Search Results for author:
Found 40 papers, 16 papers with code
How to Complete Domain Tuning while Keeping General Ability in LLM: Adaptive Layer-wise and Element-wise Regularization
Large Language Models (LLMs) exhibit strong general-purpose language capabilities.
LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment
As large language models (LLMs) demonstrate exceptional performance across various domains, the deployment of these models on edge devices has emerged as a new trend.
Structure-Based Molecule Optimization via Gradient-Guided Bayesian Update
Structure-based molecule optimization (SBMO) aims to optimize molecules with both continuous coordinates and discrete types against protein targets.
Model Editing for LLMs4Code: How Far are We?
Despite that, a comprehensive study that thoroughly compares and analyzes the performance of the state-of-the-art model editing techniques for adapting the knowledge within LLMs4Code across various code-related tasks is notably absent.
Identifying Knowledge Editing Types in Large Language Models
However, there is a lack of effective measures to prevent the malicious misuse of this technology, which could lead to harmful edits in LLMs.
The Scaling Law in Stellar Light Curves
Analyzing time series of fluxes from stars, known as stellar light curves, can reveal valuable information about stellar properties.
PTA: Enhancing Multimodal Sentiment Analysis through Pipelined Prediction and Translation-based Alignment
In contrast, a pipeline framework first identifies aspects through MATE (Multimodal Aspect Term Extraction) and then aligns these aspects with image patches for sentiment classification (MASC: Multimodal Aspect-Oriented Sentiment Classification).
Aspect-Based Sentiment Analysis
Multimodal Sentiment Analysis
+2
Latent Chemical Space Searching for Plug-in Multi-objective Molecule Generation
Molecular generation, an essential method for identifying new drug structures, has been supported by advancements in machine learning and computational technology.
DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking
Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base.
SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering
In particular, local editing methods, which directly update model parameters, are more suitable for updating a small amount of knowledge.
How to Bridge the Gap between Modalities: Survey on Multimodal Large Language Model
We explore Multimodal Large Language Models (MLLMs), which integrate LLMs like GPT-4 to handle multimodal data, including text, images, audio, and more.
Automatic nodule identification and differentiation in ultrasound videos to facilitate per-nodule examination
Ultrasound is a vital diagnostic technique in health screening, with the advantages of non-invasive, cost-effective, and radiation free, and therefore is widely applied in the diagnosis of nodules.
Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models
Notably, the error remains under 3% for 30-day light curves, whose oscillations are undetectable by a conventional pipeline in 30% cases.
PMET: Precise Model Editing in a Transformer
To achieve more precise model editing, we analyze hidden states of MHSA and FFN, finding that MHSA encodes certain general knowledge extraction patterns.
Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical World
We also demonstrate the effectiveness of our approach in physical-world scenarios under various settings, including different angles, distances, postures, and scenes for both visible and infrared sensors.
Unified Adversarial Patch for Cross-modal Attacks in the Physical World
To show the potential risks under such scenes, we propose a unified adversarial patch to perform cross-modal physical attacks, i. e., fooling visible and infrared object detectors at the same time via a single patch.
Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction
Recently, many studies incorporate external knowledge into character-level feature based models to improve the performance of Chinese relation extraction.
Artificial Intelligence System for Detection and Screening of Cardiac Abnormalities using Electrocardiogram Images
In this study, we present an AI system developed to detect and screen cardiac abnormalities (CAs) from real-world ECG images.
Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks
Extensive experiments are conducted on the Face Recognition (FR) task, and results on four representative FR models show that our method can significantly improve the attack success rate and query efficiency.
Behavior Prior Representation learning for Offline Reinforcement Learning
Our method, Behavior Prior Representation (BPR), learns state representations with an easy-to-integrate objective based on behavior cloning of the dataset: we first learn a state representation by mimicking actions from the dataset, and then train a policy on top of the fixed representation, using any off-the-shelf Offline RL algorithm.
Span-based joint entity and relation extraction augmented with sequence tagging mechanism
On the one hand, the core architecture enables our model to learn token-level label information via the sequence tagging mechanism and then uses the information in the span-based joint extraction; on the other hand, it establishes a bi-directional information interaction between NER and RE.
Joint Entity and Relation Extraction
named-entity-recognition
+3
A Two-Phase Paradigm for Joint Entity-Relation Extraction
An exhaustive study has been conducted to investigate span-based models for the joint entity and relation extraction task.
Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes
Few-shot named entity recognition (NER) enables us to build a NER system for a new domain using very few labeled examples.
A Context-Aware Approach for Textual Adversarial Attack through Probability Difference Guided Beam Search
Textual adversarial attacks expose the vulnerabilities of text classifiers and can be used to improve their robustness.
SummScore: A Comprehensive Evaluation Metric for Summary Quality Based on Cross-Encoder
However, the existing evaluation metrics for summary text are only rough proxies for summary quality, suffering from low correlation with human scoring and inhibition of summary diversity.
Topic-Grained Text Representation-based Model for Document Retrieval
Document retrieval enables users to find their required documents accurately and quickly.
Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognition
Previous research has demonstrated that the two paradigms have clear complementary advantages, but few models have attempted to leverage these advantages in a single NER model as far as we know.
Astroconformer: Inferring Surface Gravity of Stars from Stellar Light Curves with Transformer
We introduce Astroconformer, a Transformer-based model to analyze stellar light curves from the Kepler mission.
Dynamic Graph Learning-Neural Network for Multivariate Time Series Modeling
The model acquires static and dynamic graph matrices from data to model long- and short-term patterns respectively.
Generating Transferable Adversarial Patch by Simultaneously Optimizing its Position and Perturbations
In this paper, we propose a method to simultaneously optimize the position and perturbation to generate transferable adversarial patches, and thus obtain high attack success rates in the black-box setting.
One Million Scenes for Autonomous Driving: ONCE Dataset
To facilitate future research on exploiting unlabeled data for 3D detection, we additionally provide a benchmark in which we reproduce and evaluate a variety of self-supervised and semi-supervised methods on the ONCE dataset.
Boosting Span-based Joint Entity and Relation Extraction via Squence Tagging Mechanism
To solve this problem, we pro-pose Sequence Tagging enhanced Span-based Network (STSN), a span-based joint extrac-tion network that is enhanced by token BIO label information derived from sequence tag-ging based NER.
Joint Entity and Relation Extraction
named-entity-recognition
+4
Adversarial Sticker: A Stealthy Attack Method in the Physical World
Unlike the previous adversarial patches by designing perturbations, our method manipulates the sticker's pasting position and rotation angle on the objects to perform physical attacks.
Span-based Joint Entity and Relation Extraction with Attention-based Span-specific and Contextual Semantic Representations
Span-based joint extraction models have shown their efficiency on entity recognition and relation extraction.
CardioLearn: A Cloud Deep Learning Service for Cardiac Disease Detection from Electrocardiogram
Electrocardiogram (ECG) is one of the most convenient and non-invasive tools for monitoring peoples' heart condition, which can use for diagnosing a wide range of heart diseases, including Cardiac Arrhythmia, Acute Coronary Syndrome, et al.
Multi-Modal Three-Stream Network for Action Recognition
Human action recognition in video is an active yet challenging research topic due to high variation and complexity of data.
The K2 Bright Star Survey I: Methodology and Data Release
While the Kepler Mission was designed to look at tens of thousands of faint stars (V > 12), brighter stars that saturated the detector are important because they can be and have been observed very accurately by other instruments.
Solar and Stellar Astrophysics Instrumentation and Methods for Astrophysics
Asteroseismology of 16000 Kepler Red Giants: Global Oscillation Parameters, Masses, and Radii
Thanks to the large red giant sample, we confirm that red-giant-branch (RGB) and helium-core-burning (HeB) stars collectively differ in the distribution of oscillation amplitude, granulation power, and width of power excess, which is mainly due to the mass difference.
Solar and Stellar Astrophysics
Attention-based Natural Language Person Retrieval
Following the recent progress in image classification and captioning using deep learning, we develop a novel natural language person retrieval system based on an attention mechanism.
Drug-drug Interaction Extraction via Recurrent Neural Network with Multiple Attention Layers
The experiments show that our model classifies most of the drug pairs into correct DDI categories, which outperforms the existing NLP or deep learning methods.
