Despite recent advances in multimodal pre-training for visual description, state-of-the-art models still produce captions containing errors, such as hallucinating objects not present in a scene. The existing prominent metric for object hallucination, CHAIR, is limited to a fixed set of MS COCO objects and synonyms. In this work, we propose a modernized open-vocabulary metric, ALOHa, which leverages large language models (LLMs) to measure object hallucinations. Specifically, we use an LLM to extract groundable objects from a candidate caption, measure their semantic similarity to reference objects from captions and object detections, and use Hungarian matching to produce a final hallucination score. We show that ALOHa correctly identifies 13.6% more hallucinated objects than CHAIR on HAT, a new gold-standard subset of MS COCO Captions annotated for hallucinations, and 30.8% more on nocaps, where objects extend beyond MS COCO categories. Our code is available at https://davidmchan.github.io/aloha/.

Direct-to-satellite (DtS) communication has gained importance recently to support globally connected Internet of things (IoT) networks. However, relatively long distances of densely deployed satellite networks around the Earth cause a high path loss. In addition, since high complexity operations such as beamforming, tracking and equalization have to be performed in IoT devices partially, both the hardware complexity and the need for high-capacity batteries of IoT devices increase. The reconfigurable intelligent surfaces (RISs) have the potential to increase the energy-efficiency and to perform complex signal processing over the transmission environment instead of IoT devices. But, RISs need the information of the cascaded channel in order to change the phase of the incident signal. This study evaluates the pilot signal as a graph and incorporates this information into the graph attention networks (GATs) to track the phase relation through pilot signaling. The proposed GAT-based channel estimation method examines the performance of the DtS IoT networks for different RIS configurations to solve the challenging channel estimation problem. It is shown that the proposed GAT both demonstrates a higher performance with increased robustness under changing conditions and has lower computational complexity compared to conventional deep learning methods. Moreover, bit error rate performance is investigated for RIS designs with discrete and non-uniform phase shifts under channel estimation based on the proposed method. One of the findings in this study is that the channel models of the operating environment and the performance of the channel estimation method must be considered during RIS design to exploit performance improvement as far as possible.

Since the start of the pandemic, many restaurants have seen great success taking their menus online, offering off-premise ordering via digital platforms. In a challenging labor market, these ordering channels provide a more efficient option for restaurants, enabling consumers to act as their own order taker. Yet, for all brands' efforts to incentivize adoption by making these channels as convenient and intuitive as possible, many consumers still prefer to call their order in via phone, the old-fashioned way. The ongoing popularity of phone ordering poses challenges for restaurants at a time when there is not always time to answer all the calls coming in. Victor Matchie, owner of Aloha, Oregon-based sandwich chain Monkey's Subs, spoke with PYMNTS about how the company's conversational artificial intelligence (AI) voice assistant, from speech recognition company SoundHound, enables the restaurant to meet this demand without the bottlenecks that can otherwise result from call-in orders at peak times.

A woman who was walking her dog in Milton Keynes, England, saw a delivery robot plunge "straight into the canal." Starship Technologies has urged residents not to worry if they see one of its robots in distress. The company noted, however, that people should report any sightings of their machines "swimming or in any other odd situation." ESPECIALLY BALL HANDLING: A man, shooting hoops in the nude at a park in Longwood, Fla., at 7:30 on a Sunday night, told arresting officers that he thought playing naked would help improve his basketball skills. A 23-year-old man kicked several people out of his family's home in Glassboro, N.J., stole a neighbor's pickup truck and got into an accident involving two other vehicles.