1 citations · 2 across the 12 of their papers we have counts for
15 papers
Inner Momentum for Differentially Private Muon
Bishnu Bhusal, Minh Vu, Ben Southworth +3
Differentially private training clips each per-example gradient before adding noise. This clipping is radial for each example, yet unequal clipping factors can distort the relative…
One Model, Two Physical Stories: Auditing Misalignment in Multi-Modal World Modeling
Geigh Zollicoffer, Minh Vu, Rajiv Ranasinghe +1
World models, systems that generate what happens next given current environmental conditions, are increasingly being implemented with multi-modal generation in mind. However, gener…
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. Empirically,…
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…
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.…
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…
ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement
Manish Bhattarai, Miguel Cordova, Minh Vu +3
We present Agentic Retrieval-Augmented Code Synthesis (ARCS), a system that improves LLM-based code generation without fine-tuning. ARCS operates through a budgeted synthesize-exec…
Topological Signatures of Adversaries in Multimodal Alignments
Minh Vu, Geigh Zollicoffer, Huy Mai +3
Multimodal Machine Learning systems, particularly those aligning text and image data like CLIP/BLIP models, have become increasingly prevalent, yet remain susceptible to adversaria…
Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty
Roman Colman, Minh Vu, Manish Bhattarai +4
For decades, corporations and governments have relied on scanned documents to record vast amounts of information. However, extracting this information is a slow and tedious process…
Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation
Manish Bhattarai, Minh Vu, Javier E. Santos +2
We introduce a novel method to enhance cross-language code translation from Fortran to C++ by integrating task-specific embedding alignment into a Retrieval-Augmented Generation (R…
HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation Learning
Manish Bhattarai, Ryan Barron, Maksim Eren +8
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external document retrieval to provide domain-specific or up-to-date knowledge. The effect…
LoRID: Low-Rank Iterative Diffusion for Adversarial Purification
Geigh Zollicoffer, Minh Vu, Ben Nebgen +3
This work presents an information-theoretic examination of diffusion-based purification methods, the state-of-the-art adversarial defenses that utilize diffusion models to remove m…
LaFA: Latent Feature Attacks on Non-negative Matrix Factorization
Minh Vu, Ben Nebgen, Erik Skau +5
As Machine Learning (ML) applications rapidly grow, concerns about adversarial attacks compromising their reliability have gained significant attention. One unsupervised ML method…