Search Results for author:
Found 11 papers, 5 papers with code
Duplex: Dual Prototype Learning for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to enable models to recognize novel compositions of visual states and objects that were absent during training.
Recent Advances in Attack and Defense Approaches of Large Language Models
Given the extensive research in the field of LLM security, we believe that summarizing the current state of affairs will help the research community better understand the present landscape and inform future developments.
Bilingual Adaptation of Monolingual Foundation Models
By continually pre-training on a mix of Arabic and English corpora, the model retains its proficiency in English while acquiring capabilities in Arabic.
keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLM
Large language models (LLMs) have exhibited remarkable performance on various natural language processing (NLP) tasks, especially for question answering.
Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Models
For downstream applications of vision-language pre-trained models, there has been significant interest in constructing effective prompts.
HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding
With the tree-likeness property of hyperbolic space, the underlying semantic hierarchy among words and topics can be better exploited to mine more interpretable topics.
Knowledge-Aware Bayesian Deep Topic Model
We propose a Bayesian generative model for incorporating prior domain knowledge into hierarchical topic modeling.
TopicNet: Semantic Graph-Guided Topic Discovery
Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner and automatically organize them into a topic hierarchy.
TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion
The model has to adapt to changes in the TKG for efficient training and inference while preserving its performance on historical knowledge.
GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems
We develop a Graph Structure Aware Incremental Learning framework, GraphSAIL, to address the commonly experienced catastrophic forgetting problem that occurs when training a model in an incremental fashion.
Non-Parametric Graph Learning for Bayesian Graph Neural Networks
A Bayesian framework which targets posterior inference of the graph by considering it as a random quantity can be beneficial.
