4 citations · 10 across the 17 of their papers we have counts for
19 papers
VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling
Yuqi Zhang, Cheng Chen, Yuyu Guo +6
Vision Language Models (VLMs) face significant challenges with ultra-long, interleaved image-text sequences due to the quadratic complexity of self-attention. Current solutions eit…
N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization
Xukun Zhu, Hang Yu, Peng Di +1
The success of Large Language Models in mathematical reasoning relies heavily on the generation of diverse and valid solution paths during the rollout phase. However, current rollo…
Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning
Tong Ye, Hang Yu, Tengfei Ma +6
Large Language Models have demonstrated remarkable progress in general-purpose capabilities and can achieve strong performance in specific domains through fine-tuning on domain-spe…
CODEFUSE-DEBENCH: An Empirical Study on Readability, Recompilability, and Functionality
Puzhuo Liu, Yuhan Huang, Jianlei Chi +2
Binary decompilation aims to recover binaries into high-level source code, but existing evaluations mainly rely on syntactic similarity or single-axis readability metrics, which fa…
TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale
Jun Wang, Ziyin Zhang, Rui Wang +2
Real-time detection and mitigation of technical anomalies are critical for large-scale cloud-native services, where even minutes of downtime can result in massive financial losses…
Guiding LLM-based Loop Invariant Synthesis via Feedback on Local Reasoning Errors
Tianchi Li, Zhenyu Yan, Junhao Liu +2
We propose a novel framework that provides constructive feedback to an LLM in the "guess-and-check" paradigm by formally verifying its own thinking process and detecting local reas…
ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World
Ziyin Zhang, Zihan Liao, Hang Yu +2
The development of high-quality text embeddings is increasingly drifting toward an exclusionary future, defined by three critical barriers: prohibitive computational costs, a narro…
SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval
Wenjie Yang, Hang Yu, Yuyu Guo +1
In this work, we address the critical yet underexplored challenge of symmetric multimodal-to-multimodal (MM2MM) retrieval, where queries and contexts are interchangeable. Existing…
LLM as Graph Kernel: Rethinking Message Passing on Text-Rich Graphs
Ying Zhang, Hang Yu, Haipeng Zhang +1
Text-rich graphs, which integrate complex structural dependencies with abundant textual information, are ubiquitous yet remain challenging for existing learning paradigms. Conventi…
From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion
Cheng Chen, Yuyu Guo, Pengpeng Zeng +4
Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection that links only the output of the vision encoder to the input of the…
Boosting Pointer Analysis With LLM-Enhanced Allocation Function Detection
Baijun Cheng, Kailong Wang, Ling Shi +5
Pointer analysis is foundational for many static analysis tasks, yet its effectiveness is often hindered by imprecise modeling of heap allocations, particularly in C/C++ programs w…
MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Security
Yongjian Guo, Puzhuo Liu, Wanlun Ma +5
The Model Context Protocol (MCP) has emerged as a universal standard that enables AI agents to seamlessly connect with external tools, significantly enhancing their functionality.…
NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories
Xinfang Chen, Siyang Xiao, Xianying Zhu +6
Code editing is a frequent yet cognitively demanding task in software development. Existing AI-powered tools often disrupt developer flow by requiring explicit natural language ins…
Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models
Hanyang Guo, Xiaoheng Xie, Hong-Ning Dai +4
Automated Program Repair (APR) is essential for ensuring software reliability and quality while enhancing efficiency and reducing developers' workload. Although rule-based and lear…
HardRace: A Dynamic Data Race Monitor for Production Use
Xudong Sun, Zhuo Chen, Jingyang Shi +5
Data races are critical issues in multithreaded program, leading to unpredictable, catastrophic and difficult-to-diagnose problems. Despite the extensive in-house testing, data rac…
REPOFUSE: Repository-Level Code Completion with Fused Dual Context
Ming Liang, Xiaoheng Xie, Gehao Zhang +6
The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from…
Principles and Practices of Large-Scale Code Analysis at Ant Group: A Data- and Logic-Oriented Approach
Xiaoheng Xie, Gang Fan, Xiaojun Lin +21
Large-scale software development requires dynamic and multifaceted static code analysis that extends beyond the capabilities of traditional tools. Existing tools like CodeQL lack c…
The Right Prompts for the Job: Repair Code-Review Defects with Large Language Model
Zelin Zhao, Zhaogui Xu, Jialong Zhu +3
Automatic program repair (APR) techniques have the potential to reduce manual efforts in uncovering and repairing program defects during the code review (CR) process. However, the…
Static Code Analysis in the AI Era: An In-depth Exploration of the Concept, Function, and Potential of Intelligent Code Analysis Agents
Gang Fan, Xiaoheng Xie, Xunjin Zheng +2
The escalating complexity of software systems and accelerating development cycles pose a significant challenge in managing code errors and implementing business logic. Traditional…