Yuxuan Yuan

SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM

2024 · arXiv (Cornell University)

While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass Large Language Model, …

Decompose and Attribute: Boosting Generalizable Open-Set Object Detection via Objectness Score

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Open-set object detection (OSOD) aims to recognize known object categories while localizing previously unseen instances. However, real-world scenarios often involve co-occurring domain shifts and novel object categories. Existing OSOD methods typically overlook domain shifts, relying …