A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Rabeeh Karimi Mahabadi, Yonatan Belinkov, James Henderson
Proposes two learning strategies to train neural models that are more robust to dataset biases and transfer better to out-of-domain datasets.
Evan Shelhamer, Jonathan Long, Trevor Darrell
Fully convolutional networks trained end-to-end for semantic segmentation achieve state-of-the-art results by adapting classification nets and using a skip architecture for detailed predictions.
Iulian Vlad Serban, Alessandro Sordoni, Yoshua Bengio, et al.
Extends hierarchical recurrent encoder-decoder networks to open-domain dialogue, showing competitiveness with n-gram models and improvement via bootstrapping from QA pairs and pretrained embeddings.
Unknown
SmolDocling introduces a compact 256M parameter model for end-to-end document conversion using a novel DocTags markup format.
Unknown
An end-to-end deep learning model for simultaneous table detection and structure recognition in documents.
Unknown
LLaVA connects CLIP and Vicuna via end-to-end training on GPT-4-generated instruction-following data from image-text pairs.
Xiao Yu, Baolin Peng, Ruize Xu, et al.
OpenForgeRL is an open-source framework that enables end-to-end training of harness-based AI agents in any environment by decoupling training and inference via a lightweight proxy and Kubernetes orchestrator.
Ruikang Li, Molin Li, Jiarui Wu, et al.
Proposes Color Pass-Through, an end-to-end learned framework that couples camera and display as a single system to improve color reproduction accuracy.
Unknown
M4-RAG is an evaluation framework for multilingual, multicultural, and multimodal RAG that focuses on end-to-end task performance and systematic failure analysis.
Hanyu Lai, Xiao Liu, Yanxiao Zhao, et al.
This paper scales end-to-end online reinforcement learning for computer use agents using distributed VM clusters.
Vikas Hassija, Vinay Chamola, Vikas Saxena, et al.
This survey reviews IoT security challenges and solutions, focusing on blockchain, fog computing, edge computing, and machine learning to achieve end-to-end secure IoT environments.
Eva McCord, Ernest Pedapati, Zag ElSayed
A HIPAA-compliant, AI-augmented LIMS architecture using finite-state workflow models and automated QC pre-screening to optimize clinical assay workflows.