Search Results for author:
Found 23 papers, 6 papers with code
近十年来澳门的词汇增长(Macau’s Vocabulary Growth in the Recent Ten Year)
“词汇增长模型可以通过拟合词种(types)与词例(tokens)之间的数量关系, 反映某一领域词汇的历时演化。澳门作为多语言多文化融合之地, 词汇的使用情况能够反映社会的关注焦点, 但目前尚无对澳门历时词汇演变的研究。本文首次构建澳门汉语历时语料库, 利用三大词汇增长模型拟合语料库的词汇变化, 并选取效果最好的 Heaps 模型进一步分析词汇演变与报刊内容的关系, 结果反映出澳门词汇的变化趋势与热点新闻、澳门施政方针和民生密切相关。本研究还采用去除文本时序信息后的乱序文本, 验证了方法的有效性。本文是首项基于大规模历时语料库考察澳门词汇演变的研究, 对深入了解澳门语言生活的发展具有重要意义。”
MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering
Understanding temporal relations and answering time-sensitive questions is crucial yet a challenging task for question-answering systems powered by large language models (LLMs).
PROFIT: A Specialized Optimizer for Deep Fine Tuning
Fine-tuning pre-trained models has become invaluable in computer vision and robotics.
LightWeather: Harnessing Absolute Positional Encoding to Efficient and Scalable Global Weather Forecasting
Recently, Transformers have gained traction in weather forecasting for their capability to capture long-term spatial-temporal correlations.
HDR Imaging for Dynamic Scenes with Events
High dynamic range imaging (HDRI) for real-world dynamic scenes is challenging because moving objects may lead to hybrid degradation of low dynamic range and motion blur.
SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors
We present SHIFT3D, a differentiable pipeline for generating 3D shapes that are structurally plausible yet challenging to 3D object detectors.
Structural Inference of Networked Dynamical Systems with Universal Differential Equations
Networked dynamical systems are common throughout science in engineering; e. g., biological networks, reaction networks, power systems, and the like.
HyperPrompt: Prompt-based Task-Conditioning of Transformers
Prompt-Tuning is a new paradigm for finetuning pre-trained language models in a parameter-efficient way.
GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting
We propose GradTail, an algorithm that uses gradients to improve model performance on the fly in the face of long-tailed training data distributions.
Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
The vast majority of deep models use multiple gradient signals, typically corresponding to a sum of multiple loss terms, to update a shared set of trainable weights.
Sparse representation for damage identification of structural systems
Specifically, an $\ell_2$ Bayesian learning method is firstly developed for updating the intact model and uncertainty quantification so as to set forward a baseline for damage detection.
Taskology: Utilizing Task Relations at Scale
Many computer vision tasks address the problem of scene understanding and are naturally interrelated e. g. object classification, detection, scene segmentation, depth estimation, etc.
Physics-informed learning of governing equations from scarce data
Harnessing data to discover the underlying governing laws or equations that describe the behavior of complex physical systems can significantly advance our modeling, simulation and understanding of such systems in various science and engineering disciplines.
The Weak Lensing Peak Statistics in the Mocks by the inverse-Gaussianization Method
We apply the inverse-Gaussianization method proposed in \citealt{arXiv:1607. 05007} to fast produce weak lensing convergence maps and investigate the peak statistics, including the peak height counts and peak steepness counts, in these mocks.
Cosmology and Nongalactic Astrophysics
DeepPerimeter: Indoor Boundary Estimation from Posed Monocular Sequences
We present DeepPerimeter, a deep learning based pipeline for inferring a full indoor perimeter (i. e. exterior boundary map) from a sequence of posed RGB images.
Ultrafast X-Ray Induced Changes of the Electronic and Magnetic Response of Solids Due to Valence Electron Redistribution
We report a novel mechanism, consisting of redistribution of valence electrons near the Fermi level, during interactions of intense femtosecond X-ray pulses with a Co/Pd multilayer.
Materials Science
Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach
Numerical results are illustrated to demonstrate that efficient policies can be learned at each user, and performance of the proposed DDPG based decentralized strategy outperforms the conventional deep Q-network (DQN) based discrete power control strategy and some other greedy strategies with reduced computation cost.
Gradient Adversarial Training of Neural Networks
We demonstrate gradient adversarial training for three different scenarios: (1) as a defense to adversarial examples we classify gradient tensors and tune them to be agnostic to the class of their corresponding example, (2) for knowledge distillation, we do binary classification of gradient tensors derived from the student or teacher network and tune the student gradient tensor to mimic the teacher's gradient tensor; and (3) for multi-task learning we classify the gradient tensors derived from different task loss functions and tune them to be statistically indistinguishable.
Estimating Depth from RGB and Sparse Sensing
We present a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels.
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
Deep multitask networks, in which one neural network produces multiple predictive outputs, can offer better speed and performance than their single-task counterparts but are challenging to train properly.
The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AI
We present a vision-only model for gaming AI which uses a late integration deep convolutional network architecture trained in a purely supervised imitation learning context.
3-D Convolutional Neural Networks for Glioblastoma Segmentation
In this paper, we propose a framework of 3-D fully CNN models for Glioblastoma segmentation from multi-modality MRI data.
