2 citations · 6 across the 37 of their papers we have counts for
42 papers
ARIA: Runtime Inspection and Amendment for Multi-Agent Systems
Bolin Shen, Yushun Dong
In LLM-based multi-agent systems (MAS), a local mistake can propagate as other agents build on it, turning a correctable error into a failed task. Diagnosing completed runs or repe…
Phantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another
Wangshu Zhu, Qianwen Guo, Yushun Dong
LLM agents increasingly operate over multiple entities, where reliable response generation requires not only retrieving relevant evidence but also preserving its association with t…
HazardWeaver: Scientific Route Selection for Hazard Analysis Agents
Wangshu Zhu, Xueqi Cheng, Liang Wu +1
Understanding and assessing natural hazards is essential for disaster preparedness and risk reduction. Recent advances in large language models have spurred growing interest in AI…
Capability Scaling-Down Laws for LLM Compression
Xueqi Cheng, Liang Wu, Kelly Wan +2
LLM compression reduces inference costs and memory requirements, but selecting a method and configuration remains largely empirical because comparable resource reductions can produ…
Do Defenses Against LLM Extraction Work Across Attacks? A Lifecycle Benchmark of Black-Box Model Extraction
Shuze Liu, Kaixiang Zhao, Runyang Xu +4
Large language models (LLMs) deployed through text-only APIs face model extraction risks, as adversaries can collect their responses to train surrogates that reproduce their capabi…
Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards
Xi Li, Shu Zhao, Xiaohan Zou +6
Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning. However, this arc…
SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents
Tianming Sha, Yue Zhao, Lichao Sun +1
Autonomous AI agents can execute complex tasks with limited human review, yet they often lack the grounded operational knowledge to make their outputs not just executable but corre…
AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network
Bolin Shen, Ziwei Huang, Zhiguang Cao +1
The Traveling Salesman Problem (TSP) is a cornerstone of combinatorial optimization and arises in many practical scenarios. Although graph-based learning approaches have been explo…
A Nationwide Benchmark for Wildfire Initial Attack Failure Prediction with Public Environmental Data
Runyang Xu, Xueqi Cheng, Yushun Dong
Initial attack (IA) is the first wildfire suppression phase, when agencies must quickly decide which fires may escape early control. Existing IA failure prediction studies often us…
EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering
Xiaopeng Yuan, Zebin Wang, Suwen Wang +3
Long-context question answering (QA) remains challenging for smaller language models even when answer-bearing evidence is already present in the input. Existing within-context retr…
Closing the Loop on Latent Reasoning via Test-Time Reconstruction
Xiaopeng Yuan, Haibo Jin, Ye Yu +4
Recent work moves intermediate reasoning from natural-language traces into latent or cache-level representations to reduce token overhead and avoid a discrete communication bottlen…
Let Them Steal: Trapping Large Language Model Extraction Attacks with Knowledge Honeypot
Yuyang Dai, Yushun Dong
Large language models deployed as commercial APIs are vulnerable to model extraction attacks, while existing defenses either act too late or degrade utility for legitimate users. W…
An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic
Shuze Liu, Qianwen Guo, Yushun Dong
Large language models (LLMs) are increasingly deployed through hosted APIs, making model extraction a practical threat to model ownership and service security. Individual extractio…
Self-Correction Can Amplify Hallucinations: Fact-Level Repair with Graph-Based Evidence Routing in Multimodal Generation
Kaixiang Zhao, Tianrun Yu, Shawn Huang +3
We study fact-level repair for multimodal generation, where a fluent output may contain specific facts that are not supported by the input. Existing inference-time repair methods o…
GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
Kaixiang Zhao, Bolin Shen, Yuyang Dai +2
Graph neural networks (GNNs) deployed as cloud services can be stolen through model-extraction attacks, which train a surrogate from query responses to reproduce the target's behav…
EpiGraph: Building Generalists for Evidence-Intensive Epilepsy Reasoning in the Wild
Yuyang Dai, Zheng Chen, Jathurshan Pradeepkumar +4
Epilepsy diagnosis and treatment require evidence-intensive reasoning across heterogeneous clinical knowledge, including biosignal patterns, genetic mechanisms, pharmacogenomics, t…
SOMA: Efficient Multi-turn LLM Serving via Small Language Model
Xueqi Cheng, Qiong Wu, Zhengyi Zhou +3
Large Language Models (LLMs) are increasingly deployed in multi-turn dialogue settings where preserving conversational context across turns is essential. A standard serving practic…
LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?
Xueqi Cheng, Yushun Dong
Multimodal large language models (MLLMs) have heterogeneous strengths across OCR, chart understanding, spatial reasoning, visual question answering, cost, and latency. Effective ML…
ReAD: Reinforcement-Guided Capability Distillation for Large Language Models
Xueqi Cheng, Xugui Zhou, Tyler Derr +1
Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller one while preserving the abili…
An Analysis of Active Learning Algorithms using Real-World Crowd-sourced Text Annotations
Varun Totakura, Ankita Singh, Yushun Dong +1
Active learning algorithms automatically identify the most informative samples from large amounts of unlabeled data and tremendously reduce human annotation effort in inducing a ma…
CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks
Bolin Shen, Zhan Cheng, Neil Zhenqiang Gong +2
Machine Learning as a Service (MLaaS) has emerged as a widely adopted paradigm for providing access to deep neural network (DNN) models, enabling users to conveniently leverage the…
CITED: A Decision Boundary-Aware Signature for GNNs Towards Model Extraction Defense
Bolin Shen, Md Shamim Seraj, Zhan Cheng +2
Graph neural networks (GNNs) have demonstrated superior performance in various applications, such as recommendation systems and financial risk management. However, deploying large-…
Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
Zhisheng Qi, Utkarsh Sahu, Li Ma +9
Retrieval-Augmented Generation (RAG) has become a cornerstone of knowledge-intensive applications, including enterprise chatbots, healthcare assistants, and agentic memory manageme…
From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges
Yihan Hong, Huaiyuan Yao, Bolin Shen +3
Rubric-based text evaluation increasingly relies on large language models (LLMs) as scalable judges, yet frozen black-box models can interpret the same criteria inconsistently, pro…