↓Skip to main content

🏢 University of Minnesota

Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor
·1554 words·8 mins· loading · loading
Computer Vision 3D Vision 🏢 University of Minnesota
Low-rank block trifocal tensor unlocks accurate, efficient camera pose synchronization.
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
·2208 words·11 mins· loading · loading
Computer Vision Image Generation 🏢 University of Minnesota
RAW: A novel watermark framework ensures the authenticity of AI-generated images by embedding learnable watermarks directly into the image data, providing provable guarantees even under adversarial at…
Meta-Learning Universal Priors Using Non-Injective Change of Variables
·2169 words·11 mins· loading · loading
AI Generated Machine Learning Meta Learning 🏢 University of Minnesota
MetaNCoV: Learn data-driven priors via non-injective change of variables for enhanced few-shot learning.
MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
·2015 words·10 mins· loading · loading
Natural Language Processing Large Language Models 🏢 University of Minnesota
Multi-Agent System for Condition Mining (MACM) dramatically boosts large language model accuracy in complex math problem-solving, exceeding existing methods by achieving higher accuracy and better gen…
Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment
·1742 words·9 mins· loading · loading
Natural Language Processing Large Language Models 🏢 University of Minnesota
Reward learning from human demonstrations enhances supervised fine-tuning (SFT) for better LLM alignment.
Coded Computing for Resilient Distributed Computing: A Learning-Theoretic Framework
·2345 words·12 mins· loading · loading
AI Generated AI Theory Optimization 🏢 University of Minnesota
LeTCC: A novel learning-theoretic framework for resilient distributed computing, achieving faster convergence and higher accuracy than existing methods by integrating learning theory principles with c…