Publications (45)
Toward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program Search
Haolin Pan, Lianghong Huang, Xvlin Zhou +2
Tensor program optimization is essential for modern machine learning systems, but its search space is enormous. Existing auto-schedulers reduce measurement cost with learned cost m…
Text Region Multiple Information Perception Network for Scene Text Detection
Jinzhi Zheng, Libo Zhang, Yanjun Wu +1
Segmentation-based scene text detection algorithms can handle arbitrary shape scene texts and have strong robustness and adaptability, so it has attracted wide attention. Existing…
QiMeng-TensorOp: Automatically Generating High-Performance Tensor Operators with Hardware Primitives
Xuzhi Zhang, Shaohui Peng, Qirui Zhou +12
Computation-intensive tensor operators constitute over 90\% of the computations in Large Language Models (LLMs) and Deep Neural Networks.Automatically and efficiently generating hi…
BPDO:Boundary Points Dynamic Optimization for Arbitrary Shape Scene Text Detection
Jinzhi Zheng, Libo Zhang, Yanjun Wu +1
Arbitrary shape scene text detection is of great importance in scene understanding tasks. Due to the complexity and diversity of text in natural scenes, existing scene text algorit…
Scale Invariant Fully Convolutional Network: Detecting Hands Efficiently
Dan Liu, Dawei Du, Libo Zhang +4
Existing hand detection methods usually follow the pipeline of multiple stages with high computation cost, i.e., feature extraction, region proposal, bounding box regression, and a…
Learning Semantic Neural Tree for Human Parsing
Ruyi Ji, Dawei Du, Libo Zhang +5
The majority of existing human parsing methods formulate the task as semantic segmentation, which regard each semantic category equally and fail to exploit the intrinsic physiologi…
Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction
Haolin Pan, Jinyuan Dong, Hongbin Zhang +3
Learning effective numerical representations, or embeddings, of programs is a fundamental prerequisite for applying machine learning to automate and enhance compiler optimization.…
A Method for Efficient Heterogeneous Parallel Compilation: A Cryptography Case Study
Zhiyuan Tan, Liutong Han, Mingjie Xing +1
In the era of diminishing returns from Moores Law, heterogeneous computing systems have emerged as a vital approach to enhance computational efficiency. This paper introduces a nov…
Towards Interpretable and Robust Hand Detection via Pixel-wise Prediction
Dan Liu, Libo Zhang, Tiejian Luo +2
The lack of interpretability of existing CNN-based hand detection methods makes it difficult to understand the rationale behind their predictions. In this paper, we propose a novel…
GRACE: Cluster-Specific Sequence Reuse for Compiler Auto-Tuning
Haolin Pan, Chao Zha, Jinyuan Dong +2
Compiler auto-tuning aims to improve optimization quality beyond fixed compiler heuristics, but existing approaches often face a trade-off between effectiveness and deployability.…
VecIntrinBench: Benchmarking Cross-Architecture Intrinsic Code Migration for RISC-V Vector
Liutong Han, Chu Kang, Mingjie Xing +1
Intrinsic functions are specialized functions provided by the compiler that efficiently operate on architecture-specific hardware, allowing programmers to write optimized code in a…
Data Priming Network for Automatic Check-Out
Congcong Li, Dawei Du, Libo Zhang +5
Automatic Check-Out (ACO) receives increased interests in recent years. An important component of the ACO system is the visual item counting, which recognizes the categories and co…
IntrinTrans: LLM-based Intrinsic Code Translator for RISC-V Vector
Liutong Han, Zhiyuan Tan, Hongbin Zhang +4
The use of intrinsic functions to leverage hardware-specific capabilities is a crucial approach for optimizing library performance. Many mainstream libraries implement a large numb…
ECSAS: Exploring Critical Scenarios from Action Sequence in Autonomous Driving
Shuting Kang, Heng Guo, Lijun Zhang +3
Critical scenario generation requires the ability of sampling critical combinations from the infinite parameter space in the logic scenario. Existing solutions aim to explore the c…
AgenticDB: Self-Evolving Reconfiguration Framework for Database Workloads
Xinyue Yang, Chaozheng Wang, Chen Zheng +2
AgenticDB is a self-evolving framework that automatically diagnoses bottlenecks and reconfigures database and operating system settings to improve workload performance while safely…
TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning
Hongyu Lin, Yuchen Li, Haoran Luo +4
Linux kernel tuning is essential for optimizing operating system (OS) performance, yet remains challenging due to the complex kernel space, sparse performance feedback, and strong…
Multi-Granularity Alignment Domain Adaptation for Object Detection
Wenzhang Zhou, Dawei Du, Libo Zhang +2
Domain adaptive object detection is challenging due to distinctive data distribution between source domain and target domain. In this paper, we propose a unified multi-granularity…
The Seeds of the FUTURE Sprout from History: Fuzzing for Unveiling Vulnerabilities in Prospective Deep-Learning Libraries
Zhiyuan Li, Jingzheng Wu, Xiang Ling +3
The widespread application of large language models (LLMs) underscores the importance of deep learning (DL) technologies that rely on foundational DL libraries such as PyTorch and…
EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization
Yize Wu, Ke Gao, Ling Li +1
Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which…
QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm
Qirui Zhou, Shaohui Peng, Weiqiang Xiong +11
The attention operator remains a critical performance bottleneck in large language models (LLMs), particularly for long-context scenarios. While FlashAttention is the most widely u…
BYOS: Knowledge-driven Large Language Models Bring Your Own Operating System More Excellent
Hongyu Lin, Yuchen Li, Haoran Luo +6
Operating system (OS) kernel tuning is a critical yet challenging problem for performance optimization, due to the large configuration space, complex interdependencies among config…
A Large Scale Empirical Analysis on the Adherence Gap between Standards and Tools in SBOM
Chengjie Wang, Jingzheng Wu, Hao Lyu +4
A Software Bill of Materials (SBOM) is a machine-readable artifact that systematically organizes software information, enhancing supply chain transparency and security. To facilita…
Feature Slice Matching for Precise Bug Detection
Ke Ma, Jianjun Huang, Wei You +4
Measuring the function similarity to detect bugs is effective, but the statements unrelated to the bugs can impede the performance due to the noise interference. Suppressing the no…
KGCompiler: Deep Learning Compilation Optimization for Knowledge Graph Complex Logical Query Answering
Hongyu Lin, Haoran Luo, Hanghang Cao +6
Complex Logical Query Answering (CLQA) involves intricate multi-hop logical reasoning over large-scale and potentially incomplete Knowledge Graphs (KGs). Although existing CLQA alg…
SiamMan: Siamese Motion-aware Network for Visual Tracking
Wenzhang Zhou, Longyin Wen, Libo Zhang +3
In this paper, we present a novel siamese motion-aware network (SiamMan) for visual tracking, which consists of the siamese feature extraction subnetwork, followed by the classific…
Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art
Xiang Ling, Lingfei Wu, Jiangyu Zhang +9
Malware has been one of the most damaging threats to computers that span across multiple operating systems and various file formats. To defend against ever-increasing and ever-evol…
Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
Ruyi Ji, Longyin Wen, Libo Zhang +5
Fine-grained visual categorization (FGVC) is an important but challenging task due to high intra-class variances and low inter-class variances caused by deformation, occlusion, ill…
Spatial Attention Pyramid Network for Unsupervised Domain Adaptation
Congcong Li, Dawei Du, Libo Zhang +4
Unsupervised domain adaptation is critical in various computer vision tasks, such as object detection, instance segmentation, and semantic segmentation, which aims to alleviate per…
CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition
Jinzhi Zheng, Ruyi Ji, Libo Zhang +2
Scene text recognition, as a cross-modal task involving vision and text, is an important research topic in computer vision. Most existing methods use language models to extract sem…
Guided Attention Network for Object Detection and Counting on Drones
Yuanqiang Cai, Dawei Du, Libo Zhang +4
Object detection and counting are related but challenging problems, especially for drone based scenes with small objects and cluttered background. In this paper, we propose a new G…
L2T-Tune:LLM-Guided Hybrid Database Tuning with LHS and TD3
Xinyue Yang, Chen Zheng, Yaoyang Hou +4
Configuration tuning is critical for database performance. Although recent advancements in database tuning have shown promising results in throughput and latency improvement, chall…
Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
Haolin Pan, Hongyu Lin, Haoran Luo +5
Compiler auto-tuning optimizes pass sequences to improve performance metrics such as Intermediate Representation (IR) instruction count. Although recent advances leveraging Large L…
Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark
Boying Wang, Libo Zhang, Longyin Wen +2
Automatic security inspection using computer vision technology is a challenging task in real-world scenarios due to various factors, including intra-class variance, class imbalance…
A Wolf in Sheep's Clothing: Practical Black-box Adversarial Attacks for Evading Learning-based Windows Malware Detection in the Wild
Xiang Ling, Zhiyu Wu, Bin Wang +5
Given the remarkable achievements of existing learning-based malware detection in both academia and industry, this paper presents MalGuise, a practical black-box adversarial attack…
A Hybrid, Knowledge-Guided Evolutionary Framework for Personalized Compiler Auto-Tuning
Haolin Pan, Hongbin Zhang, Mingjie Xing +1
Compiler pass auto-tuning is critical for enhancing software performance, yet finding the optimal pass sequence for a specific program is an NP-hard problem. Traditional, general-p…
Exploring the Feasibility of End-to-End Large Language Model as a Compiler
Hongbin Zhang, Shihao Gao, Yang Liu +3
In recent years, end-to-end Large Language Model (LLM) technology has shown substantial advantages across various domains. As critical system software and infrastructure, compilers…
Analog Beamforming Enabled Multicasting: Finite-Alphabet Inputs and Statistical CSI
Yanjun Wu, Zhong Xie, Zhuochen Xie +2
The average multicast rate (AMR) is analyzed in a multicast channel utilizing analog beamforming with finite-alphabet inputs, considering statistical channel state information (CSI…
ECCO: Evidence-Driven Causal Reasoning for Compiler Optimization
Haolin Pan, Lianghong Huang, Jinyuan Dong +2
Compiler auto-tuning faces a dichotomy between traditional black-box search methods, which lack semantic guidance, and recent Large Language Model (LLM) approaches, which often suf…
Speculative Rollback Correction for Quality-Diverse Web Agent Imitation
Longkun Hao, Hongyu Lin, Hao Li +10
Training interactive web agents through imitation learning from expert trajectories has emerged as a highly effective approach. However, determining the optimal timing for expert i…
Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaptation
Yize Wu, Ke Gao, Ling Li +1
Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient method for fine-tuning Large Langauge Models. It updates the weight matrix as , where is the ori…
A Case for Agentic Tuning: From Documentation to Action in PostgreSQL
Hongyu Lin, Mingyu Li, Weichen Zhang +4
Documentation has long guided computer system tuning by distilling expert knowledge into per-parameter recommendations. Yet such guides capture only what experts conclude, discardi…
Synergy-Guided Compiler Auto-Tuning of Nested LLVM Pass Pipelines
Haolin Pan, Jinyuan Dong, Mingjie Xing +1
Compiler optimization relies on sequences of passes to improve program performance. Selecting and ordering these passes automatically, known as compiler auto-tuning, is challenging…
QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation
Xinguo Zhu, Shaohui Peng, Jiaming Guo +10
Developing high-performance GPU kernels is critical for AI and scientific computing, but remains challenging due to its reliance on expert crafting and poor portability. While LLMs…
AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework
Hongyu Lin, Haolin Pan, Haoran Luo +5
Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potentia…
When Large Language Models Confront Repository-Level Automatic Program Repair: How Well They Done?
Yuxiao Chen, Jingzheng Wu, Xiang Ling +4
In recent years, large language models (LLMs) have demonstrated substantial potential in addressing automatic program repair (APR) tasks. However, the current evaluation of these m…