Human-in-the-Loop Mixup: Aligning Synthetic Data with Human Perception - Oral Session 2
Explore human-aligned synthetic data in machine learning, focusing on mixup regularization. Discover how perceptual judgments and uncertainties can enhance model reliability and generalization.
MixupE: Understanding and Improving Mixup from Directional Derivative Perspective - Oral Session 1
Explore MixupE, an improved data augmentation technique for deep neural networks. Gain insights into its theoretical foundations and practical applications across various domains.
RouteLLM - Learning to Route Large Language Models with Preference Data
Optimize LLM deployment with dynamic routing, balancing cost and performance. Learn to train routers using preference data, achieving significant cost reduction while maintaining quality responses.
Fine-Tuning Large Language Models Faster Using Bonito for Task-Specific Training Data Generation
Accelerate LLM fine-tuning with Bonito: Generate task-specific training data for faster instruction tuning and improved zero-shot task adaptation on specialized, private datasets.
Tune in and Dropout - How Data Augmentation Can Help Us Build Better Brain Decoders
Explore data augmentation techniques for improving brain decoders, enhancing neural signal interpretation and brain-computer interface performance.
Tuning Foundation Models: A Comprehensive Guide
Explore techniques for customizing foundation models with your data, improving performance across tasks while understanding limitations and future prospects.
Secure Self-supervised Learning: Challenges and Solutions
Explore secure self-supervised learning techniques, focusing on backdoor attacks, data auditing, and membership inference for pre-trained encoders in machine learning.
Leaf Tracking, Counting and Occlusion in Plants Using Artificial Neural Networks
Discover how to implement artificial neural networks for plant leaf analysis, including tracking, counting, and handling occlusion through advanced image processing techniques.
Creating a Bernie Sanders Detector Using YOLOv4 - OpenCV Python - Computer Vision
Learn to create a Bernie Sanders detector using YOLOv4/v5, OpenCV, and Roboflow. Build datasets, train models, and implement real-time detection on various platforms.
OpenCV AI Kit Raspberry Pi Smart Camera - OpenCV Python - Computer Vision - 2021
Build a real-time AI surveillance camera using Raspberry Pi and OpenCV AI Kit. Detect objects, people, and packages with MobileNet SSD at 30 FPS. Includes hardware setup, coding, and Roboflow integration for custom object detection.