109 citations · 182 across the 20 of their papers we have counts for
21 papers
CARET: Training-Free Test-Time Scaling for Repository-Level Code Completion
Jiajie Wang, Yutong Zhao, Kebin Peng +3
Retrieval-augmented generation (RAG) dominates repository-level code completion: it retrieves cross-file context (R), then decodes one greedy completion (G). Existing work mainly f…
Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding
Yisong Xiao, Aishan Liu, Yongxin Huang +6
Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases from their training data, resultin…
Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms
Xianzong Wu, Xiaohong Li, Yuejun Guo +4
Prediction uncertainty is a widely adopted metric for quantifying model confidence, with downstream applications spanning model explanation, data selection, and prediction rollback…
GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety Logic
Tianyuan Zhang, Peng Yue, Zihao Peng +8
Multimodal large language models (MLLMs) are increasingly integrated into autonomous driving (AD) systems; however, they remain vulnerable to diverse safety threats, particularly i…
Ensemble-Based Uncertainty Estimation for Code Correctness Estimation
Yunxiang Wei, Tianlin Li, Yuwei Zheng +6
Large language models (LLMs) have demonstrated remarkable capabilities in generating programs from natural language descriptions, yet ensuring their correctness without an external…
Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw
Zonghao Ying, Xiao Yang, Siyang Wu +7
The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI sy…
KernelClaw: A Multi-Agent Framework for GPU Kernel Optimization with Dual-Memory Mechanisms
Qitong Sun, Jun Han, Tianlin Li +6
Improving GPU kernel efficiency is crucial for efficient AI systems. Recent work has explored leveraging large language models (LLMs) for GPU kernel generation and optimization. Ho…
RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
Le Wang, Zonghao Ying, Xiao Yang +7
Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks, yet they remain vulnerable to hazardous instructions that m…
CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge Transfer
Kaixin Wang, Tianlin Li, Xiaoyu Zhang +6
Code Large Language Models (CodeLLMs) have been widely adopted for Natural Language to Programming Language code generation, powering applications with large user bases. Their perf…
MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair
Changqing Li, Tianlin Li, Xiaohan Zhang +2
Large Language Models (LLMs) face persistent and evolving trustworthiness issues, motivating developers to seek automated and flexible repair methods that enable convenient deploym…
From Context to Intent: Reasoning-Guided Function-Level Code Completion
Yanzhou Li, Tianlin Li, Yiran Zhang +4
The growing capabilities of Large Language Models (LLMs) have led to their widespread adoption for function completion within code repositories. Recent studies on such tasks show p…
BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks
Yisong Xiao, Aishan Liu, Xinwei Zhang +6
Pre-trained large deep learning models are now serving as the dominant component for downstream middleware users and have revolutionized the learning paradigm, replacing the tradit…
Compromising Embodied Agents with Contextual Backdoor Attacks
Aishan Liu, Yuguang Zhou, Xianglong Liu +9
Large language models (LLMs) have transformed the development of embodied intelligence. By providing a few contextual demonstrations, developers can utilize the extensive internal…
IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
Yue Cao, Tianlin Li, Xiaofeng Cao +3
We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene…
FAIRER: Fairness as Decision Rationale Alignment
Tianlin Li, Qing Guo, Aishan Liu +3
Deep neural networks (DNNs) have made significant progress, but often suffer from fairness issues, as deep models typically show distinct accuracy differences among certain subgrou…
On the Robustness of Segment Anything
Yihao Huang, Yue Cao, Tianlin Li +5
Segment anything model (SAM) has presented impressive objectness identification capability with the idea of prompt learning and a new collected large-scale dataset. Given a prompt…
Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing
Yisong Xiao, Aishan Liu, Tianlin Li +1
Machine learning (ML) systems have achieved remarkable performance across a wide area of applications. However, they frequently exhibit unfair behaviors in sensitive application do…
NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks
Xiaofei Xie, Tianlin Li, Jian Wang +4
Deep learning has recently been widely applied to many applications across different domains, e.g., image classification and audio recognition. However, the quality of Deep Neural…
Unveiling Project-Specific Bias in Neural Code Models
Zhiming Li, Yanzhou Li, Tianlin Li +5
Deep learning has introduced significant improvements in many software analysis tasks. Although the Large Language Models (LLMs) based neural code models demonstrate commendable pe…
Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
Chongzhi Zhang, Aishan Liu, Xianglong Liu +4
Deep neural networks (DNNs) are vulnerable to adversarial examples where inputs with imperceptible perturbations mislead DNNs to incorrect results. Despite the potential risk they…
Knowledge Consistency between Neural Networks and Beyond
Ruofan Liang, Tianlin Li, Longfei Li +2
This paper aims to analyze knowledge consistency between pre-trained deep neural networks. We propose a generic definition for knowledge consistency between neural networks at diff…