arXiv subjects

Xin Hu

Publications and source records attributed to Xin Hu.

At least 37 records · Page 2Linked to original sources

arXiv2025

PediaMind-R1: A Temperament-Aware Language Model for Personalized Early Childhood Care Reasoning via Cognitive Modeling and Preference Alignment

This paper presents PediaMind-R1, a domain-specialized large language model designed to achieve active personalization in intelligent parenting scenarios. Unlike conventional systems that provide generic suggestions, PediaMind-R1 draws on insights from developmental psychology. It introduces temperament theory from the Thomas-Chess framework and builds a temperament knowledge graph for infants and toddlers (0-3 years). Our two-stage training pipeline first uses supervised fine-tuning to teach structured chain-of-thought reasoning, and then applies a GRPO-based alignment stage to reinforce logical consistency, domain expertise, and empathetic caregiving strategies. We further design an evaluation framework comprising temperament-sensitive multiple-choice tests and human assessments. The results demonstrate that PediaMind-R1 can accurately interpret early childhood temperament profiles and proactively engage in individualized reasoning. This work highlights the value of integrating vertical-domain modeling with psychological theory. It offers a novel approach to developing user-centered LLMs that advance the practice of active personalization in sensitive caregiving contexts.

cs.CL↗

arXiv2025

TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognition

Multimodal Emotion Recognition (MER) aims to accurately identify human emotional states by integrating heterogeneous modalities such as visual, auditory, and textual data. Existing approaches predominantly rely on unified emotion labels to supervise model training, often overlooking a critical challenge: inter-modal emotion conflicts, wherein different modalities within the same sample may express divergent emotional tendencies. In this work, we address this overlooked issue by proposing a novel framework, Typicality-based Consistent-aware Multimodal Emotion Recognition (TiCAL), inspired by the stage-wise nature of human emotion perception. TiCAL dynamically assesses the consistency of each training sample by leveraging pseudo unimodal emotion labels alongside a typicality estimation. To further enhance emotion representation, we embed features in a hyperbolic space, enabling the capture of fine-grained distinctions among emotional categories. By incorporating consistency estimates into the learning process, our method improves model performance, particularly on samples exhibiting high modality inconsistency. Extensive experiments on benchmark datasets, e.g, CMU-MOSEI and MER2023, validate the effectiveness of TiCAL in mitigating inter-modal emotional conflicts and enhancing overall recognition accuracy, e.g., with about 2.6% improvements over the state-of-the-art DMD.

cs.CV↗

arXiv2025

VLMs Guided Interpretable Decision Making for Autonomous Driving

Recent advancements in autonomous driving (AD) have explored the use of vision-language models (VLMs) within visual question answering (VQA) frameworks for direct driving decision-making. However, these approaches often depend on handcrafted prompts and suffer from inconsistent performance, limiting their robustness and generalization in real-world scenarios. In this work, we evaluate state-of-the-art open-source VLMs on high-level decision-making tasks using ego-view visual inputs and identify critical limitations in their ability to deliver reliable, context-aware decisions. Motivated by these observations, we propose a new approach that shifts the role of VLMs from direct decision generators to semantic enhancers. Specifically, we leverage their strong general scene understanding to enrich existing vision-based benchmarks with structured, linguistically rich scene descriptions. Building on this enriched representation, we introduce a multi-modal interactive architecture that fuses visual and linguistic features for more accurate decision-making and interpretable textual explanations. Furthermore, we design a post-hoc refinement module that utilizes VLMs to enhance prediction reliability. Extensive experiments on two autonomous driving benchmarks demonstrate that our approach achieves state-of-the-art performance, offering a promising direction for integrating VLMs into reliable and interpretable AD systems.

cs.CV↗

arXiv2025

Does Bigger Mean Better? Comparitive Analysis of CNNs and Biomedical Vision Language Modles in Medical Diagnosis

The accurate interpretation of chest radiographs using automated methods is a critical task in medical imaging. This paper presents a comparative analysis between a supervised lightweight Convolutional Neural Network (CNN) and a state-of-the-art, zero-shot medical Vision-Language Model (VLM), BiomedCLIP, across two distinct diagnostic tasks: pneumonia detection on the PneumoniaMNIST benchmark and tuberculosis detection on the Shenzhen TB dataset. Our experiments show that supervised CNNs serve as highly competitive baselines in both cases. While the default zero-shot performance of the VLM is lower, we demonstrate that its potential can be unlocked via a simple yet crucial remedy: decision threshold calibration. By optimizing the classification threshold on a validation set, the performance of BiomedCLIP is significantly boosted across both datasets. For pneumonia detection, calibration enables the zero-shot VLM to achieve a superior F1-score of 0.8841, surpassing the supervised CNN's 0.8803. For tuberculosis detection, calibration dramatically improves the F1-score from 0.4812 to 0.7684, bringing it close to the supervised baseline's 0.7834. This work highlights a key insight: proper calibration is essential for leveraging the full diagnostic power of zero-shot VLMs, enabling them to match or even outperform efficient, task-specific supervised models.

cs.CV↗

arXiv2025

StructLayoutFormer:Conditional Structured Layout Generation via Structure Serialization and Disentanglement

Structured layouts are preferable in many 2D visual contents (\eg, GUIs, webpages) since the structural information allows convenient layout editing. Computational frameworks can help create structured layouts but require heavy labor input. Existing data-driven approaches are effective in automatically generating fixed layouts but fail to produce layout structures. We present StructLayoutFormer, a novel Transformer-based approach for conditional structured layout generation. We use a structure serialization scheme to represent structured layouts as sequences. To better control the structures of generated layouts, we disentangle the structural information from the element placements. Our approach is the first data-driven approach that achieves conditional structured layout generation and produces realistic layout structures explicitly. We compare our approach with existing data-driven layout generation approaches by including post-processing for structure extraction. Extensive experiments have shown that our approach exceeds these baselines in conditional structured layout generation. We also demonstrate that our approach is effective in extracting and transferring layout structures. The code is publicly available at %\href{https://github.com/Teagrus/StructLayoutFormer} {https://github.com/Teagrus/StructLayoutFormer}.

cs.GR↗

arXiv2025

Lightweight Baselines for Medical Abstract Classification: DistilBERT with Cross-Entropy as a Strong Default

The research evaluates lightweight medical abstract classification methods to establish their maximum performance capabilities under financial budget restrictions. On the public medical abstracts corpus, we finetune BERT base and Distil BERT with three objectives cross entropy (CE), class weighted CE, and focal loss under identical tokenization, sequence length, optimizer, and schedule. DistilBERT with plain CE gives the strongest raw argmax trade off, while a post hoc operating point selection (validation calibrated, classwise thresholds) sub stantially improves deployed performance; under this tuned regime, focal benefits most. We report Accuracy, Macro F1, and WeightedF1, release evaluation artifacts, and include confusion analyses to clarify error structure. The practical takeaway is to start with a compact encoder and CE, then add lightweight calibration or thresholding when deployment requires higher macro balance.

cs.CL↗

arXiv2025

Renaissance of RNNs in Streaming Clinical Time Series: Compact Recurrence Remains Competitive with Transformers

We present a compact, strictly causal benchmark for streaming clinical time series on the MIT--BIH Arrhythmia Database using per-second heart rate. Two tasks are studied under record-level, non-overlapping splits: near-term tachycardia risk (next ten seconds) and one-step heart rate forecasting. We compare a GRU-D (RNN) and a Transformer under matched training budgets against strong non-learned baselines. Evaluation is calibration-aware for classification and proper for forecasting, with temperature scaling and grouped bootstrap confidence intervals. On MIT-BIH, GRU-D slightly surpasses the Transformer for tachycardia risk, while the Transformer clearly lowers forecasting error relative to GRU-D and persistence. Our results show that, in longitudinal monitoring, model choice is task-dependent: compact RNNs remain competitive for short-horizon risk scoring, whereas compact Transformers deliver clearer gains for point forecasting.

cs.LG↗

arXiv2025

Multi-branch of Attention Yields Accurate Results for Tabular Data

Tabular data inherently exhibits significant feature heterogeneity, but existing transformer-based methods lack specialized mechanisms to handle this property. To bridge the gap, we propose MAYA, an encoder-decoder transformer-based framework. In the encoder, we design a Multi-Branch of Attention (MBA) that constructs multiple parallel attention branches and averages the features at each branch, effectively fusing heterogeneous features while limiting parameter growth. Additionally, we employ collaborative learning with a dynamic consistency weight constraint to produce more robust representations. In the decoder stage, cross-attention is utilized to seamlessly integrate tabular data with corresponding label features. This dual-attention mechanism effectively captures both intra-instance and inter-instance interactions. We evaluate the proposed method on a wide range of datasets and compare it with other state-of-the-art transformer-based methods. Extensive experiments demonstrate that our model achieves superior performance among transformer-based methods in both tabular classification and regression tasks.

cs.LG↗

arXiv2025

Dynamic Prompt Fusion for Multi-Task and Cross-Domain Adaptation in LLMs

This study addresses the generalization limitations commonly observed in large language models under multi-task and cross-domain settings. Unlike prior methods such as SPoT, which depends on fixed prompt templates, our study introduces a unified multi-task learning framework with dynamic prompt scheduling mechanism. By introducing a prompt pool and a task-aware scheduling strategy, the method dynamically combines and aligns prompts for different tasks. This enhances the model's ability to capture semantic differences across tasks. During prompt fusion, the model uses task embeddings and a gating mechanism to finely control the prompt signals. This ensures alignment between prompt content and task-specific demands. At the same time, it builds flexible sharing pathways across tasks. In addition, the proposed optimization objective centers on joint multi-task learning. It incorporates an automatic learning strategy for scheduling weights, which effectively mitigates task interference and negative transfer. To evaluate the effectiveness of the method, a series of sensitivity experiments were conducted. These experiments examined the impact of prompt temperature parameters and task number variation. The results confirm the advantages of the proposed mechanism in maintaining model stability and enhancing transferability. Experimental findings show that the prompt scheduling method significantly improves performance on a range of language understanding and knowledge reasoning tasks. These results fully demonstrate its applicability and effectiveness in unified multi-task modeling and cross-domain adaptation.

cs.CL↗

arXiv2025

eSkinHealth: A Multimodal Dataset for Neglected Tropical Skin Diseases

Skin Neglected Tropical Diseases (NTDs) impose severe health and socioeconomic burdens in impoverished tropical communities. Yet, advancements in AI-driven diagnostic support are hindered by data scarcity, particularly for underrepresented populations and rare manifestations of NTDs. Existing dermatological datasets often lack the demographic and disease spectrum crucial for developing reliable recognition models of NTDs. To address this, we introduce eSkinHealth, a novel dermatological dataset collected on-site in Côte d'Ivoire and Ghana. Specifically, eSkinHealth contains 5,623 images from 1,639 cases and encompasses 47 skin diseases, focusing uniquely on skin NTDs and rare conditions among West African populations. We further propose an AI-expert collaboration paradigm to implement foundation language and segmentation models for efficient generation of multimodal annotations, under dermatologists' guidance. In addition to patient metadata and diagnosis labels, eSkinHealth also includes semantic lesion masks, instance-specific visual captions, and clinical concepts. Overall, our work provides a valuable new resource and a scalable annotation framework, aiming to catalyze the development of more equitable, accurate, and interpretable AI tools for global dermatology.

cs.AI↗

arXiv2025

Collaborative Distillation Strategies for Parameter-Efficient Language Model Deployment

This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and integrates their output probability distributions and intermediate semantic features. This guides the student model to learn from multiple sources of knowledge. As a result, the student model gains stronger language understanding and generation ability while maintaining a small parameter size. To achieve this, the paper introduces a weighted output fusion mechanism, a feature alignment loss function, and an entropy-driven dynamic teacher weighting strategy. These components improve the quality and stability of knowledge transfer during distillation. Under multi-teacher guidance, the student model captures semantic information more effectively and demonstrates strong performance across multiple evaluation metrics. In particular, the method shows high consistency in expression, generalization ability, and task adaptability in tasks such as language modeling, text generation, and multi-task learning. The experiments compare the proposed method with several widely adopted distillation approaches. The results further confirm its overall advantages in perplexity, distillation loss, and generation quality. This study provides a feasible technical path for the efficient compression of large-scale language models. It also demonstrates the effectiveness of multi-teacher collaborative mechanisms in complex language modeling tasks.

cs.CL↗

arXiv2025

SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning

Panoptic Scene Graph Generation (PSG) integrates instance segmentation with relation understanding to capture pixel-level structural relationships in complex scenes. Although recent approaches leveraging pre-trained vision-language models (VLMs) have significantly improved performance in the open-vocabulary setting, they commonly ignore the inherent limitations of VLMs in spatial relation reasoning, such as difficulty in distinguishing object relative positions, which results in suboptimal relation prediction. Motivated by the denoising diffusion model's inversion process in preserving the spatial structure of input images, we propose SPADE (SPatial-Aware Denoising-nEtwork) framework -- a novel approach for open-vocabulary PSG. SPADE consists of two key steps: (1) inversion-guided calibration for the UNet adaptation, and (2) spatial-aware context reasoning. In the first step, we calibrate a general pre-trained teacher diffusion model into a PSG-specific denoising network with cross-attention maps derived during inversion through a lightweight LoRA-based fine-tuning strategy. In the second step, we develop a spatial-aware relation graph transformer that captures both local and long-range contextual information, facilitating the generation of high-quality relation queries. Extensive experiments on benchmark PSG and Visual Genome datasets demonstrate that SPADE outperforms state-of-the-art methods in both closed- and open-set scenarios, particularly for spatial relationship prediction.

cs.CV↗

arXiv2025

Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition

Visual Emotion Recognition (VER) is a critical yet challenging task aimed at inferring emotional states of individuals based on visual cues. However, existing works focus on single domains, e.g., realistic images or stickers, limiting VER models' cross-domain generalizability. To fill this gap, we introduce an Unsupervised Cross-Domain Visual Emotion Recognition (UCDVER) task, which aims to generalize visual emotion recognition from the source domain (e.g., realistic images) to the low-resource target domain (e.g., stickers) in an unsupervised manner. Compared to the conventional unsupervised domain adaptation problems, UCDVER presents two key challenges: a significant emotional expression variability and an affective distribution shift. To mitigate these issues, we propose the Knowledge-aligned Counterfactual-enhancement Diffusion Perception (KCDP) framework. Specifically, KCDP leverages a VLM to align emotional representations in a shared knowledge space and guides diffusion models for improved visual affective perception. Furthermore, a Counterfactual-Enhanced Language-image Emotional Alignment (CLIEA) method generates high-quality pseudo-labels for the target domain. Extensive experiments demonstrate that our model surpasses SOTA models in both perceptibility and generalization, e.g., gaining 12% improvements over the SOTA VER model TGCA-PVT. The project page is at https://yinwen2019.github.io/ucdver.

cs.CV↗

arXiv2025

Valley Polarization and Anomalous Valley Hall Effect in Altermagnet Ti2Se2S with Multipiezo Properties

Recently, altermagnets demonstrate numerous newfangle physical phenomena due to their inherent antiferromagnetic coupling and spontaneous spin splitting, that are anticipated to enable innovative spintronic devices. However, the rare two-dimensional altermagnets have been reported, making it difficult to meet the requirements for high-performance spintronic devices on account of the growth big data. Here, we predict a stable monolayer Ti2Se2S with out-of-plane altermagnetic ground state and giant valley splitting. The electronic properties of altermagnet Ti2Se2S are highly dependent on the onsite electron correlation. Through symmetry analysis, we find that the valleys of X and Y points are protected by the mirror Mxy symmetry rather than the time-reversal symmetry. Therefore, the multipiezo effect, including piezovalley and piezomagnetism, can be induced by the uniaxial strain. The total valley splitting of monolayer Ti2Se2S can be as high as ~500 meV. Most interestingly, the direction of valley polarization can be effectively tuned by the uniaxial strain, based on this, we have defined logical "0", "+1", and "-1" states for data transmission and storage. In addition, we have designed a schematic diagram for observing the anomalous Hall effect in experimentally. Our findings have enriched the candidate materials of two-dimensional altermagnet for the ultra-fast and low power consumption device applications.

cond-mat.mtrl-sci↗

arXiv2025

Toeplitz Operators on Fock Space $F_α^{\infty}$

In this paper, we study necessary and sufficient conditions for a positive Borel measure $μ$ on the complex space $\mathbb{C}$ to be a $(\infty,q)$ or $(p,\infty)$ (vanishing) Fock-Carleson measure through its Berezin transform. Then we discuss boundedness and compactness of the Toeplitz operator $T_μ$ with a positive Borel measure $μ$ as symbol on Fock space $F_α^{\infty}$. Furthermore, we charaterize these properties of the Toeplitz operator T_φ$ with a symbol $φ$ which is in $BMO$.

math.FA↗

arXiv2025

Enhancing Skin Disease Diagnosis: Interpretable Visual Concept Discovery with SAM

Current AI-assisted skin image diagnosis has achieved dermatologist-level performance in classifying skin cancer, driven by rapid advancements in deep learning architectures. However, unlike traditional vision tasks, skin images in general present unique challenges due to the limited availability of well-annotated datasets, complex variations in conditions, and the necessity for detailed interpretations to ensure patient safety. Previous segmentation methods have sought to reduce image noise and enhance diagnostic performance, but these techniques require fine-grained, pixel-level ground truth masks for training. In contrast, with the rise of foundation models, the Segment Anything Model (SAM) has been introduced to facilitate promptable segmentation, enabling the automation of the segmentation process with simple yet effective prompts. Efforts applying SAM predominantly focus on dermatoscopy images, which present more easily identifiable lesion boundaries than clinical photos taken with smartphones. This limitation constrains the practicality of these approaches to real-world applications. To overcome the challenges posed by noisy clinical photos acquired via non-standardized protocols and to improve diagnostic accessibility, we propose a novel Cross-Attentive Fusion framework for interpretable skin lesion diagnosis. Our method leverages SAM to generate visual concepts for skin diseases using prompts, integrating local visual concepts with global image features to enhance model performance. Extensive evaluation on two skin disease datasets demonstrates our proposed method's effectiveness on lesion diagnosis and interpretability.

cs.CV↗

arXiv2025

Evaluating the Ability of Large Language Models to Generate Verifiable Specifications in VeriFast

Static verification is a powerful method for enhancing software quality, but it demands significant human labor and resources. This is particularly true of static verifiers that reason about heap manipulating programs using an ownership logic. LLMs have shown promise in a number of software engineering activities, including code generation, test generation, proof generation for theorem provers, and specification generation for static verifiers. However, prior work has not explored how well LLMs can perform specification generation for specifications based in an ownership logic, such as separation logic. To address this gap, this paper explores OpenAI's GPT-4o model's effectiveness in generating specifications on C programs that are verifiable with VeriFast, a separation logic based static verifier. Our experiment employs three different types of user inputs as well as basic and Chain-of-Thought (CoT) prompting to assess GPT's capabilities. Our results indicate that the specifications generated by GPT-4o preserve functional behavior, but struggle to be verifiable. When the specifications are verifiable they contain redundancies. Future directions are discussed to improve the performance.

cs.SE↗

arXiv2025

Architected Dual-Network Solvent-free Adhesives for Stretchable Fabrics

Natural systems, such as tendons and spider silk, demonstrate how the combination of strength and stretchability can be effectively achieved by integrating stiff and flexible network structures. Inspired by these systems, we developed a novel, solvent-free dual-network adhesive based on a self-assembling ABA triblock copolymer, poly(methyl methacrylate)-poly(n-butyl acrylate)-poly(methyl methacrylate) (PMMA-b-PnBA-b-PMMA), designed for applications requiring both high strength and stretchability. The triblock copolymer forms a physically crosslinked network through microdomains of PMMA end-blocks that provide structural integrity, while the PnBA mid-block forms a soft, stretchable matrix. To further enhance mechanical performance, a second poly(n-butyl acrylate) (PnBA) network is polymerized in situ, locking the PMMA microdomains in place and creating a load-bearing system. By varying the crosslinking density of the secondary network, we tailor the adhesive's mechanical properties (Young's modulus: 0.17 - 1.18 MPa) to suit different substrates, creating a mechanically transparent seam. The resulting dual-network system combines different strategies to achieve high strength and stretchability, with adhesive performance comparable to industrial methods such as sewing, particularly in bonding neoprene fabric composites and sealing the joints. Our solvent-free approach also eliminates the need for lengthy solvent evaporation steps, offering an eco-friendly and more efficient alternative for flexible adhesive applications in fields such as soft robotics, flexible electronics, and sports apparel.

cond-mat.mtrl-sci↗