arXiv subjects

Bin Sheng

Publications and source records attributed to Bin Sheng.

At least 19 recordsLinked to original sources

arXiv2026

SkelGen4D: Weakly-Supervised Skeleton-Based 4D Generation for Text-Driven Mesh Animation

We study 4D generation to synthesize temporally coherent sequences of 3D geometry for animation and content creation. In contrast to existing SDS-based optimization methods and video-driven animation approaches, we adopt a skeleton-driven animation framework aligned with standard industrial pipelines, which enables explicit control and editing. To this end, we propose SkelGen4D, a weakly supervised feed-forward framework for text-driven mesh animation that generates explicit skeleton motions without requiring per-frame skeleton annotations. SkelGen4D first recovers temporally consistent pseudo-skeletons from animated meshes via differentiable fitting, and then generates text-conditioned skeleton motion sequences in a feed-forward manner, further refined with Motion-GRPO to ensure temporally coherent, physically plausible, and articulated animation. We evaluate our method on two large-scale benchmarks, Truebones Zoo and Diffusion4D. Our results show that our weakly supervised skeleton modeling matches or surpasses fully supervised baselines while scaling to diverse object categories for high-quality text-driven mesh animation. Further, our method supports flexible motion editing and is aligned with standard animation production pipelines.

cs.CV↗

arXiv2026

A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trial

Rare diseases affect millions of individuals worldwide, yet timely diagnosis remains a major public health challenge due to scarcity of specialized clinical expertise. While large language models (LLMs) show promise to support rare disease diagnosis, current models are constrained by insufficient clinical deployability, limited clinically grounded evidence, and scarcity of training data. Here we present RaDaR (Rare Disease navigatoR), an open-source, compact reasoning LLM (32B parameters) for rare disease diagnosis. RaDaR was trained with 49,170 publicly available free-text cases and 104,666 synthetic cases with reasoning-enhanced training. RaDaR showed the strongest performance among evaluated open-source models, including the 671B DeepSeek-R1, across public benchmarks and four external validation centers. In a retrospective cohort, RaDaR prioritized the final diagnosis before documented clinical suspicion in 61.06 percent of cases, corresponding to a potential lead time of 1.87 months and 50.18 percent of the within-center interval. In a randomized physician-assistance trial, RaDaR assistance improved physicians' rare-disease diagnostic accuracy by 21.44 percentage points compared with internet search alone. Synthetic-data ablations suggested that phenotype-anchored narratives provide useful training signal for long-tail rare diseases, with a monotonic scaling trend within the tested data range. Together, RaDaR and its development and validation framework provide a deployable rare-disease reasoning model and a reproducible development framework for diagnostic AI under data scarcity.

cs.AI↗

arXiv2026

coDrawAgents: A Multi-Agent Dialogue Framework for Compositional Image Generation

Text-to-image generation has advanced rapidly, but existing models still struggle with faithfully composing multiple objects and preserving their attributes in complex scenes. We propose coDrawAgents, an interactive multi-agent dialogue framework with four specialized agents: Interpreter, Planner, Checker, and Painter that collaborate to improve compositional generation. The Interpreter adaptively decides between a direct text-to-image pathway and a layout-aware multi-agent process. In the layout-aware mode, it parses the prompt into attribute-rich object descriptors, ranks them by semantic salience, and groups objects with the same semantic priority level for joint generation. Guided by the Interpreter, the Planner adopts a divide-and-conquer strategy, incrementally proposing layouts for objects with the same semantic priority level while grounding decisions in the evolving visual context of the canvas. The Checker introduces an explicit error-correction mechanism by validating spatial consistency and attribute alignment, and refining layouts before they are rendered. Finally, the Painter synthesizes the image step by step, incorporating newly planned objects into the canvas to provide richer context for subsequent iterations. Together, these agents address three key challenges: reducing layout complexity, grounding planning in visual context, and enabling explicit error correction. Extensive experiments on benchmarks GenEval and DPG-Bench demonstrate that coDrawAgents substantially improves text-image alignment, spatial accuracy, and attribute binding compared to existing methods.

cs.CV↗

arXiv2025

Performance Analysis of Spatiotemporal 2-D Polar Codes for Massive MIMO with MMSE Receivers

With the evolution from 5G to 6G, ultra-reliable low-latency communication (URLLC) faces increasingly stringent performance requirements. Lower latency constraints demand shorter channel coding lengths, which can severely degrade decoding performance. The massive multiple-input multiple-output (MIMO) system is considered a crucial technology to address this challenge due to its abundant spatial degrees of freedom (DoF). While polar codes are theoretically capacity-achieving in the limit of infinite code length, their practical applicability is limited by significant decoding latency. In this paper, we establish a unified theoretical framework and propose a novel spatiotemporal two-dimensional (2-D) polar coding scheme for massive MIMO systems employing minimum mean square error (MMSE) receivers. The polar transform is jointly applied over both spatial and temporal dimensions to fully exploit the large spatial DoF. By leveraging the near-deterministic signal-to-interference-plus-noise ratio (SINR) property of MMSE detection, the spatial domain is modeled as a set of parallel Gaussian sub-channels. Within this framework, we perform a theoretical analysis of the 2-D polarization behavior using the Gaussian approximation method, and the capacity-achieving property of the proposed scheme is proved under finite blocklength constraints and large spatial DoF. Simulation results further demonstrate that, compared to traditional time-domain polar codes, the proposed 2-D scheme can significantly reduce latency while guaranteeing reliability, or alternatively improve reliability under the same latency constraint -- offering a capacity-achieving and latency-efficient channel coding solution for massive MIMO systems in future 6G URLLC scenarios.

cs.IT↗

arXiv2025

CGM Data Analysis 2.0: Functional Data Pattern Recognition and Artificial Intelligence Applications

New methods of CGM data analysis are emerging that are valuable for interpreting CGM patterns and underlying metabolic physiology. These new methods use functional data analysis and artificial intelligence (AI), including machine learning (ML). Compared to traditional metrics for evaluating CGM tracing results (CGM Data Analysis 1.0), these new methods, which we refer to as CGM Data Analysis 2.0, can provide a more detailed understanding of glucose fluctuations and trends and enable more personalized and effective diabetes management strategies once translated into practical clinical solutions.

q-bio.QM↗

arXiv2024

3DPX: Single Panoramic X-ray Analysis Guided by 3D Oral Structure Reconstruction

Panoramic X-ray (PX) is a prevalent modality in dentistry practice owing to its wide availability and low cost. However, as a 2D projection of a 3D structure, PX suffers from anatomical information loss and PX diagnosis is limited compared to that with 3D imaging modalities. 2D-to-3D reconstruction methods have been explored for the ability to synthesize the absent 3D anatomical information from 2D PX for use in PX image analysis. However, there are challenges in leveraging such 3D synthesized reconstructions. First, inferring 3D depth from 2D images remains a challenging task with limited accuracy. The second challenge is the joint analysis of 2D PX with its 3D synthesized counterpart, with the aim to maximize the 2D-3D synergy while minimizing the errors arising from the synthesized image. In this study, we propose a new method termed 3DPX - PX image analysis guided by 2D-to-3D reconstruction, to overcome these challenges. 3DPX consists of (i) a novel progressive reconstruction network to improve 2D-to-3D reconstruction and, (ii) a contrastive-guided bidirectional multimodality alignment module for 3D-guided 2D PX classification and segmentation tasks. The reconstruction network progressively reconstructs 3D images with knowledge imposed on the intermediate reconstructions at multiple pyramid levels and incorporates Multilayer Perceptrons to improve semantic understanding. The downstream networks leverage the reconstructed images as 3D anatomical guidance to the PX analysis through feature alignment, which increases the 2D-3D synergy with bidirectional feature projection and decease the impact of potential errors with contrastive guidance. Extensive experiments on two oral datasets involving 464 studies demonstrate that 3DPX outperforms the state-of-the-art methods in various tasks including 2D-to-3D reconstruction, PX classification and lesion segmentation.

eess.IV↗

arXiv2024

DSDFormer: An Innovative Transformer-Mamba Framework for Robust High-Precision Driver Distraction Identification

Driver distraction remains a leading cause of traffic accidents, posing a critical threat to road safety globally. As intelligent transportation systems evolve, accurate and real-time identification of driver distraction has become essential. However, existing methods struggle to capture both global contextual and fine-grained local features while contending with noisy labels in training datasets. To address these challenges, we propose DSDFormer, a novel framework that integrates the strengths of Transformer and Mamba architectures through a Dual State Domain Attention (DSDA) mechanism, enabling a balance between long-range dependencies and detailed feature extraction for robust driver behavior recognition. Additionally, we introduce Temporal Reasoning Confident Learning (TRCL), an unsupervised approach that refines noisy labels by leveraging spatiotemporal correlations in video sequences. Our model achieves state-of-the-art performance on the AUC-V1, AUC-V2, and 100-Driver datasets and demonstrates real-time processing efficiency on the NVIDIA Jetson AGX Orin platform. Extensive experimental results confirm that DSDFormer and TRCL significantly improve both the accuracy and robustness of driver distraction detection, offering a scalable solution to enhance road safety.

cs.CV↗

arXiv2024

Serp-Mamba: Advancing High-Resolution Retinal Vessel Segmentation with Selective State-Space Model

Ultra-Wide-Field Scanning Laser Ophthalmoscopy (UWF-SLO) images capture high-resolution views of the retina with typically 200 spanning degrees. Accurate segmentation of vessels in UWF-SLO images is essential for detecting and diagnosing fundus disease. Recent studies have revealed that the selective State Space Model (SSM) in Mamba performs well in modeling long-range dependencies, which is crucial for capturing the continuity of elongated vessel structures. Inspired by this, we propose the first Serpentine Mamba (Serp-Mamba) network to address this challenging task. Specifically, we recognize the intricate, varied, and delicate nature of the tubular structure of vessels. Furthermore, the high-resolution of UWF-SLO images exacerbates the imbalance between the vessel and background categories. Based on the above observations, we first devise a Serpentine Interwoven Adaptive (SIA) scan mechanism, which scans UWF-SLO images along curved vessel structures in a snake-like crawling manner. This approach, consistent with vascular texture transformations, ensures the effective and continuous capture of curved vascular structure features. Second, we propose an Ambiguity-Driven Dual Recalibration (ADDR) module to address the category imbalance problem intensified by high-resolution images. Our ADDR module delineates pixels by two learnable thresholds and refines ambiguous pixels through a dual-driven strategy, thereby accurately distinguishing vessels and background regions. Experiment results on three datasets demonstrate the superior performance of our Serp-Mamba on high-resolution vessel segmentation. We also conduct a series of ablation studies to verify the impact of our designs. Our code shall be released upon publication of this work.

cs.CV↗

arXiv2024

3DPX: Progressive 2D-to-3D Oral Image Reconstruction with Hybrid MLP-CNN Networks

Panoramic X-ray (PX) is a prevalent modality in dental practice for its wide availability and low cost. However, as a 2D projection image, PX does not contain 3D anatomical information, and therefore has limited use in dental applications that can benefit from 3D information, e.g., tooth angular misa-lignment detection and classification. Reconstructing 3D structures directly from 2D PX has recently been explored to address limitations with existing methods primarily reliant on Convolutional Neural Networks (CNNs) for direct 2D-to-3D mapping. These methods, however, are unable to correctly infer depth-axis spatial information. In addition, they are limited by the in-trinsic locality of convolution operations, as the convolution kernels only capture the information of immediate neighborhood pixels. In this study, we propose a progressive hybrid Multilayer Perceptron (MLP)-CNN pyra-mid network (3DPX) for 2D-to-3D oral PX reconstruction. We introduce a progressive reconstruction strategy, where 3D images are progressively re-constructed in the 3DPX with guidance imposed on the intermediate recon-struction result at each pyramid level. Further, motivated by the recent ad-vancement of MLPs that show promise in capturing fine-grained long-range dependency, our 3DPX integrates MLPs and CNNs to improve the semantic understanding during reconstruction. Extensive experiments on two large datasets involving 464 studies demonstrate that our 3DPX outperforms state-of-the-art 2D-to-3D oral reconstruction methods, including standalone MLP and transformers, in reconstruction quality, and also im-proves the performance of downstream angular misalignment classification tasks.

eess.IV↗

arXiv2024

Spatially Correlated RIS-Aided Secure Massive MIMO Under CSI and Hardware Imperfections

This paper investigates the integration of a reconfigurable intelligent surface (RIS) into a secure multiuser massive multiple-input multiple-output (MIMO) system in the presence of transceiver hardware impairments (HWI), imperfect channel state information (CSI), and spatially correlated channels. We first introduce a linear minimum-mean-square error estimation algorithm for the aggregate channel by considering the impact of transceiver HWI and RIS phase-shift errors. Then, we derive a lower bound for the achievable ergodic secrecy rate in the presence of a multi-antenna eavesdropper when artificial noise (AN) is employed at the base station (BS). In addition, the obtained expressions of the ergodic secrecy rate are further simplified in some noteworthy special cases to obtain valuable insights. To counteract the effects of HWI, we present a power allocation optimization strategy between the confidential signals and AN, which admits a fixed-point equation solution. Our analysis reveals that a non-zero ergodic secrecy rate is preserved if the total transmit power decreases no faster than $1/N$, where $N$ is the number of RIS elements. Moreover, the ergodic secrecy rate grows logarithmically with the number of BS antennas $M$ and approaches a certain limit in the asymptotic regime $N\rightarrow\infty$. Simulation results are provided to verify the derived analytical results. They reveal the impact of key design parameters on the secrecy rate. It is shown that, with the proposed power allocation strategy, the secrecy rate loss due to HWI can be counteracted by increasing the number of low-cost RIS elements.

cs.IT↗

arXiv2023

Scene-aware Human Pose Generation using Transformer

Affordance learning considers the interaction opportunities for an actor in the scene and thus has wide application in scene understanding and intelligent robotics. In this paper, we focus on contextual affordance learning, i.e., using affordance as context to generate a reasonable human pose in a scene. Existing scene-aware human pose generation methods could be divided into two categories depending on whether using pose templates. Our proposed method belongs to the template-based category, which benefits from the representative pose templates. Moreover, inspired by recent transformer-based methods, we associate each query embedding with a pose template, and use the interaction between query embeddings and scene feature map to effectively predict the scale and offsets for each pose template. In addition, we employ knowledge distillation to facilitate the offset learning given the predicted scale. Comprehensive experiments on Sitcom dataset demonstrate the effectiveness of our method.

cs.CV↗

arXiv2023

Deep Dynamic Epidemiological Modelling for COVID-19 Forecasting in Multi-level Districts

Objective: COVID-19 has spread worldwide and made a huge influence across the world. Modeling the infectious spread situation of COVID-19 is essential to understand the current condition and to formulate intervention measurements. Epidemiological equations based on the SEIR model simulate disease development. The traditional parameter estimation method to solve SEIR equations could not precisely fit real-world data due to different situations, such as social distancing policies and intervention strategies. Additionally, learning-based models achieve outstanding fitting performance, but cannot visualize mechanisms. Methods: Thus, we propose a deep dynamic epidemiological (DDE) method that combines epidemiological equations and deep-learning advantages to obtain high accuracy and visualization. The DDE contains deep networks to fit the effect function to simulate the ever-changing situations based on the neural ODE method in solving variants' equations, ensuring the fitting performance of multi-level areas. Results: We introduce four SEIR variants to fit different situations in different countries and regions. We compare our DDE method with traditional parameter estimation methods (Nelder-Mead, BFGS, Powell, Truncated Newton Conjugate-Gradient, Neural ODE) in fitting the real-world data in the cases of countries (the USA, Columbia, South Africa) and regions (Wuhan in China, Piedmont in Italy). Our DDE method achieves the best Mean Square Error and Pearson coefficient in all five areas. Further, compared with the state-of-art learning-based approaches, the DDE outperforms all techniques, including LSTM, RNN, GRU, Random Forest, Extremely Random Trees, and Decision Tree. Conclusion: DDE presents outstanding predictive ability and visualized display of the changes in infection rates in different regions and countries.

cs.LG↗

arXiv2023

TransMRSR: Transformer-based Self-Distilled Generative Prior for Brain MRI Super-Resolution

Magnetic resonance images (MRI) acquired with low through-plane resolution compromise time and cost. The poor resolution in one orientation is insufficient to meet the requirement of high resolution for early diagnosis of brain disease and morphometric study. The common Single image super-resolution (SISR) solutions face two main challenges: (1) local detailed and global anatomical structural information combination; and (2) large-scale restoration when applied for reconstructing thick-slice MRI into high-resolution (HR) iso-tropic data. To address these problems, we propose a novel two-stage network for brain MRI SR named TransMRSR based on the convolutional blocks to extract local information and transformer blocks to capture long-range dependencies. TransMRSR consists of three modules: the shallow local feature extraction, the deep non-local feature capture, and the HR image reconstruction. We perform a generative task to encapsulate diverse priors into a generative network (GAN), which is the decoder sub-module of the deep non-local feature capture part, in the first stage. The pre-trained GAN is used for the second stage of SR task. We further eliminate the potential latent space shift caused by the two-stage training strategy through the self-distilled truncation trick. The extensive experiments show that our method achieves superior performance to other SSIR methods on both public and private datasets. Code is released at https://github.com/goddesshs/TransMRSR.git .

eess.IV↗

arXiv2023

DRAC: Diabetic Retinopathy Analysis Challenge with Ultra-Wide Optical Coherence Tomography Angiography Images

Computer-assisted automatic analysis of diabetic retinopathy (DR) is of great importance in reducing the risks of vision loss and even blindness. Ultra-wide optical coherence tomography angiography (UW-OCTA) is a non-invasive and safe imaging modality in DR diagnosis system, but there is a lack of publicly available benchmarks for model development and evaluation. To promote further research and scientific benchmarking for diabetic retinopathy analysis using UW-OCTA images, we organized a challenge named "DRAC - Diabetic Retinopathy Analysis Challenge" in conjunction with the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2022). The challenge consists of three tasks: segmentation of DR lesions, image quality assessment and DR grading. The scientific community responded positively to the challenge, with 11, 12, and 13 teams from geographically diverse institutes submitting different solutions in these three tasks, respectively. This paper presents a summary and analysis of the top-performing solutions and results for each task of the challenge. The obtained results from top algorithms indicate the importance of data augmentation, model architecture and ensemble of networks in improving the performance of deep learning models. These findings have the potential to enable new developments in diabetic retinopathy analysis. The challenge remains open for post-challenge registrations and submissions for benchmarking future methodology developments.

eess.IV↗

arXiv2023

Secure Communication for Spatially Correlated Massive MIMO with Low-Resolution DACs

In this paper, the performance of a secure massive multiple-input multiple-output (MIMO) system adopting low-resolution digital-to-analog converters (DACs) is analyzed over spatially correlated wireless channels. A tight lower bound for the achievable secrecy rate is derived with artificial noise (AN) transmitted in the null space of the user channels. Using the analytical results, the impact of spatial correlation on the secrecy rate is explicitly evaluated in the presence of low-resolution DACs. The analytical observations reveal that using low-resolution DACs can be beneficial to the secrecy performance compared with ideal DACs, when the channels are strongly correlated and optimal power allocation is not employed.

cs.IT↗

arXiv2022

Closed-form Approximation for Performance Bound of Finite Blocklength Massive MIMO Transmission

Ultra-reliable low latency communications (uRLLC) is adopted in the fifth generation (5G) mobile networks to better support mission-critical applications that demand high level of reliability and low latency. With the aid of well-established multiple-input multiple-output (MIMO) information theory, uRLLC in the future 6G is expected to provide enhanced capability towards extreme connectivity. Since the latency constraint can be represented equivalently by blocklength, channel coding theory at finite block-length plays an important role in the theoretic analysis of uRLLC. On the basis of Polyanskiy's and Yang's asymptotic results, we first derive the exact close-form expressions for the expectation and variance of channel dispersion. Then, the bound of average maximal achievable rate is given for massive MIMO systems in ideal independent and identically distributed fading channels. This is the study to reveal the underlying connections among the fundamental parameters in MIMO transmissions in a concise and complete close-form formula. Most importantly, the inversely proportional law observed therein implies that the latency can be further reduced at expense of spatial degrees of freedom.

cs.IT↗

arXiv2022

Solving Routing Problems via Important Cuts

We introduce a novel approach of using important cuts which allowed us to design significantly faster fixed-parameter tractable (FPT) algorithms for the following routing problems: the Mixed Chinese Postman Problem parameterized by the number of directed edges (Gutin et al., JCSS 2017), the Minimum Shared Edges problem (MSE) parameterized by the number p of paths between two specified vertices (Fluschnik et al., JCSS 2019), and the Weighted Min Cut Prevention problem (Gruttemeier et al., WG 2021). The Minimum Vulnerability problem (MV) is a generalization of MSE (Assadi et al., Algorithmica 2014). The only known FPT algorithm for MV parameterized by p (the same parameter as for MSE) was for chordal graphs (Aoki et al., JCO 2018). We design an FPT algorithm for MV on all undirected graphs.

cs.DS↗

arXiv2022

Spatiotemporal 2-D Channel Coding for Very Low Latency Reliable MIMO Transmission

To fully support vertical industries, 5G and its corresponding channel coding are expected to meet requirements of different applications. However, for applications of 5G and beyond 5G (B5G) such as URLLC, the transmission latency is required to be much shorter than that in eMBB. Therefore, the resulting channel code length reduces drastically. In this case, the traditional 1-D channel coding suffers a lot from the performance degradation and fails to deliver strong reliability with very low latency. To remove this bottleneck, new channel coding scheme beyond the existing 1-D one is in urgent need. By making full use of the spacial freedom of massive MIMO systems, this paper devotes itself in proposing a spatiotemporal 2-D channel coding for very low latency reliable transmission. For a very short time-domain code length $N^{\text{time}}=16$, $64 \times 128$ MIMO system employing the proposed spatiotemporal 2-D coding scheme successfully shows more than $3$\,dB performance gain at $\text{FER}=10^{-3}$, compared to the 1-D time-domain channel coding. It is noted that the proposed coding scheme is suitable for different channel codes and enjoys high flexibility to adapt to difference scenarios. By appropriately selecting the code rate, code length, and the number of codewords in the time and space domains, the proposed coding scheme can achieve a good trade-off between the transmission latency and reliability.

cs.IT↗