1 citations · 4 across the 12 of their papers we have counts for
16 papers
Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory
Luoxi Tang, Yuqiao Meng, Nilesh Auradkar +3
Agentic memory allows LLM agents to reuse past experience, yet retrieved memories can also distort inference even when they are benign, correctly stored, and appropriately retrieve…
Polar: LLM-Powered Synthesis of Real-World Cyber Evidence for Prioritization and Mitigation
Luoxi Tang, Yuqiao Meng, Ankita Patra +3
Cyber threat analysis increasingly depends on evidence distributed across vendor advisories, vulnerability databases, and threat intelligence sources. Turning these fragmented obse…
MemFit: Efficient Long-Term Agentic Memory
Mitchell Piehl, Muchao Ye
Long-term memory systems for large language models (LLMs) have gained popularity for extending reasoning capabilities across applications. Current memory systems rely on LLM agents…
Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs
Xi Xiao, Chen Liu, Chih-Ting Liao +9
Multimodal large language models (MLLMs) extend large language models (LLMs) with visual perception, enabling joint reasoning over images and text. Despite inheriting strong reason…
LATERN: Test-Time Context-Aware Explainable Video Anomaly Detection
Mitchell Piehl, Muchao Ye
Vision-language models (VLMs) have recently emerged as a promising paradigm for video anomaly detection (VAD) due to their strong visual reasoning ability and natural language-base…
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
Yuqiao Meng, Sakshi Sunil Narvekar, Luoxi Tang +4
Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning, but this convenience opens a critical vulnerability: a single corrupted entry…
OracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal Control
Darryl Jacob, Xinyu Liu, Muchao Ye +2
Transparent decision-making is essential for traffic signal control (TSC) systems to earn public trust. However, traditional reinforcement learning-based TSC methods function as bl…
ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models
Mitchell Piehl, Zhaohan Xi, Zuobin Xiong +2
Large language models (LLMs) are increasingly augmented with long-term memory systems to overcome finite context windows and enable persistent reasoning across interactions. Howeve…
Understanding Real-World Traffic Safety through RoadSafe365 Benchmark
Xinyu Liu, Darryl C. Jacob, Yuxin Liu +4
Although recent traffic benchmarks have advanced multimodal data analysis, they generally lack systematic evaluation aligned with official safety standards. To fill this gap, we in…
The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization
Luoxi Tang, Yuqiao Meng, Joseph Costa +3
Multi-agent debate (MAD) systems improve LLM reasoning through iterative deliberation, but remain vulnerable to debate collapse, a failure type where final agent decisions are comp…
SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware Learning
Zihao Zhao, Shengting Cao, Muchao Ye
Multi-modal large language models (MLLMs) have demonstrated significant progress in reasoning capabilities and shown promising effectiveness in video anomaly understanding (VAU) ta…
POLAR: Automating Cyber Threat Prioritization through LLM-Powered Assessment
Luoxi Tang, Yuqiao Meng, Ankita Patra +3
Large Language Models (LLMs) are intensively used to assist security analysts in counteracting the rapid exploitation of cyber threats, wherein LLMs offer cyber threat intelligence…
CyLens: Towards Reinventing Cyber Threat Intelligence in the Paradigm of Agentic Large Language Models
Xiaoqun Liu, Jiacheng Liang, Qiben Yan +5
The exponential growth of cyber threat knowledge, exemplified by the expansion of databases such as MITRE-CVE and NVD, poses significant challenges for cyber threat analysis. Secur…
VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models
Muchao Ye, Weiyang Liu, Pan He
The rapid advancement of vision-language models (VLMs) has established a new paradigm in video anomaly detection (VAD): leveraging VLMs to simultaneously detect anomalies and provi…
Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
Xiaoqun Liu, Jiacheng Liang, Luoxi Tang +3
Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerabil…
Robustifying Safety-Aligned Large Language Models through Clean Data Curation
Xiaoqun Liu, Jiacheng Liang, Muchao Ye +1
Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of…