S. Wang

A Simple Unknown-Instance-Aware Framework for Open-Set Object Detection

2023

Open-set object detection aims to detect training set objects (known classes) and non-training set objects (unknown classes). The current frameworks rely on human-in-the-loop, i.e., humans provide training data of unknown classes, to be aware of …

SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation

2025 · arXiv (Cornell University)

The rapid growth of scientific literature demands robust tools for automated survey-generation. However, current large language model (LLM)-based methods often lack in-depth analysis, structural coherence, and reliable citations. To address these limitations, we introduce SciSage, …

SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin

2025 · arXiv (Cornell University)

Large Language Models (LLMs) have emerged as a promising approach for binary decompilation. However, the existing LLM-based decompilers still are somewhat limited in effectively presenting a program's source-level structure with its original identifiers. To mitigate …