Search Results for author:
Found 37 papers, 14 papers with code
FinTeamExperts: Role Specialized MOEs For Financial Analysis
The framework simulates a collaborative team setting by training each model to specialize in distinct roles: Macro Analysts, Micro analysts, and Quantitative Analysts.
Latent Space Score-based Diffusion Model for Probabilistic Multivariate Time Series Imputation
To address these issues, we propose the Latent Space Score-Based Diffusion Model (LSSDM) for probabilistic multivariate time series imputation.
An Empirical Study on Information Extraction using Large Language Models
To demonstrate the latest representative progress in LLMs' information extraction ability, we assess the information extraction ability of GPT-4 (the latest version of GPT at the time of writing this paper) from four perspectives: Performance, Evaluation Criteria, Robustness, and Error Types.
SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding
(3) Few-shot IO prompting method outperforms the other two methods: zero-shot IO and few-shot CoT.
Combined CNN and ViT features off-the-shelf: Another astounding baseline for recognition
We apply pre-trained architectures, originally developed for the ImageNet Large Scale Visual Recognition Challenge, for periocular recognition.
Expected Grad-CAM: Towards gradient faithfulness
Although input-gradients techniques have evolved to mitigate and tackle the challenges associated with gradients, modern gradient-weighted CAM approaches still rely on vanilla gradients, which are inherently susceptible to the saturation phenomena.
Deep Network Pruning: A Comparative Study on CNNs in Face Recognition
The method is tested on three networks based on the small SqueezeNet (1. 24M parameters) and the popular MobileNetv2 (3. 5M) and ResNet50 (23. 5M) architectures.
Mixture of Latent Experts Using Tensor Products
For \textit{routing function}, we tailor two innovative routing functions according to the granularity: \texttt{TensorPoly-I} which directs to each rank within the entangled tensor while \texttt{TensorPoly-II} offers a finer-grained routing approach targeting each order of the entangled tensor.
Higher-order Spatio-temporal Physics-incorporated Graph Neural Network for Multivariate Time Series Imputation
Also, graph-like optical flow, dynamic graphs, and missing impact can be obtained naturally by HSPGNN, which provides better dynamic analysis and explanation than traditional data-driven models.
Is Your LLM Outdated? Evaluating LLMs at Temporal Generalization
The rapid advancement of Large Language Models (LLMs) highlights the urgent need for evolving evaluation methodologies that keep pace with improvements in language comprehension and information processing.
LMVD: A Large-Scale Multimodal Vlog Dataset for Depression Detection in the Wild
Depression can significantly impact many aspects of an individual's life, including their personal and social functioning, academic and work performance, and overall quality of life.
Predicting Overtakes in Trucks Using CAN Data
Safe overtakes in trucks are crucial to prevent accidents, reduce congestion, and ensure efficient traffic flow, making early prediction essential for timely and informed driving decisions.
Pushing The Limit of LLM Capacity for Text Classification
The value of text classification's future research has encountered challenges and uncertainties, due to the extraordinary efficacy demonstrated by large language models (LLMs) across numerous downstream NLP tasks.
Climate Change from Large Language Models
Climate change poses grave challenges, demanding widespread understanding and low-carbon lifestyle awareness.
Occluded Person Re-Identification with Deep Learning: A Survey and Perspectives
Person re-identification (Re-ID) technology plays an increasingly crucial role in intelligent surveillance systems.
Towards Subject Agnostic Affective Emotion Recognition
Our domain adaptation approach is augmented through meta-learning, which consists of a recurrent neural network, a classifier, and a distributional shift controller based on a sum-decomposable function.
DialogueLLM: Context and Emotion Knowledge-Tuned Large Language Models for Emotion Recognition in Conversations
Large language models (LLMs) and their variants have shown extraordinary efficacy across numerous downstream natural language processing (NLP) tasks, which has presented a new vision for the development of NLP.
VISU at WASSA 2023 Shared Task: Detecting Emotions in Reaction to News Stories Leveraging BERT and Stacked Embeddings
Our system, VISU, participated in the WASSA 2023 Shared Task (3) of Emotion Classification from essays written in reaction to news articles.
An Explainable Model-Agnostic Algorithm for CNN-based Biometrics Verification
This paper describes an adaptation of the Local Interpretable Model-Agnostic Explanations (LIME) AI method to operate under a biometric verification setting.
An Empirical Study on Information Extraction using Large Language Models
To demonstrate the latest representative progress in LLMs' information extraction ability, we assess the information extraction ability of GPT-4 (the latest version of GPT at the time of writing this paper) from four perspectives: Performance, Evaluation Criteria, Robustness, and Error Types.
Dynamic Causal Explanation Based Diffusion-Variational Graph Neural Network for Spatio-temporal Forecasting
Also, by F1-score and probability distribution analysis, we demonstrate that DVGNN better reflects the causal relationship and uncertainty of dynamic graphs.
A Novel Deep Learning based Model for Erythrocytes Classification and Quantification in Sickle Cell Disease
We chose SCD as a model disease condition due to the presence of diverse erythrocyte morphologies in the blood samples of SCD patients.
Huatuo-26M, a Large-scale Chinese Medical QA Dataset
Moreover, we also experimentally show the benefit of the proposed dataset in many aspects: (i) trained models for other QA datasets in a zero-shot fashion; and (ii) as external knowledge for retrieval-augmented generation (RAG); and (iii) improving existing pre-trained language models by using the QA pairs as a pre-training corpus in continued training manner.
A Survey on Few-Shot Class-Incremental Learning
Overall, this paper offers a comprehensive analysis of the latest advances in FSCIL from a methodological, performance, and application perspective.
class-incremental learning
Few-Shot Class-Incremental Learning
+8
Natural Language Reasoning, A Survey
This survey paper proposes a clearer view of natural language reasoning in the field of Natural Language Processing (NLP), both conceptually and practically.
An Overview of Violence Detection Techniques: Current Challenges and Future Directions
The Big Video Data generated in today's smart cities has raised concerns from its purposeful usage perspective, where surveillance cameras, among many others are the most prominent resources to contribute to the huge volumes of data, making its automated analysis a difficult task in terms of computation and preciseness.
Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk
However, the humor aspect of natural language is relatively under-investigated, especially in the age of pre-trained language models.
EEG based Emotion Recognition: A Tutorial and Review
Hence, in this paper, we review from the perspective of researchers who try to take the first step on this topic.
MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare
Mental health is a critical issue in modern society, and mental disorders could sometimes turn to suicidal ideation without adequate treatment.
Pre-trained Language Models in Biomedical Domain: A Systematic Survey
In this paper, we summarize the recent progress of pre-trained language models in the biomedical domain and their applications in biomedical downstream tasks.
Deep Learning for Depression Recognition with Audiovisual Cues: A Review
Consequently, to improve current medical care, many scholars have used deep learning to extract a representation of depression cues in audio and video for automatic depression detection.
Structural block driven - enhanced convolutional neural representation for relation extraction
In this paper, we propose a novel lightweight relation extraction approach of structural block driven - convolutional neural learning.
Kernel Method based on Non-Linear Coherent State
In this paper, by mapping datasets to a set of non-linear coherent states, the process of encoding inputs in quantum states as a non-linear feature map is re-interpreted.
Robustness analytics to data heterogeneity in edge computing
Second, we study a classifier aggregated from a collection of local classifiers trained by data through active sampling at the edge.
Quantum-like Structure in Multidimensional Relevance Judgements
A large number of studies in cognitive science have revealed that probabilistic outcomes of certain human decisions do not agree with the axioms of classical probability theory.
Multi-class Classification Model Inspired by Quantum Detection Theory
Machine Learning has become very famous currently which assist in identifying the patterns from the raw data.
