Large Language Models (LLMs) have recently demonstrated remarkable performance in tasks such as Retrieval-Augmented Generation (RAG) and autonomous AI agent workflows. Yet, when faced with large sets of unstructured documents requiring progressive exploration, analysis, and synthesis, such as conducting literature survey, existing approaches often fall short. We address this challenge -- termed Progressive Document Investigation -- by introducing Graphy, an end-to-end platform that automates data modeling, exploration and high-quality report generation in a user-friendly manner. Graphy comprises an offline Scrapper that transforms raw documents into a structured graph of Fact and Dimension nodes, and an online Surveyor that enables iterative exploration and LLM-driven report generation. We showcase a pre-scrapped graph of over 50,000 papers -- complete with their references -- demonstrating how Graphy facilitates the literature-survey scenario. The demonstration video can be found at https://youtu.be/uM4nzkAdGlM.

Artificial intelligence has been tapped by insurers to ramp up customer experience and accelerate the speed of decision-making. Customer Conversations When call centres were shut down during the pandemic, our AI-driven chatbot came to the fore. Not only did customers feel the same level of comfort that they did while interacting with call centre executives, as evidenced by the overnight spike in servicing via this medium, accompanied by a 90% dip in grievances, but the AI-driven chatbot went beyond the shift in plane from person-driven servicing to bot-driven servicing to include conversations in languages beyond English. More importantly, the servicing was not restricted to a few niche cases, but the most sought-after array of services that were offered by insurers via the call centre. Motor On the Spot Claim Servicing Traditional claim servicing involves the entire rigmarole of a call from the customer from the site of the crash of the vehicle to the insurance company, the appointment of a surveyor, his on-site visit and assessment, submission of the report to the firm and subsequent processing of the claims.

EyeVi, an Estonian startup, plans to build out tools to automate road data capture to improve maintenance and operations and expand into U.S. markets. EyeVi provides road service surveyors, repair crews, and municipalities with computer-vision hardware and AI-driven SaaS to map and identify road infrastructure needs. "We are developing a platform that can survey the road for about one-hundredth the cost of manual approaches today," EyeVi CEO Gaspar Anton told VentureBeat. Anton conceived of the idea about a decade ago as a driver for Google Streetview. Now EyeVi, which has raised $2 million in seed funding, is extending the same concept to support road operations and maintenance.

If you happen to be crossing the San Francisco Bay or Golden Gate bridges this week, look for a massive surfboard with a red sail on top cruising slowly across the water. Don't flinch if you don't see anyone on board. It's actually an autonomous research vessel known as the Saildrone Surveyor and it's being steered remotely from shore. The 72-foot-long vessel is launching this week into the bay from its dock at a former naval base in Alameda, California. It is designed to spend months at sea mapping the seafloor with powerful sonar devices, while simultaneously scanning the ocean surface for genetic material to identify fish and other marine organisms swimming below.

"It's very common," says Jess Hanham casually, when asked how often he finds suspected unexploded bombs. Mr Hanham is a co-founder of Spectrum Offshore, a marine survey firm that does a lot of work in the Thames Estuary. His firm undertakes all sorts of marine surveying, but working on sites for new offshore wind farms has become a big business for him. Work in the Thames Estuary, and other areas that were the targets of bombing in World War 2, are likely to involve picking up signals of unexploded munitions. "You can find a significant amount of contacts that need further investigation and for a wind farm that will be established in the initial pre-engineering survey," he says.

The insurance industry is one of the oldest and most critical industries in the world. 'Trust' is the most important currency in this industry and hence insurance was always a people-intensive industry. Whether it is an agent who sells policies or surveyor who assesses claims, insurance companies always had to rely on people to build customer trust. A large part of claim assessment is to monitor'fraud claims' – and until recently, the only way to assess claims was to manually investigate on a case by case basis. With the advent of technology, there is a big disruption coming to the insurance industry.

The hack, featuring software engineers from Microsoft who had travelled from across Europe and Africa to work with OS's machine learning team, used the city of Hull as a testbed. The trained machine model finished the week by correctly identifying 87% of the roof types it was shown. In its training the model was shown 500 flat roofs and 500 hipped/gabled roofs, set a confidence limit of 90%, which means it must be 90% confident or more for its assessment to count. Isabel Sargent, Senior Research and Development Scientist at OS, says: "Thanks to the excellence of the Microsoft team we have been able to work out together how to stream this machine captured data into our database for if and when we're ready to put machine learning into production. It's already very accurate, going from zero to 87% accuracy in just one week, but we need to increase its success rate. Although much slower, humans typically have an error rate of around 5%."

Two rhinos at the Kuzikus Nature Reserve in Namibia, photographed by drone. When the U.S. military needed to identify mines in a dangerous valley in Afghanistan, aerial-imagery specialist Tudor Thomas helped build a plane-based system to map it. Back in 2013, similar systems cost the military and its contractors one to five million dollars, Thomas says--and that didn't even include the cost of the plane. "It's hard to comprehend how much was getting spent just to make a simple aerial image," he says. The experience sparked an idea for a business: mapping by drone.

We investigate the task of generating coherent survey articles for scientific topics. We introduce an extractive summarization algorithm that combines a content model with a discourse model to generate coherent and readable summaries of scientific topics using text from scientific articles relevant to the topic. Human evaluation on 15 topics in computational linguistics shows that our system produces significantly more coherent summaries than previous systems. Specifically, our system improves the ratings for coherence by 36% in human evaluation compared to C-Lexrank, a state of the art system for scientific article summarization.

We consider the crowdsourcing task of learning the answer to simple multiple-choice microtasks. In order to provide statistically significant results, one often needs to ask multiple workers to answer the same microtask. A stopping rule is an algorithm that for a given microtask decides for any given set of worker answers if the system should stop and output an answer or iterate and ask one more worker. A quality score for a worker is a score that reflects the historic performance of that worker. In this paper we investigate how to devise better stopping rules given such quality scores. We conduct a data analysis on a large-scale industrial crowdsourcing platform, and use the observations from this analysis to design new stopping rules that use the workers’ quality scores in a non-trivial manner. We then conduct a simulation based on a real-world workload, showing that our algorithm performs better than the more naive approaches.