Publications

Preprint

MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression Youpeng Zhao, Tian Tan, Liqian Peng, Jun Wang, Alec Go
TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Zhiben Chen*, Youpeng Zhao*, Yang Sui, Jun Wang, Yuzhang Shang [Project] [Code] (*: equal contribution)

Conference Publications

Understanding and Tackling Label Errors in Individual-Level Natural Language Understanding Yunpeng Xiao, Kyrie Zhou, Youpeng Zhao, Kai Shu ASONAM 2026 - Best Paper Award 🏆
GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving Shakya Jayakody*, Youpeng Zhao*†, Chinmay Nehate, Jun Wang MLSys 2026 (*: equal contribution , †: project lead)
AIR: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question Answering Yuanhao Zou, Shengji Jin, Andong Deng, Youpeng Zhao, Jun Wang, Chen Chen ICLR 2026
AIRES: Accelerating Out-of-Core GCNs via Algorithm-System Co-Design Shakya Jayakody, Youpeng Zhao, Jun Wang ICLR 2026
MeRino: Entropy-driven Design for Generative Language Models on IoT Devices Youpeng Zhao, Ming Lin, Huadong Tang, Qiang Wu, Jun Wang AAAI 2025
ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching Youpeng Zhao, Di Wu, Jun Wang ISCA 2024
Parameter-Efficient Vision Transformer with Linear Attention Youpeng Zhao, Huadong Tang, Yingying Jiang, Qiang Wu, Jun Wang ICIP 2023
Class-aware contextual information for semantic segmentation Huadong Tang, Youpeng Zhao, Yingying Jiang, Zhuoxin Gan, Qiang Wu ICASSP 2023
Semi-supervised segmentation of mitochondria from electron microscopy images using spatial continuity Yunpeng Xiao, Youpeng Zhao, Ge Yang ISBI 2022

Journal Publications

Classifier Enhancement Using Extended Context and Domain Experts for Semantic Segmentation Huadong Tang, Youpeng Zhao, Min Xu, Jun Wang, Qiang Wu IEEE Transactions on Multimedia (TMM) 2025
CAA: Class-Aware Affinity calculation add-on for semantic segmentation Huadong Tang, Youpeng Zhao, Chaofan Du, Min Xu, Qiang Wu Knowledge-Based Systems (KBS) 2024

Workshop Publications

Are We Scaling the Right Thing? A System Perspective on Test-Time Scaling Youpeng Zhao, Jinpeng LV, Di Wu, Jun Wang, Christopher Gooley NeurIPS 2025 - Workshop on Efficient Reasoning