Search Results for author:
Found 63 papers, 37 papers with code
TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification
Based on continuous prompt embeddings, we propose TransPrompt, a transferable prompting framework for few-shot learning across similar tasks.
CFMD: Dynamic Cross-layer Feature Fusion for Salient Object Detection
Cross-layer feature pyramid networks (CFPNs) have achieved notable progress in multi-scale feature fusion and boundary detail preservation for salient object detection.
Circuit Diagram Retrieval Based on Hierarchical Circuit Graph Representation
The proposed methodology consists of two principal components: a circuit diagram recognition algorithm designed to extract the circuit components and topological structure of the circuit using proposed GAM-YOLO model and a 2-step connected domain filtering algorithm, and a hierarchical retrieval strategy based on graph similarity and different graph representation methods for analog circuits.
PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
The emergence of Retrieval-augmented generation (RAG) has alleviated the issues of outdated and hallucinatory content in the generation of large language models (LLMs), yet it still reveals numerous limitations.
DocEDA: Automated Extraction and Design of Analog Circuits from Documents with Large Language Model
Efficient and accurate extraction of electrical parameters from circuit datasheets and design documents is critical for accelerating circuit design in Electronic Design Automation (EDA).
Cross-model Control: Improving Multiple Large Language Models in One-time Training
Based on this insight, we incorporate a tiny language model with a minimal number of parameters.
A Time Series is Worth Five Experts: Heterogeneous Mixture of Experts for Traffic Flow Prediction
Accurate traffic prediction faces significant challenges, necessitating a deep understanding of both temporal and spatial cues and their complex interactions across multiple variables.
Ranked #1 on
Traffic Prediction
on METR-LA
Expert-level vision-language foundation model for real-world radiology and comprehensive evaluation
When evaluated on the real-world benchmark involving three representative modalities, 2D images (chest X-rays), multi-view images (mammograms), and 3D images (thyroid CT scans), RadFound significantly outperforms other VL foundation models on both quantitative metrics and human evaluation.
DFDG: Data-Free Dual-Generator Adversarial Distillation for One-Shot Federated Learning
In dual-model distillation, the trained dual generators work together to provide the training data for updates of the global model.
Privacy-Preserving Federated Learning with Consistency via Knowledge Distillation Using Conditional Generator
Federated Learning (FL) is gaining popularity as a distributed learning framework that only shares model parameters or gradient updates and keeps private data locally.
Fast and Modular Autonomy Software for Autonomous Racing Vehicles
While far from challenging what a human racecar driver can do, the IAC is pushing the state of the art by facilitating full-sized ARV competitions.
Weakly supervised alignment and registration of MR-CT for cervical cancer radiotherapy
The fusion of the information characteristics of both computed tomography (CT) and magnetic resonance imaging(MRI) modalities may be useful in achieving a precise outline of the extent of paracervical tissue invasion.
A method for quantifying the generalization capabilities of generative models for solving Ising models
Here we design a Hamming distance regularizer in the framework of a class of generative models, variational autoregressive networks (VAN), to quantify the generalization capabilities of various network architectures combined with VAN.
Structure-aware Fine-tuning for Code Pre-trained Models
Over the past few years, we have witnessed remarkable advancements in Code Pre-trained Models (CodePTMs).
Message Passing Variational Autoregressive Network for Solving Intractable Ising Models
Many deep neural networks have been used to solve Ising models, including autoregressive neural networks, convolutional neural networks, recurrent neural networks, and graph neural networks.
Personalized Programming Guidance based on Deep Programming Learning Style Capturing
With the rapid development of big data and AI technology, programming is in high demand and has become an essential skill for students.
InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment
In this paper, we propose InstructGraph, a framework that empowers LLMs with the abilities of graph reasoning and generation by instruction tuning and preference alignment.
Optimal estimation of Gaussian (poly)trees
We develop optimal algorithms for learning undirected Gaussian trees and directed Gaussian polytrees from data.
FaKnow: A Unified Library for Fake News Detection
Over the past years, a large number of fake news detection algorithms based on deep learning have emerged.
Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends
Natural Language Processing (NLP) aims to analyze text or speech via techniques in the computer science field.
Federated Learning via Consensus Mechanism on Heterogeneous Data: A New Perspective on Convergence
We theoretically show that the consensus mechanism can guarantee the convergence of the global objective.
Prioritized Propagation in Graph Neural Networks
Specifically, the framework consists of three components: a backbone GNN model, a propagation controller to determine the optimal propagation steps for nodes, and a weight controller to compute the priority scores for nodes.
Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding
The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios.
DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models
Chain-of-Thought (CoT) prompting has proven to be effective in enhancing the reasoning capabilities of Large Language Models (LLMs) with at least 100 billion parameters.
Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning
Large language models (LLMs) enable in-context learning (ICL) by conditioning on a few labeled training examples as a text-based prompt, eliminating the need for parameter updates and achieving competitive performance.
Graph Self-Contrast Representation Learning
Further, Since the triplet loss only optimizes the relative distance between the anchor and its positive/negative samples, it is difficult to ensure the absolute distance between the anchor and positive sample.
Exchanging-based Multimodal Fusion with Transformer
To solve these issues, in this paper, we propose a novel exchanging-based multimodal fusion model MuSE for text-vision fusion based on Transformer.
TransPrompt v2: A Transferable Prompting Framework for Cross-task Text Classification
We propose TransPrompt v2, a novel transferable prompting framework for few-shot learning across similar or distant text classification tasks.
UPFL: Unsupervised Personalized Federated Learning towards New Clients
To address this challenge, we extend the adaptive risk minimization technique into the unsupervised personalized federated learning setting and propose our method, FedTTA.
You Can Backdoor Personalized Federated Learning
The resistance of pFL methods with parameter decoupling is attributed to the heterogeneous classifiers between malicious clients and benign counterparts.
Boosting Language Models Reasoning with Chain-of-Knowledge Prompting
To mitigate this brittleness, we propose a novel Chain-of-Knowledge (CoK) prompting, where we aim at eliciting LLMs to generate explicit pieces of knowledge evidence in the form of structure triple.
CLIP3Dstyler: Language Guided 3D Arbitrary Neural Style Transfer
In this paper, we propose a novel language-guided 3D arbitrary neural style transfer method (CLIP3Dstyler).
TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills
To tackle the issue, in this paper, we present TransCoder, a unified Transferable fine-tuning strategy for Code representation learning.
When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario
In this paper, we introduce gradient descent into black-box tuning scenario through knowledge distillation.
Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives
Large language models (LLMs) have shown increasing power on various natural language processing (NLP) tasks.
HugNLP: A Unified and Comprehensive Library for Natural Language Processing
In this paper, we introduce HugNLP, a unified and comprehensive library for natural language processing (NLP) with the prevalent backend of HuggingFace Transformers, which is designed for NLP researchers to easily utilize off-the-shelf algorithms and develop novel methods with user-defined models and tasks in real-world scenarios.
GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting
Federated Learning (FL) has emerged as a de facto machine learning area and received rapid increasing research interests from the community.
Uncertainty-aware Self-training for Low-resource Neural Sequence Labeling
Neural sequence labeling (NSL) aims at assigning labels for input language tokens, which covers a broad range of applications, such as named entity recognition (NER) and slot filling, etc.
Meta-Learning Triplet Network with Adaptive Margins for Few-Shot Named Entity Recognition
We design an improved triplet network to map samples and prototype vectors into a low-dimensional space that is easier to be classified and propose an adaptive margin for each entity type.
Meta-Learning Siamese Network for Few-Shot Text Classification
Few-shot learning has been used to tackle the problem of label scarcity in text classification, of which meta-learning based methods have shown to be effective, such as the prototypical networks (PROTO).
SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking
In this paper, to comprehensively enhance the performance of generative graph SSL against other GCL models on both unsupervised and supervised learning tasks, we propose the SeeGera model, which is based on the family of self-supervised variational graph auto-encoder (VGAE).
DDIT: Semantic Scene Completion via Deformable Deep Implicit Templates
It abstracts the shape prior of a category, and thus can provide constraints on the overall shape of an instance.
OSS Mentor A framework for improving developers contributions via deep reinforcement learning
In open source project governance, there has been a lot of concern about how to measure developers' contributions.
SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition
Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data.
Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding
In this paper, to address these problems, we introduce a seminal knowledge prompting paradigm and further propose a knowledge-prompting-based PLM framework KP-PLM.
CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure
To interpret these models, some probing methods have been applied.
Understanding Long Programming Languages with Structure-Aware Sparse Attention
With top-$k$ sparse attention, the most crucial attention relation can be obtained with a lower computational cost.
Towards Unified Prompt Tuning for Few-shot Text Classification
Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts.
A Neural Network Architecture for Program Understanding Inspired by Human Behaviors
In this paper, we consider human behaviors and propose the PGNN-EK model that consists of two main components.
KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering
Extractive Question Answering (EQA) is one of the most important tasks in Machine Reading Comprehension (MRC), which can be solved by fine-tuning the span selecting heads of Pre-trained Language Models (PLMs).
Optimal estimation of Gaussian DAG models
In other words, at least for Gaussian models with equal error variances, learning a directed graphical model is statistically no more difficult than learning an undirected graphical model.
Programming Knowledge Tracing: A Comprehensive Dataset and A New Model
More specifically, we construct a bipartite graph for programming problem embedding, and design an improved pre-training model PLCodeBERT for code embedding, as well as a double-sequence RNN model with exponential decay attention for effective feature fusion.
Efficient Bayesian network structure learning via local Markov boundary search
Perhaps surprisingly, we show that for certain graph ensembles, a simple forward greedy search algorithm (i. e. without a backward pruning phase) suffices to learn the Markov boundary of each node.
Structure learning in polynomial time: Greedy algorithms, Bregman information, and exponential families
Greedy algorithms have long been a workhorse for learning graphical models, and more broadly for learning statistical models with sparse structure.
Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieved state-of-the-art performance.
On Disambiguating Authors: Collaboration Network Reconstruction in a Bottom-up Manner
In this paper, we model the author disambiguation as a collaboration network reconstruction problem, and propose an incremental and unsupervised author disambiguation method, namely IUAD, which performs in a bottom-up manner.
Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction
In this paper, we propose a general approach to learn relation prototypesfrom unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient trainingdata.
EDSL: An Encoder-Decoder Architecture with Symbol-Level Features for Printed Mathematical Expression Recognition
The symbol-level image encoder of EDSL consists of segmentation module and reconstruction module.
A polynomial-time algorithm for learning nonparametric causal graphs
We establish finite-sample guarantees for a polynomial-time algorithm for learning a nonlinear, nonparametric directed acyclic graphical (DAG) model from data.
Hierarchical Optimization Time Integration for CFL-rate MPM Stepping
We propose Hierarchical Optimization Time Integration (HOT) for efficient implicit time-stepping of the Material Point Method (MPM) irrespective of simulated materials and conditions.
Graphics
Improving Neural Relation Extraction with Implicit Mutual Relations
In contrast to existing distant supervision approaches that suffer from insufficient training corpora to extract relations, our proposal of mining implicit mutual relation from the massive unlabeled corpora transfers the semantic information of entity pairs into the RE model, which is more expressive and semantically plausible.
Learning Vertex Representations for Bipartite Networks
Recent years have witnessed a widespread increase of interest in network representation learning (NRL).
BiRank: Towards Ranking on Bipartite Graphs
In this paper, we study the problem of ranking vertices of a bipartite graph, based on the graph's link structure as well as prior information about vertices (which we term a query vector).
