papers

Publications (31)

cs.CR2025

POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models

Yangguang Shao, Xinjie Lin, Haozheng Luo +4

Large language models (LLMs) have achieved remarkable success in various domains, primarily due to their strong capabilities in reasoning and generating human-like text. Despite th…

cs.CR2026

ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attack

Xingwei Lin, Wenhao Lin, Sicong Cao +4

Multi-turn jailbreak attacks have emerged as a critical threat to Large Language Models (LLMs), bypassing safety mechanisms by progressively constructing adversarial contexts from…

cs.AI2026

Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization

Jiahao Yu, Zelei Cheng, Xian Wu +1

Software engineering presents complex, multi-step challenges for Large Language Models (LLMs), requiring reasoning over large codebases and coordinated tool use. The difficulty of…

cs.CR2025

Locus: Agentic Predicate Synthesis for Directed Fuzzing

Jie Zhu, Chihao Shen, Ziyang Li +3

Directed fuzzing aims to find program inputs that lead to specified target program states. It has broad applications, such as debugging system crashes, confirming reported bugs, an…

cs.CV2024

T-CorresNet: Template Guided 3D Point Cloud Completion with Correspondence Pooling Query Generation Strategy

Fan Duan, Jiahao Yu, Li Chen

Point clouds are commonly used in various practical applications such as autonomous driving and the manufacturing industry. However, these point clouds often suffer from incomplete…

cs.CL2026

Decoupled Alignment for Robust Plug-and-Play Adaptation

Haozheng Luo, Jiahao Yu, Wenxin Zhang +9

The paper proposes a training-free, plug-and-play method that uses knowledge distillation and model fusion to correct misaligned (shadow-aligned) large language models, improving s…

#large language models#model alignment#plug-and-play adaptation#knowledge distillation
cs.CR2025

UTF:Undertrained Tokens as Fingerprints A Novel Approach to LLM Identification

Jiacheng Cai, Jiahao Yu, Yangguang Shao +1

Fingerprinting large language models (LLMs) is essential for verifying model ownership, ensuring authenticity, and preventing misuse. Traditional fingerprinting methods often requi…

cs.CL2025

The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)

Zihao Wang, Yibo Jiang, Jiahao Yu +1

Large language models (LLMs) that integrate multiple input roles (e.g., system instructions, user queries, external tool outputs) are increasingly prevalent in practice. Ensuring t…

cs.IR2024

DSFNet: Learning Disentangled Scenario Factorization for Multi-Scenario Route Ranking

Jiahao Yu, Yihai Duan, Longfei Xu +6

Multi-scenario route ranking (MSRR) is crucial in many industrial mapping systems. However, the industrial community mainly adopts interactive interfaces to encourage users to sele…

cs.CR2024

Assessing Prompt Injection Risks in 200+ Custom GPTs

Jiahao Yu, Yuhang Wu, Dong Shu +3

In the rapidly evolving landscape of artificial intelligence, ChatGPT has been widely used in various applications. The new feature - customization of ChatGPT models by users to ca…

cs.IR2025

TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems

Jiahao Yu, Haozhuang Liu, Yeqiu Yang +4

Regression models are crucial in recommender systems. However, retransformation bias problem has been conspicuously neglected within the community. While many works in other fields…

cs.CR2025

PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs

Jiahao Yu, Yangguang Shao, Hanwen Miao +1

Large Language Models (LLMs) have gained widespread use in various applications due to their powerful capability to generate human-like text. However, prompt injection attacks, whi…

cs.CR2025

BlockScan: Detecting Anomalies in Blockchain Transactions

Jiahao Yu, Xian Wu, Hao Liu +2

We propose BlockScan, a customized Transformer for anomaly detection in blockchain transactions. Unlike existing methods that rely on rule-based systems or directly apply off-the-s…

cs.LG2025

A Survey on Explainable Deep Reinforcement Learning

Zelei Cheng, Jiahao Yu, Xinyu Xing

Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making tasks across diverse domains, yet its reliance on black-box neural architectures hin…

cs.LG2025

GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models

Haozheng Luo, Chenghao Qiu, Yimin Wang +9

We propose the first unified adversarial attack benchmark for Genomic Foundation Models (GFMs), named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first compre…

cs.IR2023

Toward Trustworthy Identity Tracing via Multi-attribute Synergistic Identification

Decheng Liu, Jiahao Yu, Ruimin Hu +1

Identity tracing is a technology that uses the selection and collection of identity attributes of the object to be tested to discover its true identity, and it is one of the most i…

cs.AI2024

Soft-Label Integration for Robust Toxicity Classification

Zelei Cheng, Xian Wu, Jiahao Yu +3

Toxicity classification in textual content remains a significant problem. Data with labels from a single annotator fall short of capturing the diversity of human perspectives. Ther…

stat.ML2024

Minimizing -Divergences by Interpolating Velocity Fields

Song Liu, Jiahao Yu, Jack Simons +2

Many machine learning problems can be seen as approximating a \textit{target} distribution using a \textit{particle} distribution by minimizing their statistical discrepancy. Wasse…

stat.ML2025

Missing Data Imputation by Reducing Mutual Information with Rectified Flows

Jiahao Yu, Qizhen Ying, Leyang Wang +2

This paper introduces a novel iterative method for missing data imputation that sequentially reduces the mutual information between data and the corresponding missingness mask. Ins…

cs.IR2025

ReaSeq: Unleashing World Knowledge via Reasoning for Sequential Modeling

Jiakai Tang, Chuan Wang, Gaoming Yang +31

Industrial recommender systems face two fundamental limitations under the log-driven paradigm: (1) knowledge poverty in ID-based item representations that causes brittle interest m…

cs.AI2024

GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Jiahao Yu, Xingwei Lin, Zheng Yu +1

Large language models (LLMs) have recently experienced tremendous popularity and are widely used from casual conversations to AI-driven programming. However, despite their consider…

cs.AI2026

GPO: Learning from Critical Steps to Improve LLM Reasoning

Jiahao Yu, Zelei Cheng, Xian Wu +1

Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks. Recently, reasoning LLMs have been proposed to improve the \…

cs.LG2022

Hybrid CNN -Interpreter: Interpret local and global contexts for CNN-based Models

Wenli Yang, Guan Huang, Renjie Li +4

Convolutional neural network (CNN) models have seen advanced improvements in performance in various domains, but lack of interpretability is a major barrier to assurance and regula…

cs.AI2025

Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries

Jiahao Yu, Haozheng Luo, Jerry Yao-Chieh Hu +3

Recent advances in Large Language Models (LLMs) have led to impressive alignment where models learn to distinguish harmful from harmless queries through supervised finetuning (SFT)…

cs.LG2024

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation

Zelei Cheng, Xian Wu, Jiahao Yu +3

Deep reinforcement learning (DRL) is playing an increasingly important role in real-world applications. However, obtaining an optimally performing DRL agent for complex tasks, espe…

cs.AI2026

Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations

Haozheng Luo, Yimin Wang, Jiahao Yu +2

We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike p…

cs.CV2021

Aesthetic Photo Collage with Deep Reinforcement Learning

Mingrui Zhang, Mading Li, Li Chen +1

Photo collage aims to automatically arrange multiple photos on a given canvas with high aesthetic quality. Existing methods are based mainly on handcrafted feature optimization, wh…

eess.SY2024

Quad: Adaptive Augmentation of Geometric Control for Agile Quadrotors with Performance Guarantees

Zhuohuan Wu, Sheng Cheng, Pan Zhao +6

Quadrotors that can operate predictably in the presence of imperfect model knowledge and external disturbances are crucial in safety-critical applications. We present L1Quad, a con…

cs.CV2024

Q2A: Querying Implicit Fully Continuous Feature Pyramid to Align Features for Medical Image Segmentation

Jiahao Yu, Li Chen

Recent medical image segmentation methods apply implicit neural representation (INR) to the decoder for achieving a continuous coordinate decoding to tackle the drawback of convent…

cs.CL2026

CSCBench: A PVC Diagnostic Benchmark for Commodity Supply Chain Reasoning

Yaxin Cui, Yuanqiang Zeng, Jiapeng Yan +8

Large Language Models (LLMs) have achieved remarkable success in general benchmarks, yet their competence in commodity supply chains (CSCs) -- a domain governed by institutional ru…

cs.CR2025

BandFuzz: An ML-powered Collaborative Fuzzing Framework

Wenxuan Shi, Hongwei Li, Jiahao Yu +3

Collaborative fuzzing combines multiple individual fuzzers and dynamically chooses appropriate combinations for different programs. Unlike individual fuzzers that rely on specific…