Qitan Lv

KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning

SciTS: Scientific Time Series Understanding and Generation with LLMs

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation

Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language Models

PEARL: Parallel Speculative Decoding with Adaptive Draft Length

Common Neighbor Induced Message Passing for Inductive Link Prediction in Knowledge Graphs