRel of 0.094 and an RMSE of 4.156 on KITTI, and an AbsRel of 0.140 on DDAD. In the zero-shot cross-dataset generalization test on NYUv2, it attains an AbsRel of 0.232, outperforming the baseline RA-Depth by 7.2%.

cs.CV↗

arXiv2026

A Framework for Generating Semantically Ambiguous Images to Probe Human and Machine Perception

The classic duck-rabbit illusion reveals that when visual evidence is ambiguous, the human brain must decide what it sees. But where exactly do human observers draw the line between ''duck'' and ''rabbit'', and do machine classifiers draw it in the same place? We use semantically ambiguous images as interpretability probes to expose how vision models represent the boundaries between concepts. We present a psychophysically-informed framework that interpolates between concepts in the CLIP embedding space to generate continuous spectra of ambiguous images, allowing us to precisely measure where and how humans and machine classifiers place their semantic boundaries. Using this framework, we show that machine classifiers are more biased towards seeing ''rabbit'', whereas humans are more aligned with the CLIP embedding used for synthesis, and the guidance scale seems to affect human sensitivity more strongly than machine classifiers. Our framework demonstrates how controlled ambiguity can serve as a diagnostic tool to bridge the gap between human psychophysical analysis, image classification, and generative image models, offering insight into human-model alignment, robustness, model interpretability, and image synthesis methods.

cs.CV↗

arXiv2026

Toward Scalable Patient Safety Training: A Prototype for Root Cause Analysis Simulation With AI Virtual Avatars

Patient safety training is essential for preparing healthcare professionals to identify, investigate, and prevent adverse events. However, conventional simulation-based approaches often require substantial faculty time, physical resources, and standardized facilitation. This paper presents a prototype AI-powered simulation platform designed to support more scalable patient safety training through root cause analysis (RCA). The system provides a Unity-based 3D simulation environment, which allows trainees to investigate an ICU adverse event by interviewing five virtual team members represented as AI-powered avatars. Each avatar is driven by a large language model (LLM) agent with role-specific knowledge and variable states of mind. Moreover, emotional text-to-speech and AI-supported facial and body animation enable more realistic and immersive interactions. After completing the simulation, trainees submit a written RCA report and receive rubric-guided formative and summative feedback automatically generated by an LLM-based assessment component. The prototype is built to support patient safety training for healthcare professionals, focusing on skills in communication, investigation, thinking, and analysis, with low recurring instructional burden. We describe the design of the platform, its core technical components, and an RCA case based on a published ICU scenario. This work demonstrates the feasibility of integrating generative AI into immersive simulation for scalable patient safety education.

cs.HC↗

arXiv2026

Simulating the Real World: A Unified Survey of Multimodal Generative Models

Understanding and replicating the real world is a critical challenge in Artificial General Intelligence (AGI) research. To achieve this, many existing approaches, such as world models, aim to capture the fundamental principles governing the physical world, enabling more accurate simulations and meaningful interactions. However, current methods often treat different modalities, including 2D (images), videos, 3D, and 4D representations, as independent domains, overlooking their interdependencies. Additionally, these methods typically focus on isolated dimensions of reality without systematically integrating their connections. In this survey, we present a unified survey for multimodal generative models that investigate the progression of data dimensionality in real-world simulation. Specifically, this survey starts from 2D generation (appearance), then moves to video (appearance+dynamics) and 3D generation (appearance+geometry), and finally culminates in 4D generation that integrate all dimensions. To the best of our knowledge, this is the first attempt to systematically unify the study of 2D, video, 3D and 4D generation within a single framework. To guide future research, we provide a comprehensive review of datasets, evaluation metrics and future directions, and fostering insights for newcomers. This survey serves as a bridge to advance the study of multimodal generative models and real-world simulation within a unified framework.

cs.CV↗

arXiv2025

Brain Connectivity Network Structure Learning For Brain Disorder Diagnosis

Recent studies in neuroscience highlight the significant potential of brain connectivity networks, which are commonly constructed from functional magnetic resonance imaging (fMRI) data for brain disorder diagnosis. Traditional brain connectivity networks are typically obtained using predefined methods that incorporate manually-set thresholds to estimate inter-regional relationships. However, such approaches often introduce redundant connections or overlook essential interactions, compromising the value of the constructed networks. Besides, the insufficiency of labeled data further increases the difficulty of learning generalized representations of intrinsic brain characteristics. To mitigate those issues, we propose a self-supervised framework to learn an optimal structure and representation for brain connectivity networks, focusing on individualized generation and optimization in an unsupervised manner. We firstly employ two existing whole-brain connectomes to adaptively construct their complementary brain network structure learner, and then introduce a multi-state graph-based encoder with a joint iterative learning strategy to simultaneously optimize both the generated network structure and its representation. By leveraging self-supervised pretraining on large-scale unlabeled brain connectivity data, our framework enables the brain connectivity network learner to generalize e ffectively to unseen disorders, while requiring only minimal finetuning of the encoder for adaptation to new diagnostic tasks. Extensive experiments on cross-dataset brain disorder diagnosis demonstrate that our method consistently outperforms state-of-the-art approaches, validating its effectiveness and generalizability. The code is publicly available at https://github.com/neochen1/BCNSL.

cs.GR↗

arXiv2025

"It Felt Like I Was Left in the Dark": Exploring Information Needs and Design Opportunities for Family Caregivers of Older Adult Patients in Critical Care Settings

Older adult patients constitute a rapidly growing subgroup of Intensive Care Unit (ICU) patients. In these situations, their family caregivers are expected to represent the unconscious patients to access and interpret patients' medical information. However, caregivers currently have to rely on overloaded clinicians for information updates and typically lack the health literacy to understand complex medical information. Our project aims to explore the information needs of caregivers of ICU older adult patients, from which we can propose design opportunities to guide future AI systems. The project begins with formative interviews with 11 caregivers to identify their challenges in accessing and interpreting medical information; From these findings, we then synthesize design requirements and propose an AI system prototype to cope with caregivers' challenges. The system prototype has two key features: a timeline visualization to show the AI extracted and summarized older adult patients' key medical events; and an LLM-based chatbot to provide context-aware informational support. We conclude our paper by reporting on the follow-up user evaluation of the system and discussing future AI-based systems for ICU caregivers of older adults.

cs.HC↗

arXiv2025

Magicarpet: A Parent-child Interactive Game Platform to Enhance Connectivity between Autistic Children and Their Parents

Autistic children often face challenges in social interaction and communication, impacting their social connectivity, especially with their parents. Despite the effectiveness of game-based interactive therapy in improving motor skills, research on enhancing parent-child relationships is lacking. We address this gap with Magicarpet, an interactive play carpet that encourages parent-child interaction and has been validated through a user study with five families. The preliminary results indicate that Magicarpet enhances the motivation and participation of autistic children in play, demonstrating the potential of human-computer interaction (HCI) designs to foster connectivity.

cs.HC↗

arXiv2023

CT-based Subchondral Bone Microstructural Analysis in Knee Osteoarthritis via MR-Guided Distillation Learning

Background: MR-based subchondral bone effectively predicts knee osteoarthritis. However, its clinical application is limited by the cost and time of MR. Purpose: We aim to develop a novel distillation-learning-based method named SRRD for subchondral bone microstructural analysis using easily-acquired CT images, which leverages paired MR images to enhance the CT-based analysis model during training. Materials and Methods: Knee joint images of both CT and MR modalities were collected from October 2020 to May 2021. Firstly, we developed a GAN-based generative model to transform MR images into CT images, which was used to establish the anatomical correspondence between the two modalities. Next, we obtained numerous patches of subchondral bone regions of MR images, together with their trabecular parameters (BV / TV, Tb. Th, Tb. Sp, Tb. N) from the corresponding CT image patches via regression. The distillation-learning technique was used to train the regression model and transfer MR structural information to the CT-based model. The regressed trabecular parameters were further used for knee osteoarthritis classification. Results: A total of 80 participants were evaluated. CT-based regression results of trabecular parameters achieved intra-class correlation coefficients (ICCs) of 0.804, 0.773, 0.711, and 0.622 for BV / TV, Tb. Th, Tb. Sp, and Tb. N, respectively. The use of distillation learning significantly improved the performance of the CT-based knee osteoarthritis classification method using the CNN approach, yielding an AUC score of 0.767 (95% CI, 0.681-0.853) instead of 0.658 (95% CI, 0.574-0.742) (p<.001). Conclusions: The proposed SRRD method showed high reliability and validity in MR-CT registration, regression, and knee osteoarthritis classification, indicating the feasibility of subchondral bone microstructural analysis based on CT images.

eess.IV↗

arXiv2023

PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embedding

Is there a unified model for generating molecules considering different conditions, such as binding pockets and chemical properties? Although target-aware generative models have made significant advances in drug design, they do not consider chemistry conditions and cannot guarantee the desired chemical properties. Unfortunately, merging the target-aware and chemical-aware models into a unified model to meet customized requirements may lead to the problem of negative transfer. Inspired by the success of multi-task learning in the NLP area, we use prefix embeddings to provide a novel generative model that considers both the targeted pocket's circumstances and a variety of chemical properties. All conditional information is represented as learnable features, which the generative model subsequently employs as a contextual prompt. Experiments show that our model exhibits good controllability in both single and multi-conditional molecular generation. The controllability enables us to outperform previous structure-based drug design methods. More interestingly, we open up the attention mechanism and reveal coupling relationships between conditions, providing guidance for multi-conditional molecule generation.

cs.AI↗