Multimodal disinformation, from 'deepfakes' to simple edits that deceive, is an important societal problem. Yet at the same time, the vast majority of media edits are harmless -- such as a filtered vacation photo. The difference between this example, and harmful edits that spread disinformation, is one of intent. Recognizing and describing this intent is a major challenge for today's AI systems. We present the task of Edited Media Understanding, requiring models to answer open-ended questions that capture the intent and implications of an image edit. We introduce a dataset for our task, EMU, with 48k question-answer pairs written in rich natural language. We evaluate a wide variety of vision-and-language models for our task, and introduce a new model PELICAN, which builds upon recent progress in pretrained multimodal representations. Our model obtains promising results on our dataset, with humans rating its answers as accurate 40.35% of the time. At the same time, there is still much work to be done -- humans prefer human-annotated captions 93.56% of the time -- and we provide analysis that highlights areas for further progress.

Large Visual Language Models (LVLMs) struggle with hallucinations in visual instruction following task(s), limiting their trustworthiness and real-world applicability. We propose Pelican -- a novel framework designed to detect and mitigate hallucinations through claim verification. Pelican first decomposes the visual claim into a chain of sub-claims based on first-order predicates. These sub-claims consist of (predicate, question) pairs and can be conceptualized as nodes of a computational graph. We then use Program-of-Thought prompting to generate Python code for answering these questions through flexible composition of external tools. Pelican improves over prior work by introducing (1) intermediate variables for precise grounding of object instances, and (2) shared computation for answering the sub-question to enable adaptive corrections and inconsistency identification. We finally use reasoning abilities of LLM to verify the correctness of the the claim by considering the consistency and confidence of the (question, answer) pairs from each sub-claim. Our experiments reveal a drop in hallucination rate by $\sim$8%-32% across various baseline LVLMs and a 27% drop compared to approaches proposed for hallucination mitigation on MMHal-Bench. Results on two other benchmarks further corroborate our results.

As particle accelerators increase their collision rates, and deep learning solutions prove their viability, there is a growing need for lightweight and fast neural network architectures for low-latency tasks such as triggering. We examine the potential of one recent Lorentz- and permutation-symmetric architecture, PELICAN, and present its instances with as few as 19 trainable parameters that outperform generic architectures with tens of thousands of parameters when compared on the binary classification task of top quark jet tagging.

PELICAN is a novel permutation equivariant and Lorentz invariant or covariant aggregator network designed to overcome common limitations found in architectures applied to particle physics problems. Compared to many approaches that use non-specialized architectures that neglect underlying physics principles and require very large numbers of parameters, PELICAN employs a fundamentally symmetry group-based architecture that demonstrates benefits in terms of reduced complexity, increased interpretability, and raw performance. We present a comprehensive study of the PELICAN algorithm architecture in the context of both tagging (classification) and reconstructing (regression) Lorentz-boosted top quarks, including the difficult task of specifically identifying and measuring the $W$-boson inside the dense environment of the Lorentz-boosted top-quark hadronic final state. We also extend the application of PELICAN to the tasks of identifying quark-initiated vs.~gluon-initiated jets, and a multi-class identification across five separate target categories of jets. When tested on the standard task of Lorentz-boosted top-quark tagging, PELICAN outperforms existing competitors with much lower model complexity and high sample efficiency. On the less common and more complex task of 4-momentum regression, PELICAN also outperforms hand-crafted, non-machine learning algorithms. We discuss the implications of symmetry-restricted architectures for the wider field of machine learning for physics.

A California-based company is developing a new drone for delivery services. Despite the increasing popularity of delivery services including the use of drones, it has been challenging for companies to keep these services profitable. This is because of the high costs associated with operating drones. CLICK TO GET KURT'S FREE CYBERGUY NEWSLETTER WITH QUICK TIPS, TECH REVIEWS, SECURITY ALERTS AND EASY HOW-TO'S TO MAKE YOU SMARTER Factors weighing in include cost of the drone itself, maintenance, and pilot training. On top of that, delivering through drones is tightly regulated by aviation authorities, which can add to the expense and difficulty of running these services.

Many current approaches to machine learning in particle physics use generic architectures that require large numbers of parameters, often adapted from unrelated data science or industry applications, and disregard underlying physics principles, thereby limiting their applicability as scientific modeling tools. In this work, we present a machine learning architecture that uses a set of inputs maximally reduced with respect to the full 6-dimensional Lorentz symmetry, and is fully permutation-equivariant throughout. We study the application of this network architecture to the standard task of classifying the origin of jets produced by either hadronically-decaying massive top quarks or light quarks, and show that the resulting network outperforms all existing competitors despite significantly lower model complexity. In addition, we present a Lorentz-covariant variant of the same network applied to a 4-momentum regression task in which we predict the full 4-vector of the W boson from a top quark decay process.

A few years ago, one of the first things I did when learning about neural networks is to train a simple image classifier. Neural nets can do a marvelous job at telling what's in an image. However, one thing I have not asked myself back then is: "What are these nets actually learning?" Let me explain what I mean by that with an example: How do we humans recognize that a dog is a dog? I'd say we look for distinctive features like pointy ears, snout, tail, four legs, and similar things.

PelicanPayments is a complete payments solution delivering exceptional levels of efficiency, control and flexibility. PelicanSecure is a comprehensive suite of real-time financial crime compliance and anti-fraud solutions. Pelican Open Banking Hub connects 6000 banks in Europe with an ability to connect to over 500 million customers. This Open Banking webinar focuses on opportunities for banks in opting for the an aggressive and proactive approach to winning new customers. To read a full report, click "Learn More:

It seems that the majority of AI solutions for payment processing are focused on fraud detection and prevention. Some companies claim to offer straight-through processing software as well. We'll get started with background information about AI in payment processing, and then we'll explore the vendor use cases in depth individually. The companies discussed in this report vary in their densities of AI talent, which is one of the three rules of thumb we use when determining whether or not a company is actually leveraging AI or using it more for marketing purposes. We look for companies with AI talent in their C-suites first and foremost, but perhaps equally important is the number of data scientists employed at the company.

Parth Desai, CEO and founder of Pelican, discusses why artificial intelligence (AI) is already fact not a fantasy, but cautions that we need to be realistic about what can really be achieved on the journey to true AI adoption in transaction banking and payments. It's very encouraging to read that respected firms such as Gartner are predicting that AI will be pervasive in all new products by 2020. And there are many discussions happening today about the potential of AI within financial services and how it will help to streamline processes and add value, but we also have to be very realistic about what is actually possible. AI uses computing power and knowledge to simulate intelligent human behaviour and is undoubtedly already in play, particularly within the military and consumer worlds. But despite all the hype, and irrespective of the sector, it still has some way to go and should not be viewed as the panacea that will solve every single problem.