夏天｜华中科技大学｜学者主页

2026

Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs

Tian Xia

arXiv preprint

2026

Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI

Tian Xia, Hanchen Li, Zhifei Li, Xiaokun Chen, Hao Kang, Yifan Qiao, Yi Xu, Ion Stoica

arXiv preprint

2026

QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling

Tian Xia, Jiaqi Zhang, Yueyang Liu, Hongjian Dou, Tingya Yin, Jiangxia Cao, Xulei Liang, Tianlu Xie, Lihao Liu, Xiang Chen, Shen Wang, Changxin Lao, Haixiang Gan, Jinkai Yu, Keting Cen, Lu Hao, Xu Zhang, Qiqiang Zhong, Zhongbo Sun, Yiyu Wang, Shuang Yang, Mingxin Wen, Xiangyu Wu, Shaoguo Liu, Tingting Gao, Zhaojie Liu, Han Li, Kun Gai

arXiv preprint

2026

MemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agents

Weiwei Xie, Shaoxiong Guo, Fan Zhang, Tian Xia, Xue Yang, Lizhuang Ma, Junchi Yan, Qibing Ren

arXiv preprint

2026

EMA: Elastic and Performance Transparent Memory Across GPUs

Yi Xu, Tian Xia, Ion Stoica

arXiv preprint

2026

SkyNomad: On Using Multi-Region Spot Instances to Minimize AI Batch Job Cost

Zhifei Li, Tian Xia, Ziming Mao, Zihan Zhou, Ethan J. Jackson, Jamison Kerney, Zhanghao Wu, Pratik Mishra, Yi Xu, Yifan Qiao, Scott Shenker, Ion Stoica

arXiv preprint

2026

IMMSched: Interruptible Multi-DNN Scheduling via Parallel Multi-Particle Optimizing Subgraph Isomorphism

Boran Zhao, Hetian Liu, Zihang Yuan, Yanbin Hu, Wenzhe Zhao, Tian Xia, Pengju Ren

arXiv preprint

2025

SkyWalker: A Locality-Aware Cross-Region Load Balancer for LLM Inference

Tian Xia, Ziming Mao, Jamison Kerney, Ethan J. Jackson, Zhifei Li, Jiarong Xing, Scott Shenker, Ion Stoica

arXiv preprint

2025

IsoSched: Preemptive Tile Cascaded Scheduling of Multi-DNN via Subgraph Isomorphism

Boran Zhao, Zihang Yuan, Yanbin Hu, Haiming Zhai, Haoruo Zhang, Wenzhe Zhao, Tian Xia, Pengju Ren

arXiv preprint

2025

SparseMap: A Sparse Tensor Accelerator Framework Based on Evolution Strategy

Boran Zhao, Haiming Zhai, Zihang Yuan, Hetian Liu, Tian Xia, Wenzhe Zhao, Pengju Ren

arXiv preprint

2025

Nearly Lossless Adaptive Bit Switching

Haiduo Huang, Zhenhua Liu, Tian Xia, Wenzhe zhao, Pengju Ren

arXiv preprint

2025

PlanGenLLMs: A Modern Survey of LLM Planning Capabilities

Hui Wei, Zihao Zhang, Shenghua He, Tian Xia, Shijia Pan, Fei Liu

arXiv preprint

2025

Partial Channel Network: Compute Fewer, Perform Better

Haiduo Huang, Tian Xia, Wenzhe zhao, Pengju Ren

arXiv preprint

2025

Barbarians at the Gate: How AI is Upending Systems Research

Audrey Cheng, Shu Liu, Melissa Pan, Zhifei Li, Bowen Wang, Alex Krentsel, Tian Xia, Mert Cemri, Jongseok Park, Shuo Yang, Jeff Chen, Lakshya Agrawal, Aditya Desai, Jiarong Xing, Koushik Sen, Matei Zaharia, Ion Stoica

arXiv preprint

2025

Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective

Shenghua He, Tian Xia, Xuan Zhou, Hui Wei

arXiv preprint

2025

The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Alejandro Cuadron, Dacheng Li, Wenjie Ma, Xingyao Wang, Yichuan Wang, Siyuan Zhuang, Shu Liu, Luis Gaspar Schroeder, Tian Xia, Huanzhi Mao, Nicholas Thumiger, Aditya Desai, Ion Stoica, Ana Klimovic, Graham Neubig, Joseph E. Gonzalez

arXiv preprint

2025

Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning

Jingyang Lin, Andy Wong, Tian Xia, Shenghua He, Hui Wei, Mei Han, Jiebo Luo

arXiv preprint

2025

NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds

Boran Zhao, Haiduo Huang, Qiwei Dang, Wenzhe Zhao, Tian Xia, Pengju Ren

arXiv preprint

2025

League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models

Qianhong Guo, Wei Xie, Xiaofang Cai, Enze Wang, Shuoyoucheng Ma, Xiaobing Sun, Tian Xia, Kai Chen, Xiaofeng Wang, Baosheng Wang

arXiv preprint

2025

Let the Barbarians In: How AI Can Accelerate Systems Performance Research

Audrey Cheng, Shu Liu, Melissa Pan, Zhifei Li, Shubham Agarwal, Mert Cemri, Bowen Wang, Alexander Krentsel, Tian Xia, Jongseok Park, Shuo Yang, Jeff Chen, Lakshya Agrawal, Ashwin Naren, Shulu Li, Ruiying Ma, Aditya Desai, Jiarong Xing, Koushik Sen, Matei Zaharia, Ion Stoica

arXiv preprint

2025

FrontierCS: Evolving Challenges for Evolving Intelligence

Qiuyang Mang, Wenhao Chai, Zhifei Li, Huanzhi Mao, Shang Zhou, Alexander Du, Hanchen Li, Shu Liu, Edwin Chen, Yichuan Wang, Xieting Chu, Zerui Cheng, Yuan Xu, Tian Xia, Zirui Wang, Tianneng Shi, Jianzhu Yao, Yilong Zhao, Qizheng Zhang, Charlie Ruan, Zeyu Shen, Kaiyuan Liu, Runyuan He, Dong Xing, Zerui Li, Zirong Zeng, Yige Jiang, Lufeng Cheng, Ziyi Zhao, Youran Sun, Wesley Zheng, Meiyuwang Zhang, Ruyi Ji, Xuechang Tu, Zihan Zheng, Zexing Chen, Kangyang Zhou, Zhaozi Wang, Jingbang Chen, Aleksandra Korolova, Peter Henderson, Pramod Viswanath, Vijay Ganesh, Saining Xie, Zhuang Liu, Dawn Song, Sewon Min, Ion Stoica, Joseph E. Gonzalez, Jingbo Shang, Alvin Cheung

arXiv preprint

2025

Locality-aware Fair Scheduling in LLM Serving

Shiyi Cao, Yichuan Wang, Ziming Mao, Pin-Lun Hsu, Liangsheng Yin, Tian Xia, Dacheng Li, Shu Liu, Yineng Zhang, Yang Zhou, Ying Sheng, Joseph Gonzalez, Ion Stoica

arXiv preprint

2024

Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method

Tian Xia, Zhiwei He, Tong Ren, Yibo Miao, Zhuosheng Zhang, Yang Yang, Rui Wang

arXiv preprint

2024

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

Tongxin Yuan, Zhiwei He, Lingzhong Dong, Yiming Wang, Ruijie Zhao, Tian Xia, Lizhen Xu, Binglin Zhou, Fangqi Li, Zhuosheng Zhang, Rui Wang, Gongshen Liu

arXiv preprint

2024

Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates

Hui Wei, Shenghua He, Tian Xia, Fei Liu, Andy Wong, Jingyang Lin, Mei Han

arXiv preprint

2024

SkyServe: Serving AI Models across Regions and Clouds with Spot Instances

Ziming Mao, Tian Xia, Zhanghao Wu, Wei-Lin Chiang, Tyler Griggs, Romil Bhardwaj, Zongheng Yang, Scott Shenker, Ion Stoica

arXiv preprint

DOI

精选作品

期刊论文

基于多视角图神经网络的跨度级方面情感三元组抽取

面向稀疏矩阵向量乘法的GPU性能建模和算法优化

基于开源处理器的间接访问数据预取器设计

面向非规则链表访存的高性能CPU预取器设计

MEF:基于在线容错的云计算资源调度方法

物联网监测时间序列数据异常检测与处理研究

基于高预测性的稀疏矩阵向量乘法并行计算优化

基于深度学习和白流量过滤的网络流量检测系统研究

支持多数据源安全共享的分布式大数据协作系统研究

结合BP神经网络的动态帧时隙ALOHA改进算法

利用JNI实现ICTCLAS系统的Java调用

基于面向对象方法的选单自动生成系统

预印本

Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs

Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI

QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling

MemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agents

EMA: Elastic and Performance Transparent Memory Across GPUs

SkyNomad: On Using Multi-Region Spot Instances to Minimize AI Batch Job Cost

IMMSched: Interruptible Multi-DNN Scheduling via Parallel Multi-Particle Optimizing Subgraph Isomorphism

SkyWalker: A Locality-Aware Cross-Region Load Balancer for LLM Inference

IsoSched: Preemptive Tile Cascaded Scheduling of Multi-DNN via Subgraph Isomorphism

SparseMap: A Sparse Tensor Accelerator Framework Based on Evolution Strategy

Nearly Lossless Adaptive Bit Switching

PlanGenLLMs: A Modern Survey of LLM Planning Capabilities

Partial Channel Network: Compute Fewer, Perform Better

Barbarians at the Gate: How AI is Upending Systems Research

Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective

The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning

NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds

League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models

Let the Barbarians In: How AI Can Accelerate Systems Performance Research

FrontierCS: Evolving Challenges for Evolving Intelligence

Locality-aware Fair Scheduling in LLM Serving

Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates

SkyServe: Serving AI Models across Regions and Clouds with Spot Instances