Viral News

Avoid Wasted Annotation Costs in Open-set Active Learning with Pre-trained Vision-Language Model

Avoid Wasted Annotation Costs in Open-set Active Learning with Pre-trained Vision-Language Model

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol
Read More
Towards Semantic Markup of Mathematical Documents via User Interaction

Towards Semantic Markup of Mathematical Documents via User Interaction

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol
Read More
Your Classifier Can Be Secretly a Likelihood-Based OOD Detector

Your Classifier Can Be Secretly a Likelihood-Based OOD Detector

arXiv:2408.04851v1 Announce Type: new Abstract: The ability to detect out-of-distribution (OOD) inputs is critical to guarantee the reliability of classification models deployed in an open environment. A fundamental challenge in OOD detection is that a discriminative classifier is typically trained to estimate the posterior probability p(y|z) for class y given an input z, but lacks the explicit likelihood estimation of p(z) ideally needed for OOD detection. While numerous OOD scoring functions have been proposed for classification models, these estimate scores are often heuristic-driven and cannot be rigorously interpreted as likelihood. To bridge the gap, we propose Intrinsic Likelihood (INK), which…
Read More
GuidedNet: Semi-Supervised Multi-Organ Segmentation via Labeled Data Guide Unlabeled Data

GuidedNet: Semi-Supervised Multi-Organ Segmentation via Labeled Data Guide Unlabeled Data

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol
Read More
Strong and weak alignment of large language models with human values

Strong and weak alignment of large language models with human values

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol
Read More
Why Keeping Humans in the Loop Is Critical for Trustworthy AI

Why Keeping Humans in the Loop Is Critical for Trustworthy AI

(solarseven/Shutterstock) As the global generative AI rollout unfolds, companies are grappling with a host of ethical and governance concerns: Should my employees fear for their jobs? How do I ensure the AI models are adequately and transparently trained? What do I do about hallucinations and toxicity? While it’s not a silver bullet, keeping humans in the AI loop is a good way to address a decent cross-section of AI worries. It’s remarkable how much progress has been made in generative AI since OpenAI shocked the world with the launch of ChatGPT just a year-and-a-half ago. While other AI trends have…
Read More
MDS-GNN: A Mutual Dual-Stream Graph Neural Network on Graphs with Incomplete Features and Structure

MDS-GNN: A Mutual Dual-Stream Graph Neural Network on Graphs with Incomplete Features and Structure

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol
Read More
Clustering-friendly Representation Learning for Enhancing Salient Features

Clustering-friendly Representation Learning for Enhancing Salient Features

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol
Read More
Batching BPE Tokenization Merges

Batching BPE Tokenization Merges

arXiv:2408.04653v1 Announce Type: new Abstract: The Byte Pair Encoding algorithm can be safely batched to merge hundreds of pairs of tokens at a time when building up a tokenizer's vocabulary. This technique combined with reducing the memory footprint of text used in vocabulary training make it feasible to train a high quality tokenizer on a basic laptop. This paper presents BatchBPE, an open-source pure Python implementation of these concepts, with the goal of making experimenting with new tokenization strategies more accessible especially in compute- and memory-constrained contexts. BatchBPE's usefulness and malleability are demonstrated through the training of several token vocabularies…
Read More
Long Context RAG Performance of LLMs

Long Context RAG Performance of LLMs

Retrieval Augmented Generation (RAG) is  the most widely adopted generative AI use case among our customers. RAG enhances the accuracy of LLMs by retrieving information from external sources such as unstructured documents or structured data.  With the availability of LLMs with longer context lengths like Anthropic Claude (200k context length), GPT-4-turbo (128k context length) and Google Gemini 1.5 pro (2 million context length), LLM app developers are able to feed more documents into their RAG applications. Taking longer context lengths to the extreme, there is even a debate about whether long context language models will eventually subsume RAG workflows. Why…
Read More
No widgets found. Go to Widget page and add the widget in Offcanvas Sidebar Widget Area.