5 papers
AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
Haoyu Huang, Hong Ting Tsang, Jiaxin Bai +3
Retrieval-augmented generation (RAG) has shown some success in augmenting large language models (LLMs) with external knowledge. However, as a non-parametric knowledge integration p…
Reliable Thinking with Images
Haobin Li, Yutong Yang, Yijie Lin +3
As a multimodal extension of Chain-of-Thought (CoT), Thinking with Images (TWI) has recently emerged as a promising avenue to enhance the reasoning capability of Multi-modal Large…
Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approach
Hang Yin, Zipeng Liu, Xiaoyong Peng +1
Graph unlearning is tailored for GNNs to handle widespread and various graph structure unlearning requests, which remain largely unexplored. The GIF (graph influence function) achi…
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora
Jiaxin Bai, Wei Fan, Qi Hu +17
We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. Our system leverages large language models t…
Improving Representation Learning of Complex Critical Care Data with ICU-BERT
Ricardo Santos, André V. Carreiro, Xi Peng +2
The multivariate, asynchronous nature of real-world clinical data, such as that generated in Intensive Care Units (ICUs), challenges traditional AI-based decision-support systems.…