Out-of-distribution (OOD) detection aims to discern outliers from the intended data distribution, which is crucial to maintaining high reliability and a good user experience. Most recent studies in OOD detection utilize the information from a single representation that resides in the penultimate layer to determine whether the input is anomalous or not. Although such a method is straightforward, the potential of diverse information in the intermediate layers is overlooked. In this paper, we propose a novel framework based on contrastive learning that encourages intermediate features to learn layer-specialized representations and assembles them implicitly into a single representation to absorb rich information in the pre-trained language model. Extensive experiments in various intent classification and OOD datasets demonstrate that our approach is significantly more effective than other works.

With the advent of deep learning methods replacing the ISP in transforming sensor RAW readings into RGB images, numerous methodologies solidified into real-life applications. Equally potent is the task of inverting this process which will have applications in enhancing computational photography tasks that are conducted in the RAW domain, addressing lack of available RAW data while reaping from the benefits of performing tasks directly on sensor readings. This paper's proposed methodology is a state-of-the-art solution to the task of RAW reconstruction, and the multi-step refinement process integrating an overexposure mask is novel in three ways: instead of from RGB to bayer, the pipeline trains from RGB to demosaiced RAW allowing use of perceptual loss functions; the multi-step processes has greatly enhanced the performance of the baseline U-Net from start to end; the pipeline is a generalizable process of refinement that can enhance other high performance methodologies that support end-to-end learning.

Many NLP datasets have been found to contain shortcuts: simple decision rules that achieve surprisingly high accuracy. However, it is difficult to discover shortcuts automatically. Prior work on automatic shortcut detection has focused on enumerating features like unigrams or bigrams, which can find only low-level shortcuts, or relied on post-hoc model interpretability methods like saliency maps, which reveal qualitative patterns without a clear statistical interpretation. In this work, we propose to use probabilistic grammars to characterize and discover shortcuts in NLP datasets. Specifically, we use a context-free grammar to model patterns in sentence classification datasets and use a synchronous context-free grammar to model datasets involving sentence pairs. The resulting grammars reveal interesting shortcut features in a number of datasets, including both simple and high-level features, and automatically identify groups of test examples on which conventional classifiers fail. Finally, we show that the features we discover can be used to generate diagnostic contrast examples and incorporated into standard robust optimization methods to improve worst-group accuracy.

While interacting with chatbots, users may elicit multiple intents in a single dialogue utterance. Instead of training a dedicated multi-intent detection model, we propose DialogUSR, a dialogue utterance splitting and reformulation task that first splits multi-intent user query into several single-intent sub-queries and then recovers all the coreferred and omitted information in the sub-queries. DialogUSR can serve as a plug-in and domain-agnostic module that empowers the multi-intent detection for the deployed chatbots with minimal efforts. We collect a high-quality naturally occurring dataset that covers 23 domains with a multi-step crowd-souring procedure. To benchmark the proposed dataset, we propose multiple action-based generative models that involve end-to-end and two-stage training, and conduct in-depth analyses on the pros and cons of the proposed baselines.

After ten years in exile, fans of gruelling psychological horror can finally pack their bags: Silent Hill is reopening to visitors. During a YouTube presentation on Wednesday evening, Konami announced a reboot of the acclaimed sequel Silent Hill 2 and two new adventures, Silent Hill Townfall and Silent Hill F. A new movie tie-in, Return to Silent Hill, and an interactive live stream series, Silent Hill Ascension, were also teased. The remake is being developed by the Polish studio Bloober Team, known for horror titles such as Blair Witch and The Medium. Also involved are key members of the original Silent Hill development team, including the composer Akira Yamaoka and concept artist Masahiro Ito, best known for his creation of Silent Hill's most infamous monster, Pyramid Head. During an interview video shown as part of the presentation, Bloober Team's creative director, Mateusz Lenart, explained that while the studio wanted to stay true to the atmosphere of the original game, certain elements were being modified for the modern era; this would include a move from a third-person camera to an "over-the-shoulder" viewpoint.

The inevitable has happened, albeit a little sooner than expected. After all the hoopla surrounding text-to-image AI generators in recent months, Meta is first out of the gate with a text-to-video version. Perhaps Meta wanted to establish some headline leadership in this space, since the results aren't ready for primetime. But as developments in text-to-image generation has shown, by the time you read this the technology will already have advanced. Meta is only giving a glimpse to the public at the tech it calls Make-A-Video.

FL, Oct. 19, 2022 (GLOBE NEWSWIRE) -- The Metaverse Spectrum will be honoring the first-ever METAVERSE 100 winners at a breakfast reception Nov. 7 at One World Trade Center in New York. A panel of metaverse and Web 3.0 experts selected 100 of the most innovative companies they believe will determine the future of the metaverse. The award recognition breakfast will be hosted by PRophet, a Stagwell Marketing Cloud Company. In conjunction with the first-ever Metaverse Spectrum Business Conference and Expo, which takes place Oct. 25, a panel of Metaverse experts were assembled to select the METAVERSE 100, an exclusive list of the most exciting people and companies in the space today. "Our team is thrilled to sponsor and participate in the Metaverse 100 Breakfast," said Andrew Meranus, Executive Vice President at PRophet.

Technology company WorkFusion is to set up its new European headquarters in Dublin city centre which will create 100 jobs over the next three years. Dublin will be the company's fourth physical office joining WorkFusion's global headquarters in New York City and locations in Warsaw in Poland and Hyderabad in India. The new Dublin office will house the company's R&D and data scientists as well as other key software engineering roles. The company works with banking, insurance and financial companies. According to a recent ManPower Group Employment Outlook Survey, three in four employers globally report difficulty finding the talent they need in 2022.

At the Warner Bros Games studio in Montreal, a 7ft Batman statue greets visitors at reception. Comics are crammed into every shelf between each desk. And rather than images of lattes and flat whites, the coffee machine proudly displays the bat symbol. So, it might surprise you to learn that the people who work here have killed Batman. For the team behind the new video game Gotham Knights, their murder was the answer to a big question: how do you do something new with a character who has been throwing the Joker in jail for 83 years? If you're thinking that Batman has been done to death, you'd be right.

You might suppose Hollywood is good at predicting the future. Indeed, Robert Wallace, head of the CIA's Office of Technical Service and the US equivalent of MI6's fictional Q, has recounted how Russian spies would watch the latest Bond movie to see what technologies might be coming their way. Hollywood's continuing obsession with killer robots might therefore be of significant concern. The newest such movie is Apple TV's forthcoming sex robot courtroom drama Dolly. I never thought I'd write the phrase "sex robot courtroom drama", but there you go.