Search Results for author:
Found 14 papers, 3 papers with code
Learning to Compress Prompt in Natural Language Formats
In this work, we propose a Natural Language Prompt Encapsulation (Nano-Capsulator) framework compressing original prompts into NL formatted Capsule Prompt while maintaining the prompt utility and transferability.
Large Language Models As Faithful Explainers
In this work, we introduce a generative explanation framework, xLLM, to improve the faithfulness of the explanations provided in natural language formats for LLMs.
LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
To achieve this goal, we propose SelfExtend to extend the context window of LLMs by constructing bi-level attention information: the grouped attention and the neighbor attention.
LETA: Learning Transferable Attribution for Generic Vision Explainer
To address this problem, we develop a pre-trained, DNN-based, generic explainer on large-scale image datasets, and leverage its transferability to explain various vision models for downstream tasks.
CODA: Temporal Domain Generalization via Concept Drift Simulator
In real-world applications, machine learning models often become obsolete due to shifts in the joint distribution arising from underlying temporal trends, a phenomenon known as the "concept drift".
GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length
Our method progressively increases the training length throughout the pretraining phase, thereby mitigating computational costs and enhancing efficiency.
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.
Towards Assumption-free Bias Mitigation
Those studies face challenges, either in inaccurate predictions of sensitive attributes or the need to mitigate unequal distribution of manually defined non-sensitive attributes related to bias.
Multi-Task Learning for Post-transplant Cause of Death Analysis: A Case Study on Liver Transplant
Organ transplant is the essential treatment method for some end-stage diseases, such as liver failure.
Towards Fair Patient-Trial Matching via Patient-Criterion Level Fairness Constraint
To tackle these challenges, deep learning frameworks have been created to match patients to trials.
Mitigating Relational Bias on Knowledge Graphs
Knowledge graph data are prevalent in real-world applications, and knowledge graph neural networks (KGNNs) are essential techniques for knowledge graph representation learning.
Auto-PINN: Understanding and Optimizing Physics-Informed Neural Architecture
Physics-informed neural networks (PINNs) are revolutionizing science and engineering practice by bringing together the power of deep learning to bear on scientific computation.
EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion
In this work, we propose an Efficient Panoptic Segmentation Network (EPSNet) to tackle the panoptic segmentation tasks with fast inference speed.
Ranked #34 on
Panoptic Segmentation
on COCO test-dev
