Viral News

Activation Space Selectable Kolmogorov-Arnold Networks

Activation Space Selectable Kolmogorov-Arnold Networks

arXiv:2408.08338v1 Announce Type: new Abstract: The multilayer perceptron (MLP), a fundamental paradigm in current artificial intelligence, is widely applied in fields such as computer vision and natural language processing. However, the recently proposed Kolmogorov-Arnold Network (KAN), based on nonlinear additive connections, has been proven to achieve performance comparable to MLPs with significantly fewer parameters. Despite this potential, the use of a single activation function space results in reduced performance of KAN and related works across different tasks. To address this issue, we propose an activation space Selectable KAN (S-KAN). S-KAN employs an adaptive strategy to choose the possible activation mode…
Read More
5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks

5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks

arXiv:2408.08345v1 Announce Type: new Abstract: Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks. Despite their success, existing visual delta-tuning art fails to exceed the upper limit of full fine-tuning on challenging tasks like object detection and segmentation. To find a competitive alternative to full fine-tuning, we propose the Multi-cognitive Visual Adapter (Mona) tuning, a novel adapter-based tuning method. First, we introduce multiple vision-friendly filters into the adapter to enhance its ability to process visual signals, while previous methods mainly rely on language-friendly linear filters. Second,…
Read More
Zero-Shot Learning and Key Points Are All You Need for Automated Fact-Checking

Zero-Shot Learning and Key Points Are All You Need for Automated Fact-Checking

arXiv:2408.08400v1 Announce Type: new Abstract: Automated fact-checking is an important task because determining the accurate status of a proposed claim within the vast amount of information available online is a critical challenge. This challenge requires robust evaluation to prevent the spread of false information. Modern large language models (LLMs) have demonstrated high capability in performing a diverse range of Natural Language Processing (NLP) tasks. By utilizing proper prompting strategies, their versatility due to their understanding of large context sizes and zero-shot learning ability enables them to simulate human problem-solving intuition and move towards being an alternative to humans for solving…
Read More
Training Large-Scale Optical Neural Networks with Two-Pass Forward Propagation

Training Large-Scale Optical Neural Networks with Two-Pass Forward Propagation

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
TurboEdit: Instant text-based image editing

TurboEdit: Instant text-based image editing

arXiv:2408.08332v1 Announce Type: new Abstract: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text…
Read More
Towards Realistic Synthetic User-Generated Content: A Scaffolding Approach to Generating Online Discussions

Towards Realistic Synthetic User-Generated Content: A Scaffolding Approach to Generating Online Discussions

arXiv:2408.08379v1 Announce Type: new Abstract: The emergence of synthetic data represents a pivotal shift in modern machine learning, offering a solution to satisfy the need for large volumes of data in domains where real data is scarce, highly private, or difficult to obtain. We investigate the feasibility of creating realistic, large-scale synthetic datasets of user-generated content, noting that such content is increasingly prevalent and a source of frequently sought information. Large language models (LLMs) offer a starting point for generating synthetic social media discussion threads, due to their ability to produce diverse responses that typify online interactions. However, as we…
Read More
Graph representations of 3D data for machine learning

Graph representations of 3D data for machine learning

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
Segment Anything for Videos: A Systematic Survey

Segment Anything for Videos: A Systematic Survey

arXiv:2408.08315v1 Announce Type: new Abstract: The recent wave of foundation models has witnessed tremendous success in computer vision (CV) and beyond, with the segment anything model (SAM) having sparked a passion for exploring task-agnostic visual foundation models. Empowered by its remarkable zero-shot generalization, SAM is currently challenging numerous traditional paradigms in CV, delivering extraordinary performance not only in various image segmentation and multi-modal segmentation (eg, text-to-mask) tasks, but also in the video domain. Additionally, the latest released SAM 2 is once again sparking research enthusiasm in the realm of promptable visual segmentation for both images and videos. However, existing surveys…
Read More
Evaluating Text Classification Robustness to Part-of-Speech Adversarial Examples

Evaluating Text Classification Robustness to Part-of-Speech Adversarial Examples

arXiv:2408.08374v1 Announce Type: new Abstract: As machine learning systems become more widely used, especially for safety critical applications, there is a growing need to ensure that these systems behave as intended, even in the face of adversarial examples. Adversarial examples are inputs that are designed to trick the decision making process, and are intended to be imperceptible to humans. However, for text-based classification systems, changes to the input, a string of text, are always perceptible. Therefore, text-based adversarial examples instead focus on trying to preserve semantics. Unfortunately, recent work has shown this goal is often not met. To improve the…
Read More
The Influence of AI-Powered Image Recognition on Privacy and Security

The Influence of AI-Powered Image Recognition on Privacy and Security

AI-powered image recognition is reshaping privacy and security landscapes, presenting both opportunities and challenges. This technology allows for highly accurate identification and analysis of visual data, which can enhance security measures in various sectors, from law enforcement to personal device authentication. However, it also raises significant privacy concerns. The ability to track individuals through facial recognition or analyze personal images without consent leads to potential misuse, sparking debates over data protection and ethical use. As these concerns grow, businesses and marketers need to navigate these changes carefully. Top freelance digital marketing specialists like Neil Patel and Brian Dean are already…
Read More
No widgets found. Go to Widget page and add the widget in Offcanvas Sidebar Widget Area.