Search Results for author:
Found 29 papers, 9 papers with code
Bubble Dynamics Transformer: Microrheology at Ultra-High Strain Rates
Laser-induced inertial cavitation (LIC)-where microscale vapor bubbles nucleate due to a focused high-energy pulsed laser and then violently collapse under surrounding high local pressures-offers a unique opportunity to investigate soft biological material mechanics at extremely high strain rates (>1000 1/s).
Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
First, a single-controller architecture combined with an abstraction of the parallel worker simplifies the development of the training pipeline.
FM-LoRA: Factorized Low-Rank Meta-Prompting for Continual Learning
Extensive experiments on various CL benchmarks, including ImageNet-R, CIFAR100, and CUB200 for class-incremental learning (CIL), and DomainNet for domain-incremental learning (DIL), with Transformers backbone demonstrate that FM-LoRA effectively mitigates catastrophic forgetting while delivering robust performance across a diverse range of tasks and domains.
Multimodal Variational Autoencoder: a Barycentric View
Previous attempts at multimodal VAEs approach this mainly through the lens of experts, aggregating unimodal inference distributions with a product of experts (PoE), a mixture of experts (MoE), or a combination of both.
Balanced 3DGS: Gaussian-wise Parallelism Rendering with Fine-Grained Tiling
3D Gaussian Splatting (3DGS) is increasingly attracting attention in both academia and industry owing to its superior visual quality and rendering speed.
Dual-Branch Subpixel-Guided Network for Hyperspectral Image Classification
Deep learning (DL) has been widely applied into hyperspectral image (HSI) classification owing to its promising feature learning and representation capabilities.
DMC-Net: Lightweight Dynamic Multi-Scale and Multi-Resolution Convolution Network for Pancreas Segmentation in CT Images
In contrast, the DMSC module extracts features at different scales by employing convolutions with different kernel sizes and utilizing dynamic mechanisms to extract global contextual information.
D2-MLP: Dynamic Decomposed MLP Mixer for Medical Image Segmentation
In contrast, MLP Mixers are proposed as a backbone to learn global information across channels with low complexity.
KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation
The recently developed retrieval-augmented generation (RAG) technology has enabled the efficient construction of domain-specific applications.
Problematic Tokens: Tokenizer Bias in Large Language Models
Recent advancements in large language models(LLMs), such as GPT-4 and GPT-4o, have shown exceptional performance, especially in languages with abundant resources like English, thanks to extensive datasets that ensure robust training.
Beyond Pixel-Wise Supervision for Medical Image Segmentation: From Traditional Models to Foundation Models
Medical image segmentation plays an important role in many image-guided clinical approaches.
Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection
Video moment retrieval and highlight detection are two highly valuable tasks in video understanding, but until recently they have been jointly studied.
AgileFormer: Spatially Agile Transformer UNet for Medical Image Segmentation
However, we argue that the current design of the vision transformer-based UNet (ViT-UNet) segmentation models may not effectively handle the heterogeneous appearance (e. g., varying shapes and sizes) of objects of interest in medical image segmentation tasks.
Ranked #2 on
Medical Image Segmentation
on ACDC
D-Net: Dynamic Large Kernel with Dynamic Feature Fusion for Volumetric Medical Image Segmentation
D-Net is able to effectively utilize a multi-scale large receptive field and adaptively harness global contextual information.
Dynamic U-Net: Adaptively Calibrate Features for Abdominal Multi-organ Segmentation
We evaluated Dynamic U-Net in two abdominal multi-organ segmentation benchmarks.
SemiSAM: Enhancing Semi-Supervised Medical Image Segmentation via SAM-Assisted Consistency Regularization
Semi-supervised learning has attracted much attention due to its less dependence on acquiring abundant annotations from experts compared to fully supervised methods, which is especially important for medical image segmentation which typically requires intensive pixel/voxel-wise labeling by domain experts.
Optimally Coordinated Energy Management Framework for Profit Maximization Considering Dispatchable and Non-Dispatchable Energy Resources
Contemporary distribution network can be seen with diverse dispatchable and non-dispatchable energy resources.
An Intelligent End-to-End Neural Architecture Search Framework for Electricity Forecasting Model Development
Although several recent studies have considered the application of the neural architecture search (NAS) technique for obtaining a network with an optimized structure in the electricity forecasting sector, their training process is computationally expensive and their search strategies are not flexible, indicating that the NAS application in this area is still at an infancy stage.
A Highly Configurable Hardware/Software Stack for DNN Inference Acceleration
We have enhanced the VTA design space and enabled end-to-end support for additional workloads.
Robust wavefront dislocations of Friedel oscillations in gapped graphene
Friedel oscillation is a well-known wave phenomenon, which represents the oscillatory response of electron waves to imperfection.
Mesoscale and Nanoscale Physics
Site-resolved imaging of ultracold fermions in a triangular-lattice quantum gas microscope
Quantum gas microscopes have expanded the capabilities of quantum simulation of Hubbard models by enabling the study of spatial spin and density correlations in square lattices.
Quantum Gases Atomic Physics
Model Synthesis for Communication Traces of System-on-Chip Designs
In this paper, we consider the problem of inferring models from communication traces of system-on-chip~(SoC) designs.
Reconfigurable Intelligent Surface: Design the Channel -- a New Opportunity for Future Wireless Networks
In this paper, we survey state-of-the-art research outcomes in the burgeoning field of reconfigurable intelligent surface (RIS) in view of its potential for significant performance enhancement for next generation wireless communication networks by means of adapting the propagation environment.
Deep Reinforcement Learning with a Stage Incentive Mechanism of Dense Reward for Robotic Trajectory Planning
Extensive experiments show that the soft stage incentive reward function is able to improve the convergence rate by up to 46. 9% with the state-of-the-art DRL methods.
Two-stage short-term wind power forecasting algorithm using different feature-learning models
Considering the overfitting issue, we propose a new moving window-based algorithm using a validation set in the first stage to update the training data in both stages with two different moving window processes. Experiments were conducted at three wind farms, and the results demonstrate that the model with single input multiple output structure obtains better forecasting accuracy compared to existing models.
Mining Message Flows using Recurrent Neural Networks for System-on-Chip Designs
Initial results show that the proposed approach is capable of extracting various patterns on system-level specifications from the highly concurrent SoC execution traces.
Single upper limb pose estimation method based on improved stacked hourglass network
Using the stacked hourglass network model, a single-person upper limb skeleton key point detection model was designed. Deconvolution was employed to replace the up-sampling operation of the hourglass module in the original model, solving the problem of rough feature maps.
Sim-to-Real Optimization of Complex Real World Mobile Network with Imperfect Information via Deep Reinforcement Learning from Self-play
Mobile network that millions of people use every day is one of the most complex systems in the world.
SYSTRAN's Pure Neural Machine Translation Systems
Since the first online demonstration of Neural Machine Translation (NMT) by LISA, NMT development has recently moved from laboratory to production systems as demonstrated by several entities announcing roll-out of NMT engines to replace their existing technologies.
