Search Results for author:
Found 22 papers, 9 papers with code
Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey
Due to intensive synchronization of models and sharing of data across GPUs and computing nodes during distributed training and inference processes, communication efficiency becomes the bottleneck for achieving high performance at a large scale.
CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment
Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences, ensuring these LLMs behave in beneficial and comprehensible ways to users.
MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property
In this paper, we contribute a new benchmark, the first Multilingual-oriented quiZ on Intellectual Property (MoZIP), for the evaluation of LLMs in the IP domain.
Layer-wise Regularized Dropout for Neural Language Models
To solve the inconsistency between training and inference caused by the randomness of dropout, some studies use consistency training to regularize dropout at the output layer.
History, Development, and Principles of Large Language Models-An Introductory Survey
Language models serve as a cornerstone in natural language processing (NLP), utilizing mathematical methods to generalize language laws and knowledge for prediction and generation.
E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models
The integration of LLMs and education is getting closer and closer, however, there is currently no benchmark for evaluating LLMs that focuses on the Chinese K-12 education domain.
Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models
In this paper, we propose a new paradigm for fine-tuning called F-Learning (Forgetting before Learning), which employs parametric arithmetic to facilitate the forgetting of old knowledge and learning of new knowledge.
Expression Syntax Information Bottleneck for Math Word Problems
To this end, we design an Expression Syntax Information Bottleneck method for MWP (called ESIB) based on variational information bottleneck, which extracts essential features of expression syntax tree while filtering latent-specific redundancy containing syntax-irrelevant features.
Accelerating Wireless Federated Learning via Nesterov's Momentum and Distributed Principle Component Analysis
A wireless federated learning system is investigated by allowing a server and workers to exchange uncoded information via orthogonal wireless channels.
Self-consistent Reasoning For Solving Math Word Problems
Specifically, we firstly obtain a sub-network by pruning a roberta2tree model, for the sake to use the gap on output distribution between the original roberta2tree model and the pruned sub-network to expose spurious correlative samples.
Data Augmentation for Depression Detection Using Skeleton-Based Gait Information
Gait analysis provides a non-contact, low-cost, and efficient early screening method for depression.
SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification
In this paper, we for the first time propose a Self-supervised Multi-scale Skeleton Graph Encoding (SM-SGE) framework that comprehensively models human body, component relations, and skeleton dynamics from unlabeled skeleton graphs of various scales to learn an effective skeleton representation for person Re-ID.
More than Encoder: Introducing Transformer Decoder to Upsample
The local and detailed feature from the shallower layer such as boundary and tissue texture is particularly more important in medical segmentation compared with natural image segmentation.
Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification
To fully explore body relations, we construct graphs to model human skeletons from different levels, and for the first time propose a Multi-level Graph encoding approach with Structural-Collaborative Relation learning (MG-SCR) to encode discriminative graph features for person Re-ID.
Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition
Existing approaches usually learn action representations by sequential prediction but they suffer from the inability to fully learn semantic information.
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification
This paper proposes a self-supervised gait encoding approach that can leverage unlabeled skeleton data to learn gait representations for person Re-ID.
Self-Supervised Gait Encoding with Locality-Aware Attention for Person Re-Identification
Unlike previous methods, we for the first time propose a generic gait encoding approach that can utilize unlabeled skeleton data to learn gait representations in a self-supervised manner.
Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
In this paper, we for the first time propose a contrastive action learning paradigm named AS-CAL that can leverage different augmentations of unlabeled skeleton data to learn action representations in an unsupervised manner.
Emotion Recognition From Gait Analyses: Current Research and Future Directions
This article reviews current research on gait-based emotion detection, particularly on how gait parameters can be affected by different emotion states and how the emotion states can be recognized through distinct gait patterns.
MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis
The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications.
Towards Interpreting Deep Neural Networks via Understanding Layer Behaviors
ii) the $W$-distance of a specific layer to the target distribution tends to decrease along training iterations.
Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks
Discriminative features are obtained by constraining the deep CNNs to map training samples to the corresponding anchors as close as possible.
