This tutorial provides comprehensive lecture notes on regression analysis, covering fundamental concepts from linear models to deep learning. It aims to equip students with a solid understanding of various regression models, including linear, logistic, and Softmax regression, along with essential methodologies like loss function design, parameter estimation, and regularization techniques, bridging classical statistics and modern machine learning practices.

DraCo introduces a novel interleaved reasoning paradigm, Draft-as-CoT, for text-to-image generation that leverages both textual and visual content. This approach addresses limitations of existing methods by generating low-resolution draft images for visual planning and verification, significantly improving the generation of rare attribute combinations and overall image quality.

This paper introduces CaFTRA, a framework for 6G wireless systems that eliminates real-time channel state information (CSI) feedback in MIMO transmission by predicting CSI from user geolocation using a Transformer network. It also proposes a many-to-one matching algorithm for efficient multi-base station (BS) association and resource block (RB) allocation in fully-decoupled radio access networks (FD-RAN), demonstrating significant improvements in spectral efficiency and user fairness compared to 5G.

This paper introduces Object-based Set Similarity (OSS), a novel metric designed to address computational costs and unreliable evaluations in active learning for real-world object detection. OSS quantifies active learning method effectiveness without requiring extensive detector training and improves evaluation robustness by identifying representative validation sets.

This paper explores using large language models (LLMs) to automate financial statement auditing, addressing inefficiencies and errors in current manual processes. It introduces a comprehensive benchmark and a five-stage evaluation framework to assess LLMs' capabilities in detecting and resolving financial statement errors.