Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Jun SatoSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works86 from public data
- GPT4AIGChip: Towards Next-Generation AI Accelerator Design Automation via Large Language Models142
This work develops a framework called GPT4AIGChip, which features an automated demo-augmented prompt-generation pipeline utilizing in-context learning to guide LLMs towards creating high-quality AI accelerator design, and is the first to demonstrate an effective pipeline for LLM-powered automated AI accelerator generation.
- Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstruction120
Instant-3D is proposed, an algorithm-hardware co-design acceleration framework that achieves instant on-device NeRF training and has enabled instant 3D reconstruction for AR/VR, requiring a reconstruction time of only 1.6 seconds per scene and meeting the AR/ VR power consumption constraint.
- BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Sampling109
This work first analyzes why distributed GCN training is ineffective and identifies the underlying cause to be the excessive number of boundary nodes of each partitioned subgraph, which easily explodes the memory and communication costs for GCNTraining.
- Swift Parameter-free Attention Network for Efficient Super-Resolution106
The Swift Parameter-free Attention Network (SPAN), a highly efficient SISR model that balances parameter count, inference speed, and image quality, is proposed, showing that it outperforms existing efficient super-resolution models in terms of both image quality and inference speed.
- PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication102
This work not only provides a theoretical convergence analysis but also finds the convergence rate of PipeGCN to be close to that of the vanilla distributed GCN training without any staleness, and develops a smoothing method to further improve Pipe GCN's convergence.
- Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AI59
A systematic review of recent progress in NSAI is provided and the performance characteristics and computational operators of NSAI models are analyzed to discuss the challenges and potential future directions of NSAI.
- Web Service Selection with Incomplete or Inconsistent User Preferences47
A system to facilitate Web service selection in face of incomplete or inconsistent user preferences is presented, which utilizes the information of historical users to amend the active user's preference, so as to improve the results of service selection.
- A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware43
This survey provides a taxonomy of GNN acceleration, review the existing approaches, and suggest future research directions, and sets the stage for further development in this area.
- 39
- 35
- Gaussian Blending Unit: An Edge GPU Plug-in for Real-Time Gaussian-Based Rendering in AR/VR34
A Gaussian Blending Unit (GBU), an edge GPU plug-in module for real-time rendering in AR/VR applications that enhances rendering speed with a dedicated rendering engine that balances the workload across rows by aggregating computations from multiple Gaussians.
- Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecture32
This paper systematically categorizes neuro-symbolic AI algorithms, and experimentally evaluates them in terms of runtime, memory, computational operators, sparsity, and system characteristics on CPUs, GPUs, and edge SoCs, revealing that neuro-symbolic models suffer from inefficiencies on off-the-shelf hardware.
- Machine-Learning and Radiomics-Based Preoperative Prediction of Ki-67 Expression in Glioma Using MRI Data31
This study introduced a novel approach for classifying Ki67 expression levels using MRI, which has been proven to be highly effective and demonstrated its potential in signalling a promising avenue for future research.
- Deep-learning and conventional radiomics to predict IDH genotyping status based on magnetic resonance imaging data in adult diffuse glioma29
An optimal machine-learning model for prediction of IDH genotyping is identified by combining deep-learning (DL) signatures and conventional radiomics (CR) features as model predictors by combining the LASSO–selected CR features and integrated DL signatures as model Predictors.
- DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks29
This work opens up a new compression paradigm for developing real-hardware efficient DNNs, leading to boosted hardware efficiency while maintaining model accuracy, and proposes a framework dubbed DepthShrinker, which develops hardware-friendly compact networks via shrinking the basic building blocks of existing efficient Dnns that feature irregular computation patterns into dense ones with much improved hardware utilization and thus real- hardware efficiency.
- Preference recommendation for personalized search28
This article proposes a preference recommendation scheme for complementing a user's CP-nets, so as to improve the accuracy of personalized search and conducts extensive simulation and user study to demonstrate the effectiveness.
- 3D-Carbon: An Analytical Carbon Modeling Tool for 3D and 2.5D Integrated Circuits27
3D-Carbon is proposed, an analytical carbon modeling tool designed to quantify the carbon emissions of 3D/2.5D ICs throughout their life cycle, and lays the initial foundation for future innovations in developing environmentally sustainable 3D/2.5D ICs.
- Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey21
The NTIRE 2024 RAW Image Super-Resolution Challenge is reviewed, highlighting the proposed solutions and results, and providing a gauge for the current state-of-the-art in RAW Image Super-Resolution.
- 18
- Unveiling the Evolution of Virtual Reality in Medicine: A Bibliometric Analysis of Research Hotspots and Trends over the Past 12 Years17
The number of publications on VR applications in the medical field has been steadily increasing year by year, and the USA is the leading country in this area, while the University of London stands out as the most published, and most influential institution.
- 17
- Deep learning based prediction of depression and anxiety in patients with type 2 diabetes mellitus using regional electronic health records15
The REDAPM effectively leverages the heterogeneous characteristics of regional EHR data, demonstrating strong predictive performance for depression onset in diabetic patients and shows potential for discovering significant clinical features, indicating considerable promise for clinical utility.
- 15
- 14
- EyeCoD14
This work proposes, develops, and validate a lensless FlatCambased eye tracking algorithm and accelerator co-design framework dubbed EyeCoD to enable eye tracking systems with a much reduced form-factor and boosted system efficiency without sacrificing the tracking accuracy, paving the way for next-generation eye tracking solutions.
- 14
- Applying contrastive pre-training for depression and anxiety risk prediction in type 2 diabetes patients based on heterogeneous electronic health records: a primary healthcare case study13
The DAP model effectively predicted post-discharge depression and anxiety in T2DM patients from PHS, reducing data fragmentation and limitations and highlighting the model’s potential for early detection and intervention in depression and anxiety, improving outcomes for diabetes patients.
- 13
- HyCTAS: Multi-objective hybrid convolution-transformer architecture search for real-time image segmentation12
A series of models via the Hybrid Convolutional-Transformer Architecture Search (HyCTAS) method that searches for the best hybrid combination of lightweight convolution layers and memory-efficient self-attention layers between branches from different resolutions and fuses them at high resolution for both efficiency and effectiveness are presented.
- Characterizing Brain Tumor Regions Using Texture Analysis in Magnetic Resonance Imaging12
Texture analysis with an SVM classifier can help differentiate between brain tumor and healthy areas with high speed and accuracy, which would facilitate its clinical application.
- Changes in brain functional networks in remitted major depressive disorder: a six-month follow-up study11
Resting-state functional connectivity of the CEN during early rMDD is associated with psychosocial function, and resting-state functional connectivity of the IPL and DLPFC in the CEN correlated with psychosocial functioning.
- 10
- 10
- MIPI 2024 Challenge on Demosaic for Hybridevs Camera: Methods and Results9
A total of 110 participants from both industrial and academic backgrounds contributed many valuable solutions to address the difficulty of the restoration of HybridEVS’s raw data, thus raising the reconstructed performance to a new height.
- Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling*8
This work explores the scaling limits of GNNs for atomistic materials modeling by developing a foundational model with billions of parameters, trained on extensive datasets in terabytescale, and develops a GNN codebase enhanced with advanced LLM-based training techniques.
- Multiple View Geometry under Projective Projection in Space-Time8
It is shown the multifocal tensors defined under space-time projective projection can be derived from non-rigid object motions viewed from multiple cameras with arbitrary translational motions, and they are practical for generating images of non- Rigid object motion viewed from cameras with arbitrarily translational motion.
- Identification and Impact Analysis of Family History of Psychiatric Disorder in Mood Disorder Patients With Pretrained Language Model7
This paper proposes a pretrained language model: Bidirectional Encoder Representations from Transformers (BERT)–Convolutional Neural Network (CNN), and projects the electronic hospitalization records into a low-dimensional dense matrix via the pretrained Chinese BERT model, which is used to extract family history based on high-level features.
- Sensor-Based Estimation of Dim Light Melatonin Onset Using Features of Two Time Scales7
Three moving average models that input sleep timing data as the first step and use recurrent neural network models as the second step are evaluated, showing statistically significantly lower root-mean-square errors than models that use either daily sampled data or frequently sampled data.
- Gaussian Cardinality Restricted Boltzmann Machines7
A generalized model with adaptive sparsity constraint, named Gaussian Cardinality Restricted Boltzmann Machines (GC-RBM), in which the thresholds of hidden unit activations are decided by the input data and a given Gaussian distribution on the pre-training phase.
- WASABI: A Metric for Evaluating Morphometric Plausibility of Synthetic Brain MRIs6
A new metric, called WASABI (Wasserstein-Based Anatomical Brain Index), is proposed, to assess the morphometric plausibility of synthetic brain MRIs, and demonstrates higher sensitivity in quantifying morphometric discrepancies compared to traditional image-level metrics, even when synthetic images achieve near-perfect visual quality.
- PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection5
PRISM-Bench is introduced, a benchmark of puzzle-based visual challenges designed to evaluate not only whether models can solve problems, but how their reasoning unfolds, and underscores the need for diagnostic evaluation protocols in the development of trustworthy MLLMs.
- 5
- 5
- 5
- 5
- e-G2C: A 0.14-to-8.31 µJ/Inference NN-based Processor with Continuous On-chip Adaptation for Anomaly Detection and ECG Conversion from EGM4
The first silicon-validated dedicated EGM-to-ECG (G2C) processor featuring continuous lightweight anomaly detection, event-driven coarse/precise conversion, and on-chip adaptation is presented, promising real-time detection/conversion and possibly life-critical interventions.
- 4
- Automatic Gating of Attributes in Deep Structure4
A deep structure named Attribute Gated Deep Belief Network (AG-DBN) that includes a tunable attribute-layer gating mechanism and automatically learns the best way of connecting attributes to appropriate hidden layers is proposed that outperforms the CNN model, VGG19, by significantly reducing the classification error.
- A cellular automaton model of Schistosoma japonicum infection4
An improved stochastic model based on cellular automaton (I-SjCA) has been introduced and it is anticipated that this model can serve as a tool for understanding schistosomiasis transmission dynamics and thus be conductive to build an effective control program.
- 3
- Anatomically Guided Latent Diffusion for Brain MRI Progression Modeling2
Experiments demonstrate that AG-LDM matches or surpasses more complex diffusion models, achieving highly competitive image quality and 15-20% reduction in volumetric errors in generated images, and highlight AG-LDM as an efficient, anatomically grounded framework for reliable brain MRI progression modeling.
- A Multi-scenario Attention-based Generative Model for Personalized Blood Pressure Time Series Forecasting2
A personalized BP forecasting model mainly using electrocardiogram (ECG) and photoplethysmogram (PPG) signals is proposed that achieves accurate and robust BP forecasts across scenarios within the Association for the Advancement of Medical Instrumentation (AAMI) standard criteria.
- 2
- 2
- Three-Dimensional Computed Tomography Scan Analysis of Secondary Labial Deformities in Patients With Unilateral Cleft Lip/Cleft Palate After Revisional Surgery2
This study demonstrates the utility of a novel method to measure and assess results in the surgical revision of UCL/UCLP patients with secondary lip deformities, and can aid the surgeon in selection of treatment techniques.
- 2
- Qualitative preference-based service selection for multiple agents2
This paper uses a qualitative graphical representation tool called CP-nets to describe preference relations in a relatively compact, intuitive and structured manner and proposes a preference reasoning algorithm to construct a derivation tree from a CP-net for each agent and then generate all service patterns for this agent.
- [Multi-dimensional evaluation system for schistosomiasis japonica transmission dynamic model].2
The multi-dimensional evaluation system is helpful for accurately assessing the simulation results of the discrete stochastic models such as SjCA, and is promising to be universalized to evaluate other similar epidemic dynamics models.
- Rectification of 3D data obtained from moving range sensor by using extended projective multiple view geometry2
This paper proposes a method for recovering correct 3D range data from a moving range sensor by using the multiple view geometry under projective projections in space-time, and shows that the extendedmultiple view geometry can be used for rectifying 3D data obtained by theMoving range sensor.
- Multiple View Geometry for Non-rigid Motions Viewed from Translational Cameras2
This paper shows the multifocal tensors defined under space-time projective projections can be derived from non-rigid object motions viewed from multiple cameras with arbitrary translational motions, and they are practical for generating images of non- Rigid object motion viewed from cameras with arbitrarily translational motion.
- 1
- 1
- 1
- Extraction of Mountain Feature Line Based on 3D Laser Scanning1
A Cut-and-Sew algorithm extracting feature line of the mountain based on laser 3D scanning is applied and the establishment of the formation of the triangular feature line is reconstructed on the mountain.
- 1
- 1
- 1
- Language Models as 3D Layout Designers: a Survey–
A focused definition and task framework for layout agents is provided and a hierarchical categorization based on LLM layout agents' output representation is proposed, to guide future research toward more capable, generalizable LLM layout agents.
- –
- –
- –
- STB-Net: a Siamese architecture-based reconstruction-segmentation network for ocular surface image segmentation–
The proposed STB-Net model provides a robust and effective solution for the automated segmentation of ocular surface structures and the precise quantification of eyelid morphological parameters and holds significant promise for enhancing the objectivity and efficiency of clinical diagnoses of eyelid disorders.
- –
- –
- –
- –
- –
- –
- [Development of a software standardizing optical density with operation settings related to several limitations].–
The results indicated that the software successfully overcame several problems including reliability of standard curve, applicable scope of samples and determination of dilution for samples outside the scope, so that I-STOD was performed more conveniently and the results of standardization were more consistent.
- Relevent factors,prevention and treatment of neonatal ventilator-associated pneumonia–
The incidence of VAP has a close conclusion with the gestational ages, the birth weights, the duration of mechanical ventilation and the times of intubation, and regulate the use of breathing machine, strengthen aseptic operation, and select effective antibiotic can control the occurrence and development of V AP.
- –
- Computing Spatio-Temporal Multiple View Geometry from Mutual Projections of Multiple Cameras–
Mutual projections of cameras in four-dimensional space is investigated and it is shown that it enables us to reduce the number of corresponding points required for computing the spatio-temporal multiple view geometry.
- –
- –
- Realization of Multicomputer Communication between PC and 51 Series Single Chip Microcomputer–
The multicomputer communication between PC and sigle chip microcomputer is realized, and PC's communication control register is set according to the characteristic of PC and 51 series microcomputer communication interface.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.