Search Results for author:
Found 23 papers, 12 papers with code
Survey and Improvement Strategies for Gene Prioritization with Large Language Models
By utilizing HPO classification, novel multi-agent techniques, and our LLM strategy, we improved causal gene identification accuracy compared to our baseline evaluation.
MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation
Large Language Models (LLMs) are becoming essential tools for various natural language processing tasks but often suffer from generating outdated or incorrect information.
Personalizing Low-Rank Bayesian Neural Networks Via Federated Learning
We evaluate LR-BPFL across a variety of datasets, demonstrating its advantages in terms of calibration, accuracy, as well as computational and memory requirements.
Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
To address this dilemma, we introduce TaylorMLP to protect the ownership of released LLMs and prevent their abuse.
Assessing and Enhancing Large Language Models in Rare Disease Question-answering
In this work, we introduce a rare disease question-answering (ReDis-QA) dataset to evaluate the performance of LLMs in diagnosing rare diseases.
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
Long context capability is a crucial competency for large language models (LLMs) as it mitigates the human struggle to digest long-form texts.
Understanding Different Design Choices in Training Large Time Series Models
Moreover, we propose \emph{time series prompt}, a novel statistical prompting strategy tailored to time series data.
FaithLM: Towards Faithful Explanations for Large Language Models
Large Language Models (LLMs) have become proficient in addressing complex tasks by leveraging their extensive internal knowledge and reasoning capabilities.
TVE: Learning Meta-attribution for Transferable Vision Explainer
This meta-attribution leverages the versatility of generic backbone encoders to comprehensively encode the attribution knowledge for the input instance, which enables TVE to seamlessly transfer to explain various downstream tasks, without the need for training on task-specific data.
DiscoverPath: A Knowledge Refinement and Retrieval System for Interdisciplinarity on Biomedical Research
The exponential growth in scholarly publications necessitates advanced tools for efficient article retrieval, especially in interdisciplinary fields where diverse terminologies are used to describe similar research.
DISPEL: Domain Generalization via Domain-Specific Liberating
Domain generalization aims to learn a generalization model that can perform well on unseen test domains by only training on limited source domains.
Efficient GNN Explanation via Learning Removal-based Attribution
A strategy of subgraph sampling is designed in LARA to improve the scalability of the training process.
Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
While the model parameters do contribute to memory usage, the primary memory bottleneck during training arises from storing feature maps, also known as activations, as they are crucial for gradient calculation.
Interactive System-wise Anomaly Detection
Anomaly detection, where data instances are discovered containing feature patterns different from the majority, plays a fundamental role in various applications.
Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach
Motivated by these sufficient conditions, we propose robust fairness regularization (RFR) by considering the worst case within the model weight perturbation ball for each sensitive attribute group.
CoRTX: Contrastive Framework for Real-time Explanation
In this work, we propose a COntrastive Real-Time eXplanation (CoRTX) framework to learn the explanation-oriented representation and relieve the intensive dependence of explainer training on explanation labels.
Efficient XAI Techniques: A Taxonomic Survey
Finally, we summarize the challenges of deploying XAI acceleration methods to real-world scenarios, overcoming the trade-off between faithfulness and efficiency, and the selection of different acceleration methods.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
DIVISION: Memory Efficient Training via Dual Activation Precision
Activation compressed training provides a solution towards reducing the memory cost of training deep neural networks~(DNNs).
Mitigating Algorithmic Bias with Limited Annotations
Existing work on fairness modeling commonly assumes that sensitive attributes for all instances are fully available, which may not be true in many real-world applications due to the high cost of acquiring sensitive information.
Accelerating Shapley Explanation via Contributive Cooperator Selection
Even though Shapley value provides an effective explanation for a DNN model prediction, the computation relies on the enumeration of all possible input feature coalitions, which leads to the exponentially growing complexity.
BED: A Real-Time Object Detection System for Edge Devices
DNNs have been an effective tool for data processing and analysis.
Fairness via Representation Neutralization
This process not only requires a lot of instance-level annotations for sensitive attributes, it also does not guarantee that all fairness sensitive information has been removed from the encoder.
TODS: An Automated Time Series Outlier Detection System
We present TODS, an automated Time Series Outlier Detection System for research and industrial applications.
