Search Results for author:
Found 25 papers, 11 papers with code
X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions
In addition, we find that models tuned on cross-lingual instruction following samples can follow the instruction in the output language without further tuning.
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
We introduce VASA, a framework for generating lifelike talking faces with appealing visual affective skills (VAS) given a single static image and a speech audio clip.
NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation
Recent fMRI-to-image approaches mainly focused on associating fMRI signals with specific conditions of pre-trained diffusion models.
MulCogBench: A Multi-modal Cognitive Benchmark Dataset for Evaluating Chinese and English Computational Language Models
Results show that language models share significant similarities with human cognitive data and the similarity patterns are modulated by the data modality and stimuli complexity.
CrackCLF: Automatic Pavement Crack Detection based on Closed-Loop Feedback
Meanwhile, these models can not automatically correct errors in the prediction, nor can it adapt to the changes of the environment to automatically extract and detect thin cracks.
Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment
It aligns the internal sentence representations across different languages via multilingual contrastive learning and aligns outputs by following cross-lingual instructions in the target language.
Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning
We further propose a simple multi-task training method to increase functional specialization and mitigate negative information transfer in multi-task learning.
BigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages
Second, we continue training the model with a large-scale parallel dataset that covers 102 natural languages.
Ranked #4 on
Machine Translation
on FLoRes-200
RemoteTouch: Enhancing Immersive 3D Video Communication with Hand Touch
A key challenge in emulating the remote hand touch is the realistic rendering of the participant's hand and arm as the hand touches the screen.
FreeEnricher: Enriching Face Landmarks without Additional Cost
To evaluate our method, we manually label the dense landmarks on 300W testset.
Ranked #1 on
Face Alignment
on 300W
Reconfigurable Wearable Antenna for 5G Applications using Nematic Liquid Crystals
The antenna is one of the key building blocks of many wearable electronic device, and its functions include wireless communications, energy harvesting and radiative wireless power transfer (WPT).
Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
In this paper, we introduce a novel contrastive action representation learning (CARL) framework to learn frame-wise action representations, especially for long videos, in a self-supervised manner.
RankedDrop: Enhancing Deep Graph Convolutional Networks Training
Introducing random edge dropping from the input graph at training epochs could reduce over-fitting and over-smoothing phenomenon and increase the depth of GNNs.
ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment
On the other hand, AAM is an attention module which can get anisotropic attention mask focusing on the region of point and its local edge connected by adjacent points, it has a stronger response in tangent than in normal, which means relaxed constraints in the tangent.
Ranked #5 on
Face Alignment
on 300W
Efficient and Systematic Partitioning of Large and Deep Neural Networks for Parallelization
We propose the Flex-Edge Recursive Graph and the Double Recursive Algorithm, successfully limiting our parallelization strategy generation to a linear complexity with a good quality of parallelization strategy.
Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models
A sequence-to-sequence learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spelling errors as input and outputs the corrected one.
Molecular Clouds in the Second Quadrant of the Milky Way Mid-plane from l$=$104$.\!\!^{\circ}$75 to l=119$.\!\!^{\circ}$75 and b=$-$5$.\!\!^{\circ}$25 to b=5$.\!\!^{\circ}$25
About 78\% of the N-PDFs of the selected molecular clouds are well fitted with log-normal functions with only small deviations at high-densities which correspond to star-forming regions with scales of $\sim$1-5 pc in the Local arm and $\sim$5-10 pc in the Perseus arm.
Astrophysics of Galaxies
Automatic Crack Detection on Road Pavements Using Encoder Decoder Architecture
Finally, the hierarchical feature learning module is designed to obtain a multi-scale features from the high to low-level convolutional layers, which are integrated to predict pixel-wise crack detection.
Ensemble of Deep Convolutional Neural Networks for Automatic Pavement Crack Detection and Measurement
In this paper, we propose an ensemble of convolutional neural networks (without a pooling layer) based on probability fusion for automated pavement crack detection and measurement.
Sparse estimation via $\ell_q$ optimization method in high-dimensional linear regression
In this paper, we discuss the statistical properties of the $\ell_q$ optimization methods $(0<q\leq 1)$, including the $\ell_q$ minimization method and the $\ell_q$ regularization method, for estimating a sparse parameter from noisy observations in high-dimensional linear regression with either a deterministic or random design.
Deep Expectation-Maximization in Hidden Markov Models via Simultaneous Perturbation Stochastic Approximation
We propose a novel method to estimate the parameters of a collection of Hidden Markov Models (HMM), each of which corresponds to a set of known features.
Accurate Retinal Vessel Segmentation via Octave Convolution Neural Network
Compared with other convolution networks utilizing standard convolution for feature extraction, the proposed method utilizes octave convolutions and octave transposed convolutions for learning multiple-spatial-frequency features, thus can better capture retinal vasculatures with varying sizes and shapes.
Online Cyber-Attack Detection in Smart Grid: A Reinforcement Learning Approach
Early detection of cyber-attacks is crucial for a safe and reliable operation of the smart grid.
Constrained Optimization Based Low-Rank Approximation of Deep Neural Networks
We present COBLA---Constrained Optimization Based Low-rank Approximation---a systematic method of finding an optimal low-rank approximation of a trained convolutional neural network, subject to constraints in the number of multiply-accumulate (MAC) operations and the memory footprint.
Multi-task Learning for Continuous Control
In addition, most reinforcement learning research on multi-task learning has been focused on discrete action spaces, which are not used for robotic control in the real-world.
