1 citations · 1 across the 13 of their papers we have counts for
16 papers
MOMAT: Mixture of Multiple Atlases for Low-Power Jailbreak Defense of Quantized LLMs
Boyang Li, Bingyu Shen, Weihao Hong +6
Quantized large language models are increasingly deployed on edge devices for their low latency and energy efficiency. However, model quantization weakens alignment safeguards, lea…
Authorization Closure Graph: Minimal Repair for LLM Agents with Evolving User Instructions
Qingzhuo Wang, CaiYi Wang, Jinglu Meng +4
Tool-using large language model (LLM) agents increasingly perform state-changing actions that require user authorization. Yet existing approaches do not provide a principled mechan…
Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions
Ruiyang Qin, Qingzhuo Wang, Tian Wang +2
The remarkable capabilities of large language models (LLMs) are often undermined by their instability. Even subtle and semantically irrelevant changes in prompts can cause dramatic…
PolySim: Deterministic Polynomial Surrogates for Cross-Modal Retrieval on CiM
Xinzhao Li, Charles Power, Pengyu Ren +10
Cross-modal retrieval on edge devices benefits from probabilistic embeddings that capture semantic uncertainty, but deploying them on compute-in-memory (CiM) hardware remains an op…
Probabilistic Memory for Trustworthy Edge Intelligence
Likai Pei, Jiahao Zheng, Xueji Zhao +9
Probabilistic computation plays an important role in trustworthy edge intelligence to quantify uncertainty, enhance robustness, reconstruct data, and protect privacy, but its adopt…
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
Qingzhuo Wang, Ruiyang Qin, Zhenxin Qin +2
Despite the success of knowledge distillation (KD) in Large Language Models (LLMs), the underlying mechanism behind its efficacy remains unclear. In this paper, we propose a unifie…
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…
Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement
Zhenxin Qin, Qiang Li, Qingzhuo Wang +3
Large Vision-Language Models (LVLMs) have achieved remarkable performance on diverse vision-language tasks. However, LVLMs still suffer from hallucinations, generating text that co…
MorphOPC: Advancing Mask Optimization with Multi-scale Hierarchical Morphological Learning
Yuting Hu, Lei Zhuang, Chen Wang +4
As feature sizes shrink to the nanometer scale, accurately transferring circuit patterns from photomasks to silicon wafers becomes increasingly challenging. Optical proximity corre…
Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection
Xinlei Guan, David Arosemena, Tejaswi Dhandu +7
The rapid growth of generative AI has introduced new challenges in content moderation and digital forensics. In particular, benign AI-generated images can be paired with harmful or…
TME-PSR: Time-aware, Multi-interest, and Explanation Personalization for Sequential Recommendation
Qingzhuo Wang, Leilei Wen, Juntao Chen +4
In this paper, we propose a sequential recommendation model that integrates Time-aware personalization, Multi-interest personalization, and Explanation personalization for Personal…
CQ-CiM: Hardware-Aware Embedding Shaping for Robust CiM-Based Retrieval
Xinzhao Li, Alptekin Vardar, Franz Müller +6
Deploying Retrieval-Augmented Generation (RAG) on edge devices is in high demand, but is hindered by the latency of massive data movement and computation on traditional architectur…
Driving Through Uncertainty: Risk-Averse Control with LLM Commonsense for Autonomous Driving under Perception Deficits
Yuting Hu, Chenhui Xu, Ruiyang Qin +4
Partial perception deficits can compromise autonomous vehicle safety by disrupting environmental understanding. Existing protocols typically default to entirely risk-avoidant actio…
Sub-Sequential Physics-Informed Learning with State Space Model
Chenhui Xu, Dancheng Liu, Yuting Hu +4
Physics-Informed Neural Networks (PINNs) are a kind of deep-learning-based numerical solvers for partial differential equations (PDEs). Existing PINNs often suffer from failure mod…
Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data
Jiajie Li, Brian R Quaranto, Chenhui Xu +5
We present RASO, a foundation model designed to Recognize Any Surgical Object, offering robust open-set recognition capabilities across a broad range of surgical procedures and obj…
NVCiM-PT: An NVCiM-assisted Prompt Tuning Framework for Edge LLMs
Ruiyang Qin, Pengyu Ren, Zheyu Yan +7
Large Language Models (LLMs) deployed on edge devices, known as edge LLMs, need to continuously fine-tune their model parameters from user-generated data under limited resource con…