Searcharxiv⌕ Search

arXiv subjects

Wen Ma

Publications and source records attributed to Wen Ma.

15 recordsLinked to original sources
arXiv2026

CyberSelf: Embodied Self-Distancing for Emotional Support in Virtual Reality

Self-distancing is an effective emotion regulation strategy; however, it may fail during personal crises due to its cognitive demands. Virtual Reality (VR) provides a novel approach to externalizing psychological distance by enabling embodied self-representation. In this paper, we present CyberSelf, a VR system for emotional support that integrates a visually self-resembling avatar, a cloned self-voice, and Large Language Model (LLM)-driven real-time dialogue. The system enables users to engage in multi-turn conversations with their self-representations in immersive VR, enabling embodied self-distancing while maintaining a strong sense of self-relevance. We evaluated CyberSelf in a short-term study that compares three levels of self-representation richness (Text, Text+Voice, and Text+Voice+Appearance). The results demonstrated robust pre-post improvements across affective and coping measures, specifically increased valence, arousal, hope, and resilience, as well as reduced anxiety and simulator sickness. Richer representations increased conversational engagement, and full embodiment produced the strongest physiological indicators of emotional regulation. A subsequent four-week long-term study demonstrated that these benefits are both sustainable and cumulative. Additionally, users rated the reconstructed avatar and the cloned voice as highly recognizable and acceptable. Collectively, these findings suggest that embodied, self-resembling conversational agents provide a viable mechanism for externalizing self-distancing and supporting emotional regulation in VR.

cs.HC↗
arXiv2026

Structure-aware Knowledge-guided Heterogeneous Mamba for Zygomaticomaxillary Suture Assessment

The Zygomaticomaxillary Suture is a key circummaxillary structure that connects the zygomatic bone and the maxilla, which serves as a primary site of resistance during maxillary advancement, and its maturation status directly influences the timing and efficacy of orthopedic interventions. However, accurate staging of ZMS maturation remains challenging due to subtle high-frequency transitions in suture lines and the global semantic ambiguity between adjacent stages. To address this, we present the first public ZMS dataset, comprising 3,790 ZMS images covering the entire age range from 4 to 24 years. Based on this dataset, we propose SKMamba, a Structure-aware and Knowledge-guided Mamba-based multi-modal framework for automated ZMS maturation assessment. SKMamba adopts a decoupled dual-path architecture that mimics the hierarchical diagnostic process used by experienced orthodontists. We first introduce an Implicit Edge Extractor (IEE), which leverages structural pre-training to reduce trabecular noise and accentuate sutural boundaries. Complementarily, a Cross-Modal Semantic Alignment (CSA) module is designed to incorporate anatomical descriptions from a large language model (LLM). This module helps align local morphological cues with global semantic descriptions while ensuring that objective morphological evidence remains the primary basis for decisions. Extensive experiments on our ZMS dataset demonstrate that SKMamba achieves state-of-the-art performance compared to existing methods. Code is available at https://github.com/galaxygxq1116/SKMamba.

cs.CV↗
arXiv2026

Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs

Vision-language models have demonstrated impressive capabilities in general medical visual question answering, yet due to limited interpretability, it remains unclear whether their predictions reflect evidence-grounded clinical reasoning or reliance on spurious priors. We introduce Med-R2 Bench, a hierarchical benchmark aligned with the clinical workflow to evaluate adversarial robustness with visual grounding. We design stepwise QA tasks to assess whether reasoning chains are strictly grounded in visual evidence across the four clinical stages, and employ adversarial perturbations to test robustness against misleading cues. Med-R2 comprises 42,432 images, 31 task categories, and 110,406 QA pairs. Evaluation across 14 VLMs reveals a sequential performance degradation along the four-stage clinical workflow. Adversarial experiments show that models rely heavily on correct prompts to guess answers. Even when provided with explicit visual cues, the models struggle to accurately align textual descriptions. Finally, we demonstrate stepwise fine-tuning using our hierarchical data significantly improves reasoning robustness, highlighting its potential to drive future improvements in evidence-based medical AI.

cs.CV↗
arXiv2026

SIGMA-ASL: Sensor-Integrated Multimodal Dataset for Sign Language Recognition

Automatic sign language recognition (SLR) has become a key enabler of inclusive human-computer interaction, fostering seamless communication between deaf individuals and hearing communities. Despite significant advances in multimodal learning, existing SLR research remains dominated by vision-based datasets, which are limited by sensitivity to lighting and occlusion, privacy concerns, and a lack of cross-modal diversity. To address these challenges, we introduce SIGMA-ASL, a large-scale multimodal dataset for SLR. The dataset integrates an Azure Kinect RGB-D camera, a millimeter-wave (mmWave) radar, and two wrist-worn inertial measurement units (IMUs) to capture complementary visual, radio-reflection, and kinematic information. Collected in a controlled studio environment with 20 participants performing 160 common American sign language (ASL) signs, SIGMA-ASL provides 93,545 temporally synchronized word-level multimodal clips. A unified sensing framework achieves millisecond-level alignment across modalities, enabling reliable sensor fusion and cross-modal learning. We further design standardized preprocessing pipelines and benchmarking protocols under both user-dependent and user-independent settings, offering a comprehensive foundation for evaluating single and multimodal SLR. Extensive experiments validate the dataset's quality and demonstrate its potential as a valuable resource for developing robust, privacy-preserving, and ubiquitous sign language recognition systems.

cs.HC↗
arXiv2026

HICT: High-precision 3D CBCT reconstruction from a single X-ray

Accurate 3D dental imaging is vital for diagnosis and treatment planning, yet CBCT's high radiation dose and cost limit its accessibility. Reconstructing 3D volumes from a single low-dose panoramic X-ray is a promising alternative but remains challenging due to geometric inconsistencies and limited accuracy. We propose HiCT, a two-stage framework that first generates geometrically consistent multi-view projections from a single panoramic image using a video diffusion model, and then reconstructs high-fidelity CBCT from the projections using a ray-based dynamic attention network and an X-ray sampling strategy. To support this, we built XCT, a large-scale dataset combining public CBCT data with 500 paired PX-CBCT cases. Extensive experiments show that HiCT achieves state-of-the-art performance, delivering accurate and geometrically consistent reconstructions for clinical use.

cs.CV↗
arXiv2025

LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability

Generating long, informative, and factual outputs remains a major challenge for Large Language Models (LLMs). Existing benchmarks for long-form generation typically assess real-world queries with hard-to-verify metrics or use synthetic setups that ease evaluation but overlook real-world intricacies. In this paper, we introduce \textbf{LongWeave}, which balances real-world and verifiable assessment with Constraint-Verifier Evaluation (CoV-Eval). CoV-Eval constructs tasks by first defining verifiable targets within real-world scenarios, then systematically generating corresponding queries, textual materials, and constraints based on these targets. This ensures that tasks are both realistic and objectively assessable, enabling rigorous assessment of model capabilities in meeting complex real-world constraints. LongWeave supports customizable input/output lengths (up to 64K/8K tokens) across seven distinct tasks. Evaluation on 23 LLMs shows that even state-of-the-art models encounter significant challenges in long-form generation as real-world complexity and output length increase.

cs.CL↗
arXiv2025

Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding

While Large Language Models (LLMs) support long contexts, they struggle with performance degradation within the context window. Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored. From the decoding perspective, we identify the Posterior Salience Attenuation (PSA) phenomenon, where the salience ratio correlates with long-text performance degradation. Notably, despite the attenuation, gold tokens still occupy high-ranking positions in the decoding space. Motivated by it, we propose the training-free Positional Contrastive Decoding (PCD) that contrasts the logits derived from long-aware attention with those from designed local-aware attention, enabling the model to focus on the gains introduced by large-scale short-to-long training. Through the analysis of long-term decay simulation, we demonstrate that PCD effectively alleviates attention score degradation. Experimental results show that PCD achieves state-of-the-art performance on long-context benchmarks.

cs.CL↗
arXiv2024

PX2Tooth: Reconstructing the 3D Point Cloud Teeth from a Single Panoramic X-ray

Reconstructing the 3D anatomical structures of the oral cavity, which originally reside in the cone-beam CT (CBCT), from a single 2D Panoramic X-ray(PX) remains a critical yet challenging task, as it can effectively reduce radiation risks and treatment costs during the diagnostic in digital dentistry. However, current methods are either error-prone or only trained/evaluated on small-scale datasets (less than 50 cases), resulting in compromised trustworthiness. In this paper, we propose PX2Tooth, a novel approach to reconstruct 3D teeth using a single PX image with a two-stage framework. First, we design the PXSegNet to segment the permanent teeth from the PX images, providing clear positional, morphological, and categorical information for each tooth. Subsequently, we design a novel tooth generation network (TGNet) that learns to transform random point clouds into 3D teeth. TGNet integrates the segmented patch information and introduces a Prior Fusion Module (PFM) to enhance the generation quality, especially in the root apex region. Moreover, we construct a dataset comprising 499 pairs of CBCT and Panoramic X-rays. Extensive experiments demonstrate that PX2Tooth can achieve an Intersection over Union (IoU) of 0.793, significantly surpassing previous methods, underscoring the great potential of artificial intelligence in digital dentistry.

cs.CV↗
arXiv2024

Super Efficient Neural Network for Compression Artifacts Reduction and Super Resolution

Video quality can suffer from limited internet speed while being streamed by users. Compression artifacts start to appear when the bitrate decreases to match the available bandwidth. Existing algorithms either focus on removing the compression artifacts at the same video resolution, or on upscaling the video resolution but not removing the artifacts. Super resolution-only approaches will amplify the artifacts along with the details by default. We propose a lightweight convolutional neural network (CNN)-based algorithm which simultaneously performs artifacts reduction and super resolution (ARSR) by enhancing the feature extraction layers and designing a custom training dataset. The output of this neural network is evaluated for test streams compressed at low bitrates using variable bitrate (VBR) encoding. The output video quality shows a 4-6 increase in video multi-method assessment fusion (VMAF) score compared to traditional interpolation upscaling approaches such as Lanczos or Bicubic.

cs.CV↗
arXiv2021

Batalin--Vilkovisky algebra structures on the Hochschild cohomology of generalized Weyl algebras

This paper is devoted to the calculation of Batalin-Vilkovisky algebra structures on the Hochschild cohomology of skew Calabi-Yau generalized Weyl algebras. We firstly establish a Van den Bergh duality at the level of complex. Then based on the results of Solotar et al., we apply Kowalzig and Krähmer's method to the Hochschild homology of generalized Weyl algebras, and translate the homological information into cohomological one by virtue of the Van den Bergh duality, obtaining the desired Batalin-Vilkovisky algebra structures. Finally, we apply our results to quantum weighted projective lines and Podleś quantum spheres, and the Batalin-Vilkovisky algebra structures for them are described completely.

math.RA↗
arXiv2021

New Galois Hulls of GRS Codes and Application to EAQECCs

Galois hulls of linear codes have important applications in quantum coding theory. In this paper, we construct some new classes of (extended) generalized Reed-Solomon (GRS) codes with Galois hulls of arbitrary dimensions. We also propose a general method on constructing GRS codes with Galois hulls of arbitrary dimensions from special Euclidean orthogonal GRS codes. Finally, we construct several new families of entanglement-assisted quantum error-correcting codes (EAQECCs) and MDS EAQECCs by utilizing the above results.

cs.IT↗
arXiv2020

Non-Volatile Memory Array Based Quantization- and Noise-Resilient LSTM Neural Networks

In cloud and edge computing models, it is important that compute devices at the edge be as power efficient as possible. Long short-term memory (LSTM) neural networks have been widely used for natural language processing, time series prediction and many other sequential data tasks. Thus, for these applications there is increasing need for low-power accelerators for LSTM model inference at the edge. In order to reduce power dissipation due to data transfers within inference devices, there has been significant interest in accelerating vector-matrix multiplication (VMM) operations using non-volatile memory (NVM) weight arrays. In NVM array-based hardware, reduced bit-widths also significantly increases the power efficiency. In this paper, we focus on the application of quantization-aware training algorithm to LSTM models, and the benefits these models bring in terms of resilience against both quantization error and analog device noise. We have shown that only 4-bit NVM weights and 4-bit ADC/DACs are needed to produce equivalent LSTM network performance as floating-point baseline. Reasonable levels of ADC quantization noise and weight noise can be naturally tolerated within our NVMbased quantized LSTM network. Benchmark analysis of our proposed LSTM accelerator for inference has shown at least 2.4x better computing efficiency and 40x higher area efficiency than traditional digital approaches (GPU, FPGA, and ASIC). Some other novel approaches based on NVM promise to deliver higher computing efficiency (up to 4.7x) but require larger arrays with potential higher error rates.

cs.NE↗
arXiv2018

Nakayama automorphisms of Ore extensions over polynomial algebras

Nakayama automorphisms play an important role in several mathematical branches, which are known to be tough to compute in general. We compute the Nakayama automorphism $ν$ of any Ore extension $R[x; σ, δ]$ over a polynomial algebra $R$ in $n$ variables for an arbitrary $n$. The formula of $ν$ is obtained explicitly. When $σ$ is not the identity map, the invariant $E^G$ is also investigated in term of Zhang's twist, where $G$ is a cyclic group sharing the same order with $σ$.

math.RA↗
arXiv2017

Perovskite-perovskite tandem photovoltaics with optimized bandgaps

We demonstrate four and two-terminal perovskite-perovskite tandem solar cells with ideally matched bandgaps. We develop an infrared absorbing 1.2eV bandgap perovskite, $FA_{0.75}Cs_{0.25}Sn_{0.5}Pb_{0.5}I_3$, that can deliver 14.8 % efficiency. By combining this material with a wider bandgap $FA_{0.83}Cs_{0.17}Pb(I_{0.5}Br_{0.5})_3$ material, we reach monolithic two terminal tandem efficiencies of 17.0 % with over 1.65 volts open-circuit voltage. We also make mechanically stacked four terminal tandem cells and obtain 20.3 % efficiency. Crucially, we find that our infrared absorbing perovskite cells exhibit excellent thermal and atmospheric stability, unprecedented for Sn based perovskites. This device architecture and materials set will enable 'all perovskite' thin film solar cells to reach the highest efficiencies in the long term at the lowest costs.

cond-mat.mtrl-sci↗