16 citations · 17 across the 8 of their papers we have counts for
8 papers
Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
Mengxuan Hu, Vivek V. Datla, Anoop Kumar +4
Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have impro…
Enhanced Diagnostic Performance via Large-Resolution Inference Optimization for Pathology Foundation Models
Mengxuan Hu, Zihan Guan, John Kang +2
Despite their prominent performance on tasks such as ROI classification and segmentation, many pathology foundation models remain constrained by a specific input size e.g. 224 x 22…
BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing
Dongliang Guo, Mengxuan Hu, Zihan Guan +2
Large multi-modal models inevitably decay over time as facts update and previously learned information becomes outdated. Traditional approaches such as fine-tuning are often imprac…
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
Zihan Guan, Mengxuan Hu, Ronghang Zhu +2
Recent studies have uncovered a troubling vulnerability in the fine-tuning stage of large language models (LLMs): even fine-tuning on entirely benign datasets can lead to a signifi…
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing
Dongliang Guo, Mengxuan Hu, Zihan Guan +3
Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ( backdo…
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
Mengxuan Hu, Hongyi Wu, Zihan Guan +4
Retrieval-Augmented Generation (RAG) is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations and enhancing the domain-specific generation capabilit…
UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models
Zihan Guan, Mengxuan Hu, Sheng Li +1
Diffusion models are vulnerable to backdoor attacks, where malicious attackers inject backdoors by poisoning certain training samples during the training stage. This poses a signif…
Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation
Zhongliang Zhou, Jielu Zhang, Zihan Guan +5
Geolocating precise locations from images presents a challenging problem in computer vision and information retrieval.Traditional methods typically employ either classification, wh…