Viral News

Hybrid-Learning Video Moment Retrieval across Multi-Domain Labels
05 Jun

Hybrid-Learning Video Moment Retrieval across Multi-Domain Labels

stp2y0 CommentsViral News
arXiv:2406.01791v1 Announce Type: new Abstract: Video moment retrieval (VMR) is to search for a visual temporal moment in an untrimmed raw video by a given text query description (sentence). Existing studies either start from collecting exhaustive frame-wise annotations on the temporal boundary of target moments (fully-supervised), or learn with only the video-level video-text pairing labels (weakly-supervised). The former is poor in generalisation to unknown concepts and/or novel scenes due to restricted dataset scale and diversity under expensive annotation costs; the latter is subject to visual-textual mis-correlations from incomplete labels. In this work, we introduce a new approach called hybrid-learning video…
Read More
An Open Multilingual System for Scoring Readability of Wikipedia
05 Jun

An Open Multilingual System for Scoring Readability of Wikipedia

stp2y0 CommentsViral News
[Submitted on 3 Jun 2024] View a PDF of the paper titled An Open Multilingual System for Scoring Readability of Wikipedia, by Mykola Trokhymovych and 2 other authors View PDF HTML (experimental) Abstract:With over 60M articles, Wikipedia has become the largest platform for open and freely accessible knowledge. While it has more than 15B monthly visits, its content is believed to be inaccessible to many readers due to the lack of readability of its text. However, previous investigations of the readability of Wikipedia have been restricted to English only, and there are currently no systems supporting the automatic readability assessment…
Read More
Who’s Watching Your GenAI Bot?
05 Jun

Who’s Watching Your GenAI Bot?

stp2y0 CommentsViral News
(Andrey-Suslov/Shutterstock) In January, a UK delivery service called DPD made headlines for the worst reasons. A customer shared an incredible exchange with DPD’s customer service chatbot, which varied in its replies from, “F**k yeah!” to “DPD is a useless customer chatbot that can’t help you.” This all took place in one very memorable but very brand-damaging exchange. Chatbots and other GenAI tools, whether internally or externally facing, are seeing rapid adoption today. Notions like the “AI arms race” as Time Magazine put it, reflect the pressure on companies to roll out these tools as quickly as possible, or risk falling…
Read More
Self-Improving Robust Preference Optimization
05 Jun

Self-Improving Robust Preference Optimization

stp2y0 CommentsViral News
arXiv:2406.01660v1 Announce Type: new Abstract: Both online and offline RLHF methods such as PPO and DPO have been extremely successful in aligning AI with human preferences. Despite their success, the existing methods suffer from a fundamental problem that their optimal solution is highly task-dependent (i.e., not robust to out-of-distribution (OOD) tasks). Here we address this challenge by proposing Self-Improving Robust Preference Optimization SRPO, a practical and mathematically principled offline RLHF framework that is completely robust to the changes in the task. The key idea of SRPO is to cast the problem of learning from human preferences as a self-improvement process,…
Read More
Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
05 Jun

Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers

stp2y0 CommentsViral News
arXiv:2406.01765v1 Announce Type: new Abstract: New transformer networks have been integrated into object tracking pipelines and have demonstrated strong performance on the latest benchmarks. This paper focuses on understanding how transformer trackers behave under adversarial attacks and how different attacks perform on tracking datasets as their parameters change. We conducted a series of experiments to evaluate the effectiveness of existing adversarial attacks on object trackers with transformer and non-transformer backbones. We experimented on 7 different trackers, including 3 that are transformer-based, and 4 which leverage other architectures. These trackers are tested against 4 recent attack methods to assess their performance…
Read More
Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation
05 Jun

Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation

stp2y0 CommentsViral News
arXiv:2406.01806v1 Announce Type: new Abstract: The advent of large language models (LLMs) has dramatically advanced the state-of-the-art in numerous natural language generation tasks. For LLMs to be applied reliably, it is essential to have an accurate measure of their confidence. Currently, the most commonly used confidence score function is the likelihood of the generated sequence, which, however, conflates semantic and syntactic components. For instance, in question-answering (QA) tasks, an awkward phrasing of the correct answer might result in a lower probability prediction. Additionally, different tokens should be weighted differently depending on the context. In this work, we propose enhancing the…
Read More
CoLa-DCE — Concept-guided Latent Diffusion Counterfactual Explanations
05 Jun

CoLa-DCE — Concept-guided Latent Diffusion Counterfactual Explanations

stp2y0 CommentsViral News
arXiv:2406.01649v1 Announce Type: new Abstract: Recent advancements in generative AI have introduced novel prospects and practical implementations. Especially diffusion models show their strength in generating diverse and, at the same time, realistic features, positioning them well for generating counterfactual explanations for computer vision models. Answering "what if" questions of what needs to change to make an image classifier change its prediction, counterfactual explanations align well with human understanding and consequently help in making model behavior more comprehensible. Current methods succeed in generating authentic counterfactuals, but lack transparency as feature changes are not directly perceivable. To address this limitation, we introduce…
Read More
An approximation-based approach versus an AI one for the study of CT images of abdominal aorta aneurysms
05 Jun

An approximation-based approach versus an AI one for the study of CT images of abdominal aorta aneurysms

stp2y0 CommentsViral News
[Submitted on 3 Jun 2024] View a PDF of the paper titled An approximation-based approach versus an AI one for the study of CT images of abdominal aorta aneurysms, by Lucrezia Rinelli and 3 other authors View PDF HTML (experimental) Abstract:This study evaluates two approaches applied to computed tomography (CT) images of patients with abdominal aortic aneurysm: one deterministic, based on tools of Approximation Theory, and one based on Artificial Intelligence. Both aim to segment the basal CT images to extract the patent area of the aortic vessel, in order to propose an alternative to nephrotoxic contrast agents for diagnosing…
Read More
OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models
05 Jun

OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models

stp2y0 CommentsViral News
arXiv:2406.01775v1 Announce Type: new Abstract: The advent of large language models (LLMs) has revolutionized natural language processing, enabling unprecedented capabilities in understanding and generating human-like text. However, the computational cost and convergence times associated with fine-tuning these models remain significant challenges. Low-Rank Adaptation (LoRA) has emerged as a promising method to mitigate these issues by introducing efficient fine-tuning techniques with a reduced number of trainable parameters. In this paper, we present OLoRA, an enhancement to the LoRA method that leverages orthonormal matrix initialization through QR decomposition. OLoRA significantly accelerates the convergence of LLM training while preserving the efficiency benefits of…
Read More
Enhancing Generative AI Security: The Role of Enterprise Browsers
05 Jun

Enhancing Generative AI Security: The Role of Enterprise Browsers

stp2y0 CommentsViral News
The rapid advancement of technology has ushered in a wave of innovations that have significantly eased our daily lives and professional responsibilities. Before these developments, the digital landscape lacked the tools necessary to streamline work and business operations. However, with the emergence of intelligent generative AI, the time and energy required for tasks have been substantially reduced. While it's unlikely that AI will render many of us jobless in the foreseeable future, there remains a pressing concern regarding its potential intrusion into our personal and sensitive data if not handled with care. Generative AI, a form of artificial intelligence designed…
Read More
No widgets found. Go to Widget page and add the widget in Offcanvas Sidebar Widget Area.