10 papers
Trustworthy Agentic AI Requires Deterministic Architectural Boundaries
Manish Bhattarai, Minh Vu
Current agentic AI architectures are fundamentally incompatible with the security and epistemological requirements of high-stakes scientific workflows. The problem is not inadequat…
Mutual Information Collapse Explains Disentanglement Failure in -VAEs
Minh Vu, Xiaoliang Wan, Shuangqing Wei
The -VAE is a foundational framework for unsupervised disentanglement, using to regulate the trade-off between latent factorization and reconstruction fidelity. Empiricall…
Privacy Enhanced PEFT: Tensor Train Decomposition Improves Privacy Utility Tradeoffs under DP-SGD
Pradip Kunwar, Minh Vu, Maanak Gupta +1
Fine-tuning large language models on sensitive data poses significant privacy risks, as membership inference attacks can reveal whether individual records were used during training…
PAS : Prelim Attention Score for Detecting Object Hallucinations in Large Vision--Language Models
Nhat Hoang-Xuan, Minh Vu, My T. Thai +1
Large vision-language models (LVLMs) are powerful, yet they remain unreliable due to object hallucinations. In this work, we show that in many hallucinatory predictions the LVLM ef…
MTRE: Multi-Token Reliability Estimation for Hallucination Detection in VLMs
Geigh Zollicoffer, Minh Vu, Manish Bhattarai
Vision-language models (VLMs) now rival human performance on many multimodal tasks, yet they still hallucinate objects or generate unsafe text. Current hallucination detectors, e.g…
HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling
Minh Vu, Brian K. Tran, Syed A. Shah +3
Large Language Models (LLMs) exhibit impressive reasoning and question-answering capabilities. However, they often produce inaccurate or unreliable content known as hallucinations.…