Search Results for author:
Found 103 papers, 42 papers with code
KLMo: Knowledge Graph Enhanced Pretrained Language Model with Fine-Grained Relationships
In this work, we propose to incorporate KG (including both entities and relations) into the language learning process to obtain KG-enhanced pretrained Language Model, namely KLMo.
Learning to Answer Psychological Questionnaire for Personality Detection
We argue that the posts created by a user contain critical contents that could help answer the questions in a questionnaire, resulting in an assessment of his personality by linking the texts and the questionnaire.
CRASpell: A Contextual Typo Robust Approach to Improve Chinese Spelling Correction
These methods have two limitations: (1) they have poor performance on multi-typo texts.
Improving Chinese Grammatical Error Detection via Data augmentation by Conditional Error Generation
The generative model may bring too many changes to the original sentences and generate semantically ambiguous sentences, so it is difficult to detect grammatical errors in these generated sentences.
Approximate Cluster-Based Sparse Document Retrieval with Segmented Maximum Term Weights
This paper revisits cluster-based retrieval that partitions the inverted index into multiple groups and skips the index partially at cluster and document levels during online inference using a learned sparse representation.
Parallel Proportional Fusion of Spiking Quantum Neural Network for Optimizing Image Classification
The recent emergence of the hybrid quantum-classical neural network (HQCNN) architecture has garnered considerable attention due to the potential advantages associated with integrating quantum principles to enhance various facets of machine learning algorithms and computations.
Are LLMs Effective Backbones for Fine-tuning? An Experimental Investigation of Supervised LLMs on Chinese Short Text Matching
The recent success of Large Language Models (LLMs) has garnered significant attention in both academia and industry.
Robust and Scalable Model Editing for Large Language Models
Large language models (LLMs) can make predictions using parametric knowledge--knowledge encoded in the model weights--or contextual knowledge--knowledge presented in the context.
ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models
Some recent efforts have explored introducing ReLU or its variants as the substitutive activation function to help LLMs achieve activation sparsity and inference acceleration, but few can simultaneously obtain high sparsity and comparable model performance.
Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement
Disentangled representation learning strives to extract the intrinsic factors within observed data.
Enhance Reasoning for Large Language Models in the Game Werewolf
This paper presents an innovative framework that integrates Large Language Models (LLMs) with an external Thinker module to enhance the reasoning capabilities of LLM-based agents.
Closed-Loop Unsupervised Representation Disentanglement with $β$-VAE Distillation and Diffusion Probabilistic Feedback
Representation disentanglement may help AI fundamentally understand the real world and thus benefit both discrimination and generation tasks.
Dimensionality Reduction and Dynamical Mode Recognition of Circular Arrays of Flame Oscillators Using Deep Neural Network
Oscillatory combustion in aero engines and modern gas turbines often has significant adverse effects on their operation, and accurately recognizing various oscillation modes is the prerequisite for understanding and controlling combustion instability.
MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation
We present MicroCinema, a straightforward yet effective framework for high-quality and coherent text-to-video generation.
SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
First, we train a degradation-aware prompt extractor, which can generate accurate soft and hard semantic prompts even under strong degradation.
PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection
Drawing inspiration from Psychological Questionnaires, which are carefully designed by psychologists to evaluate individual personality traits through a series of targeted items, we argue that these items can be regarded as a collection of well-structured chain-of-thought (CoT) processes.
Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems
Efficient knowledge retrieval plays a pivotal role in ensuring the success of end-to-end task-oriented dialogue systems by facilitating the selection of relevant information necessary to fulfill user requests.
Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration
Instruction-tuning can be substantially optimized through enhanced diversity, resulting in models capable of handling a broader spectrum of tasks.
Generalized Robust Test-Time Adaptation in Continuous Dynamic Scenarios
Test-time adaptation (TTA) adapts the pre-trained models to test distributions during the inference phase exclusively employing unlabeled test data streams, which holds great value for the deployment of models in real-world applications.
A Demand-Supply Cooperative Responding Strategy in Power System with High Renewable Energy Penetration
In this context, unreasonable profit distributions on the demand-supply side would lead to the conflict of interests and diminish the effectiveness of cooperative responses.
ConPET: Continual Parameter-Efficient Tuning for Large Language Models
First, Static ConPET can adapt former continual learning methods originally designed for relatively smaller models to LLMs through PET and a dynamic replay strategy, which largely reduces the tuning costs and alleviates the over-fitting and forgetting issue.
Breaking through the learning plateaus of in-context learning in Transformer
To study the mechanism behind the learning plateaus, we conceptually seperate a component within the model's internal representation that is exclusively affected by the model's weights.
Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization
Diffusion models have demonstrated impressive performance in various image generation, editing, enhancement and translation tasks.
Inferior Alveolar Nerve Segmentation in CBCT images using Connectivity-Based Selective Re-training
Inferior Alveolar Nerve (IAN) canal detection in CBCT is an important step in many dental and maxillofacial surgery applications to prevent irreversible damage to the nerve during the procedure. The ToothFairy2023 Challenge aims to establish a 3D maxillofacial dataset consisting of all sparse labels and partial dense labels, and improve the ability of automatic IAN segmentation.
Representation Sparsification with Hybrid Thresholding for Fast SPLADE-based Document Retrieval
Learned sparse document representations using a transformer-based neural model has been found to be attractive in both relevance effectiveness and time efficiency.
Distributed Online Convex Optimization with Adversarial Constraints: Reduced Cumulative Constraint Violation Bounds under Slater's Condition
Moreover, if the loss functions are strongly convex, then the network regret bound is reduced to $\mathcal{O}(\log(T))$, and the network cumulative constraint violation bound is reduced to $\mathcal{O}(\sqrt{\log(T)T})$ and $\mathcal{O}(\log(T))$ without and with Slater's condition, respectively.
Multi-source adversarial transfer learning for ultrasound image segmentation with limited similarity
Transfer learning provides the possibility to solve this problem, but there are too many features in natural images that are not related to the target domain.
Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization
In this paper, we study several typical disentangled representation learning works in terms of both disentanglement and compositional generalization abilities, and we provide an important insight: vector-based representation (using a vector instead of a scalar to represent a concept) is the key to empower both good disentanglement and strong compositional generalization.
FARA: Future-aware Ranking Algorithm for Fairness Optimization
However, we find that most existing fair ranking methods adopt greedy algorithms that only optimize rankings for the next immediate session or request.
Mitigating Exploitation Bias in Learning to Rank with an Uncertainty-aware Empirical Bayes Approach
While previous studies have demonstrated the effectiveness of using user behavior signals (e. g., clicks) as both features and labels of LTR algorithms, we argue that existing LTR algorithms that indiscriminately treat behavior and non-behavior signals in input features could lead to suboptimal performance in practice.
Clustering-Aware Negative Sampling for Unsupervised Sentence Representation
Contrastive learning has been widely studied in sentence representation learning.
Optimizing Guided Traversal for Fast Learned Sparse Retrieval
Recent studies show that BM25-driven dynamic index skipping can greatly accelerate MaxScore-based document retrieval based on the learned sparse representation derived by DeepImpact.
A geometry-aware deep network for depth estimation in monocular endoscopy
To address this issue, we introduce a gradient loss to penalize edge fluctuations ambiguous around stepped edge structures and a normal loss to explicitly express the sensitivity to frequently small structures, and propose a geometric consistency loss to spreads the spatial information across the sample grids to constrain the global geometric anatomy structures.
Continuous Indeterminate Probability Neural Network
Third, we propose a new method to visualize the latent random variables, we use one of N dimensional latent variables as a decoder to reconstruct the input image, which can work even for classification tasks, in this way, we can see what each latent variable has learned.
Indeterminate Probability Neural Network
Besides, for our proposed neural network framework, the output of neural network is defined as probability events, and based on the statistical analysis of these events, the inference model for classification task is deduced.
Koos Classification of Vestibular Schwannoma via Image Translation-Based Unsupervised Cross-Modality Domain Adaptation
If ceT1 scans and their annotations can be used for unsupervised learning of hrT2 scans, the performance of Koos classifi-cation using unlabeled hrT2 scans will be greatly improved.
Synthesizing Realistic Image Restoration Training Pairs: A Diffusion Approach
In supervised image restoration tasks, one key issue is how to obtain the aligned high-quality (HQ) and low-quality (LQ) training image pairs.
Research on road object detection algorithm based on improved YOLOX
Road object detection is an important branch of automatic driving technology, The model with higher detection accuracy is more conducive to the safe driving of vehicles.
DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders
Image colorization is a challenging problem due to multi-modal uncertainty and high ill-posedness.
Marginal-Certainty-aware Fair Ranking Algorithm
In MCFair, we first develop a ranking objective that includes uncertainty, fairness, and user utility.
Orders Are Unwanted: Dynamic Deep Graph Convolutional Network for Personality Detection
Predicting personality traits based on online posts has emerged as an important task in many fields such as social network analysis.
AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning
Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available.
Fast-ParC: Capturing Position Aware Global Feature for ConvNets and ViTs
Transformer models have made tremendous progress in various fields in recent years.
Reinforcement Learning to Rank with Coarse-grained Labels
The results on simulated coarse-grained labeled dataset show that while using coarse-grained labels to train an RL model for LTR tasks still can not outperform traditional approaches using fine-grained labels, it still achieve somewhat promising results and is potentially helpful for future research in LTR.
High-Order Leader-Follower Tracking Control under Limited Information Availability
Limited information availability represents a fundamental challenge for control of multi-agent systems, since an agent often lacks sensing capabilities to measure certain states of its own and can exchange data only with its neighbors.
A Flexible Diffusion Model
Despite the empirical success of the hand-crafted fixed forward SDEs, a great quantity of proper forward SDEs remain unexplored.
Learning to Rank Rationales for Explainable Recommendation
Seeing this gap, we propose a model named Semantic-Enhanced Bayesian Personalized Explanation Ranking (SE-BPER) to effectively combine the interaction information and semantic information.
Visual Concepts Tokenization
We further propose a Concept Disentangling Loss to facilitate that different concept tokens represent independent visual concepts.
Test-time Batch Normalization
Deep neural networks often suffer the data distribution shift between training and testing, and the batch statistics are observed to reflect the shift.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Dual Skipping Guidance for Document Retrieval with Learned Sparse Representations
This paper proposes a dual skipping guidance scheme with hybrid scoring to accelerate document retrieval that uses learned sparse representations while still delivering a good relevance.
Hybrid Cloud-Edge Collaborative Data Anomaly Detection in Industrial Sensor Networks
The sensor data detection model based on Gaussian and Bayesian algorithms can detect the anomalous sensor data in real-time and upload them to the cloud for further analysis, filtering the normal sensor data and reducing traffic load.
Vertical Allocation-based Fair Exposure Amortizing in Ranking
Result ranking often affects consumer satisfaction as well as the amount of exposure each item receives in the ranking services.
Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking
Transformer based re-ranking models can achieve high search relevance through context-aware soft matching of query tokens with document tokens.
Beyond a Video Frame Interpolator: A Space Decoupled Learning Approach to Continuous Image Transition
Most of the existing deep learning based VFI methods adopt off-the-shelf optical flow algorithms to estimate the bidirectional flows and interpolate the missing frames accordingly.
Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors
Unlike image-space methods, our FeMaSR restores HR images by matching distorted LR image {\it features} to their distortion-free HR counterparts in our pretrained HR priors, and decoding the matched features to obtain realistic HR images.
Contextual Debiasing for Visual Recognition With Causal Mechanisms
As a common problem in the visual world, contextual bias means the recognition may depend on the co-occurrence context rather than the objects themselves, which is even more severe in multi-label tasks due to multiple targets and the absence of location.
Ranked #9 on
Multi-Label Classification
on MS-COCO
Anomaly-Injected Deep Support Vector Data Description for Text Outlier Detection
Anomaly detection or outlier detection is a common task in various domains, which has attracted significant research efforts in recent years.
Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game
The deep policy gradient method has demonstrated promising results in many large-scale games, where the agent learns purely from its own experience.
Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving
The ability to predict unseen vehicles is critical for safety in autonomous driving.
Multiplex Graph Neural Network for Extractive Text Summarization
Extractive text summarization aims at extracting the most representative sentences from a given document as its summary.
ULTRA: An Unbiased Learning To Rank Algorithm Toolbox
Our toolbox is an important resource for researchers to conduct experiments on ULTR algorithms with different configurations as well as testing their own algorithms with the supported features.
PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction
In this paper, we propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) for CSC, which jointly learns how to understand language and correct spelling errors.
TexSmart: A System for Enhanced Natural Language Understanding
This paper introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
DeceFL: A Principled Decentralized Federated Learning Framework
Although there has been a joint effort in tackling such a critical issue by proposing privacy-preserving machine learning frameworks, such as federated learning, most state-of-the-art frameworks are built still in a centralized way, in which a central client is needed for collecting and distributing model information (instead of data itself) from every other client, leading to high communication pressure and high vulnerability when there exists a failure at or attack on the central client.
Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints
A novel algorithm is first proposed and it achieves an $\mathcal{O}(T^{\max\{c, 1-c\}})$ bound for static regret and an $\mathcal{O}(T^{(1-c)/2})$ bound for cumulative constraint violation, where $c\in(0, 1)$ is a user-defined trade-off parameter, and thus has improved performance compared with existing results.
Psycholinguistic Tripartite Graph Network for Personality Detection
In this paper, we propose a psycholinguistic knowledge-based tripartite graph network, TrigNet, which consists of a tripartite graph network and a BERT-based graph initializer.
GAN Prior Embedded Network for Blind Face Restoration in the Wild
The proposed GAN prior embedded network (GPEN) is easy-to-implement, and it can generate visually photo-realistic results.
Ranked #1 on
Blind Face Restoration
on CelebA-HQ
Regret and Cumulative Constraint Violation Analysis for Distributed Online Constrained Convex Optimization
This is a sequential decision making problem with two sequences of arbitrarily varying convex loss and constraint functions.
Composite Re-Ranking for Efficient Document Search with BERT
By applying token encoding on top of a dual-encoder architecture, BECR separates the attentions between a query and a document while capturing the contextual semantics of a query.
SME: ReRAM-based Sparse-Multiplication-Engine to Squeeze-Out Bit Sparsity of Neural Network
However, it is challenging for crossbar architecture to exploit the sparsity in the DNN.
Gravitational-Wave Detector Networks: Standard Sirens on Cosmology and Modified Gravity Theory
We give a conservative and realistic estimation of the catalogue and Hubble diagram of GW standard sirens and their potential on studying cosmology and modified gravity theory in the 2030s.
Cosmology and Nongalactic Astrophysics Instrumentation and Methods for Astrophysics General Relativity and Quantum Cosmology
A Driving Behavior Recognition Model with Bi-LSTM and Multi-Scale CNN
In autonomous driving, perceiving the driving behaviors of surrounding agents is important for the ego-vehicle to make a reasonable decision.
Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement
From the unsupervised disentanglement perspective, we rethink content and style and propose a formulation for unsupervised C-S disentanglement based on our assumption that different factors are of different importance and popularity for image reconstruction, which serves as a data bias.
Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View
Based on this observation, we argue that it is possible to mitigate the trade-off by $(i)$ leveraging the pretrained generative models with high generation quality, $(ii)$ focusing on discovering the traversal directions as factors for disentangled representation learning.
Towards Building A Group-based Unsupervised Representation Disentanglement Framework
We then propose a model, based on existing VAE-based methods, to tackle the unsupervised learning problem of the framework.
Maximizing Marginal Fairness for Dynamic Learning to Rank
Rankings, especially those in search and recommendation systems, often determine how people access information and how information is exposed to people.
g-SiC6 Monolayer: A New Graphene-like Dirac Cone Material with a High Fermi Velocity
In this work, using first-principles calculations, we have predicted a new Dirac cone material of silicon carbide with the new stoichiometries, named g-SiC6 monolayer, which is composed of sp2 hybridized with a graphene-like structure.
Materials Science
TexSmart: A Text Understanding System for Fine-Grained NER and Enhanced Semantic Analysis
This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
Sparsity-Aware SSAF Algorithm with Individual Weighting Factors for Acoustic Echo Cancellation
In this paper, we propose and analyze the sparsity-aware sign subband adaptive filtering with individual weighting factors (S-IWF-SSAF) algorithm, and consider its application in acoustic echo cancellation (AEC).
Stem-leaf segmentation and phenotypic trait extraction of maize shoots from three-dimensional point cloud
However, automatic stem-leaf segmentation of maize shoots from three-dimensional (3D) point clouds remains challenging, especially for new emerging leaves that are very close and wrapped together during the seedling stage.
Analysis of Multivariate Scoring Functions for Automatic Unbiased Learning to Rank
Because click data is often noisy and biased, a variety of methods have been proposed to construct unbiased learning to rank (ULTR) algorithms for the learning of unbiased ranking models.
HEU Emotion: A Large-scale Database for Multi-modal Emotion Recognition in the Wild
Existing multimodal emotion databases in the real-world conditions are few and small, with a limited number of subjects and expressed in a single language.
Traffic Agent Trajectory Prediction Using Social Convolution and Attention Mechanism
In this paper, we propose a model to predict the trajectories of target agents around an autonomous vehicle.
A Primal-Dual SGD Algorithm for Distributed Nonconvex Optimization
The distributed nonconvex optimization problem of minimizing a global cost function formed by a sum of $n$ local cost functions by using local information exchange is considered.
Optimization and Control
Commonsense Evidence Generation and Injection in Reading Comprehension
Human tackle reading comprehension not only based on the given context itself but often rely on the commonsense beyond.
Unbiased Learning to Rank: Online or Offline?
While their definitions of \textit{unbiasness} are different, these two types of ULTR algorithms share the same goal -- to find the best models that rank documents based on their intrinsic relevance or utility.
Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition
For the same action, the knowledge learned from different media types, e. g., videos and images, may be related and complementary.
Global Temporal Representation based CNNs for Infrared Action Recognition
Existing methods for infrared action recognition are either based on spatial or local temporal information, however, the global temporal information, which can better describe the movements of body parts across the whole video, is not considered.
Distributed Stochastic Gradient Method for Non-Convex Problems with Applications in Supervised Learning
Numerical results also show that the proposed distributed algorithm allows the individual agents to recognize the digits even though the training data corresponding to all the digits is not locally available to each agent.
Optimization and Control Systems and Control Systems and Control
Multi-Grained Named Entity Recognition
This paper presents a novel framework, MGNER, for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be non-overlapping or totally nested.
Ranked #5 on
Nested Mention Recognition
on ACE 2005
Multi-Grained Named Entity Recognition
named-entity-recognition
+5
Event Detection without Triggers
The goal of event detection (ED) is to detect the occurrences of events and categorize them.
On the Generation of Medical Question-Answer Pairs
Question answering (QA) has achieved promising progress recently.
Multi-Grained Entity Proposal Network for Named Entity Recognition
In this paper, we focus on a new Named Entity Recognition (NER) task, i. e., the Multi-grained NER task.
Geodesic Clustering in Deep Generative Models
Deep generative models are tremendously successful in learning low-dimensional latent representations that well-describe the data.
Hierarchically Learned View-Invariant Representations for Cross-View Action Recognition
In order to make the feature representations of videos across views transferable, we then learn a transferable dictionary pair simultaneously from pairs of videos taken at different views to encourage each action video across views to have the same sparse representation.
VH-HFCN based Parking Slot and Lane Markings Segmentation on Panoramic Surround View
At the same time, we proposed a highly fused convolutional network (HFCN) based segmentation method for parking slot and lane markings based on the PSV dataset.
$ρ$-hot Lexicon Embedding-based Two-level LSTM for Sentiment Analysis
Lexical cues are useful for sentiment analysis, and they have been utilized in conventional studies.
Semantic Segmentation via Highly Fused Convolutional Network with Multiple Soft Cost Functions
We evaluate our model on three major segmentation datasets: CamVid, PASCAL VOC and ADE20K.
Disentangled Variational Auto-Encoder for Semi-supervised Learning
The majority of existing semi-supervised VAEs utilize a classifier to exploit label information, where the parameters of the classifier are introduced to the VAE.
Identifying Genetic Risk Factors via Sparse Group Lasso with Group Graph Structure
As a regression model, it is competitive to the state-of-the-arts sparse models; as a variable selection method, SGLGG is promising for identifying Alzheimer's disease-related risk SNPs.
Traffic-Aware Transmission Mode Selection in D2D-enabled Cellular Networks with Token System
We consider a D2D-enabled cellular network where user equipments (UEs) owned by rational users are incentivized to form D2D pairs using tokens.
Large-scale Collaborative Imaging Genetics Studies of Risk Genetic Factors for Alzheimer's Disease Across Multiple Institutions
To the best of our knowledge, this is the first successful run of the computationally intensive model selection procedure to learn a consistent model across different institutions without compromising their privacy while ranking the SNPs that may collectively affect AD.
