12 papers
JevCoder: When Does Decision Delegation Pay Off in Code Repair?
Jiahao Zhang, Yifan Zhang, Yu Huang
A coding agent repeatedly makes decisions as it repairs code. These decisions shape repair trajectories and affect the token cost of successive model requests. We ask which repair…
Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution
Jiahao Zhang, Yifan Zhang, Yu Huang
Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration, hypothesis, implementation,…
D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models
Liyuan Zhang, Jiarui Zhang, Jinwei Yao +6
Speculative decoding accelerates autoregressive large language model inference by drafting multiple tokens and verifying them in a single target-model forward pass. Recent diffusio…
Controlling Repetition in Protein Language Models
Jiahao Zhang, Zeqing Zhang, Di Wang +1
Protein language models (PLMs) have enabled advances in structure prediction and de novo protein design, yet they frequently collapse into pathological repetition during generation…
RAG-Anything: All-in-One RAG Framework
Zirui Guo, Xubin Ren, Lingrui Xu +2
Retrieval-Augmented Generation (RAG) has emerged as a fundamental paradigm for expanding Large Language Models beyond their static training limitations. However, a critical misalig…
LSM-OPD: Boosting Scan in LSM-Trees by Enabling Direct Computing on Compressed Data
Jianfeng Huang, Ziyao Wang, Lin Yuan +5
Scan-based operations, such as backstage compaction and value filtering, have emerged as the main bottleneck for LSM-Trees in supporting contemporary data-intensive applications. F…
Retrieval-Augmented Prompt for OOD Detection
Ruisong Han, Zongbo Han, Jiahao Zhang +2
Out-of-Distribution (OOD) detection is crucial for the reliable deployment of machine learning models in-the-wild, enabling accurate identification of test samples that differ from…
EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention
Yifan Zhang, Chen Huang, Yueke Zhang +5
Code Language Models (CodeLLMs) learn token importance from data correlations, whereas human developers attend selectively to semantically salient code. We present EyeMulator, a mo…
Flow Sensitivity without Control Flow Graph: An Efficient Andersen-Style Flow-Sensitive Pointer Analysis
Jiahao Zhang, Xiao Cheng, Yuxiang Lei
Flow-sensitive pointer analysis constitutes an essential component of precise program analysis for accurately modeling pointer behaviors by incorporating control flows. Flow-sensit…
Distilling Desired Comments for Enhanced Code Review with Large Language Models
Yongda Yu, Lei Zhang, Guoping Rong +9
There has been a growing interest in using Large Language Models (LLMs) for code review thanks to their proven proficiency in code comprehension. The primary objective of most revi…
TombRaider: Entering the Vault of History to Jailbreak Large Language Models
Junchen Ding, Jiahao Zhang, Yi Liu +3
Warning: This paper contains content that may involve potentially harmful behaviours, discussed strictly for research purposes. Jailbreak attacks can hinder the safety of Large Lan…
EnJa: Ensemble Jailbreak on Large Language Models
Jiahao Zhang, Zilong Wang, Ruofan Wang +2
As Large Language Models (LLMs) are increasingly being deployed in safety-critical applications, their vulnerability to potential jailbreaks -- malicious prompts that can disable t…