A documentary about Hideo Kojima, one of the most lauded video game designers on the planet, is on the way. A trailer offers a first peek at what's in store for those who plan to check out Hideo Kojima: Connecting Worlds. Kojima wrote on Twitter that the film will provide a behind-the-scenes look at the development of Death Stranding, as well as "shots from the early days of our independent studio, memories from my childhood and my creative journey." The trailer encapsulates all of that while suggesting the film is a celebration of Kojima and his work. Friends, collaborators and fans including Geoff Keighley, Guillermo del Toro, Norman Reedus and George Miller are shown talking up Kojima and his credentials.

An image of a baby Elon Musk is making waves on the internet, showing the billionaire as a toddler with a white button-up shirt, brown overalls and signature haircut. The adorable photo, however, was made by a Twitter user with the help of artificial intelligence who tweeted: 'Elon Musk was reportedly working on some anti-aging formula, but it got way out of hand.' The Tesla CEO took the opportunity to respond, posting: 'Guys, I think I maybe took too much.' Users flocked to the comment section of the image, many joking that Musk is'the real Boss Baby.' AI-generated images have taken over the internet in recent months, some sparking joy and others causing terror. In March, a photo of Pope Francis donning a huge white puffer jacket immediately fooled the internet.

This disturbingly real-looking artificial intelligence sci-fi was made a couple of years ago on what looks like a budget of small change tipped out of the film-makers' coin jars. It's getting a release now presumably on account of AI anxiety creeping up the league table of things that keep people awake at night. Like the Nosedive episode of Charlie Brooker's Black Mirror, the premise here is that in an apparently-near future people wear contact lenses that feed them information about the world. Andrew Riddell plays Patrick, who like everyone else wears dazzling blue contact lenses that fill the air around him with holograms. Patrick is an agoraphobic who hasn't left his apartment for over a month; he spends his time playing computer games, going hammer and tongs with 3D zombies.

Speaker diarization is the task of answering Who spoke and when? in an audio stream. Pipeline systems rely on speech segmentation to extract speakers' segments and achieve robust speaker diarization. This paper proposes a common framework to solve three segmentation tasks in the distant speech scenario: Voice Activity Detection (VAD), Overlapped Speech Detection (OSD), and Speaker Change Detection (SCD). In the literature, a few studies investigate the multi-microphone distant speech scenario. In this work, we propose a new set of spatial features based on direction-of-arrival estimations in the circular harmonic domain (CH-DOA). These spatial features are extracted from multi-microphone audio data and combined with standard acoustic features. Experiments on the AMI meeting corpus show that CH-DOA can improve the segmentation while being robust in the case of deactivated microphones.

Large language models (LLMs) can be used to generate text data for training and evaluating other models. However, creating high-quality datasets with LLMs can be challenging. In this work, we explore human-AI partnerships to facilitate high diversity and accuracy in LLM-based text data generation. We first examine two approaches to diversify text generation: 1) logit suppression, which minimizes the generation of languages that have already been frequently generated, and 2) temperature sampling, which flattens the token sampling probability. We found that diversification approaches can increase data diversity but often at the cost of data accuracy (i.e., text and labels being appropriate for the target domain). To address this issue, we examined two human interventions, 1) label replacement (LR), correcting misaligned labels, and 2) out-of-scope filtering (OOSF), removing instances that are out of the user's domain of interest or to which no considered label applies. With oracle studies, we found that LR increases the absolute accuracy of models trained with diversified datasets by 14.4%. Moreover, we found that some models trained with data generated with LR interventions outperformed LLM-based few-shot classification. In contrast, OOSF was not effective in increasing model accuracy, implying the need for future work in human-in-the-loop text data generation.

A new class of tools, colloquially called generative AI, can produce high-quality artistic media for visual arts, concept art, music, fiction, literature, video, and animation. The generative capabilities of these tools are likely to fundamentally alter the creative processes by which creators formulate ideas and put them into production. As creativity is reimagined, so too may be many sectors of society. Understanding the impact of generative AI - and making policy decisions around it - requires new interdisciplinary scientific inquiry into culture, economics, law, algorithms, and the interaction of technology and creativity. We argue that generative AI is not the harbinger of art's demise, but rather is a new medium with its own distinct affordances. In this vein, we consider the impacts of this new medium on creators across four themes: aesthetics and culture, legal questions of ownership and credit, the future of creative work, and impacts on the contemporary media ecosystem. Across these themes, we highlight key research questions and directions to inform policy and beneficial uses of the technology.

To promote the development of Vision-Language Pre-training (VLP) and multimodal Large Language Model (LLM) in the Chinese community, we firstly release the largest public Chinese high-quality video-language dataset named Youku-mPLUG, which is collected from Youku, a well-known Chinese video-sharing website, with strict criteria of safety, diversity, and quality. Youku-mPLUG contains 10 million Chinese video-text pairs filtered from 400 million raw videos across a wide range of 45 diverse categories for large-scale pre-training. In addition, to facilitate a comprehensive evaluation of video-language models, we carefully build the largest human-annotated Chinese benchmarks covering three popular video-language tasks of cross-modal retrieval, video captioning, and video category classification. Youku-mPLUG can enable researchers to conduct more in-depth multimodal research and develop better applications in the future. Furthermore, we release popular video-language pre-training models, ALPRO and mPLUG-2, and our proposed modularized decoder-only model mPLUG-video pre-trained on Youku-mPLUG. Experiments show that models pre-trained on Youku-mPLUG gain up to 23.1% improvement in video category classification. Besides, mPLUG-video achieves a new state-of-the-art result on these benchmarks with 80.5% top-1 accuracy in video category classification and 68.9 CIDEr score in video captioning, respectively. Finally, we scale up mPLUG-video based on the frozen Bloomz with only 1.7% trainable parameters as Chinese multimodal LLM, and demonstrate impressive instruction and video understanding ability. The zero-shot instruction understanding experiment indicates that pretraining with Youku-mPLUG can enhance the ability to comprehend overall and detailed visual semantics, recognize scene text, and leverage open-domain knowledge.

Topic models have been prevalent for decades with various applications. However, existing topic models commonly suffer from the notorious topic collapsing: discovered topics semantically collapse towards each other, leading to highly repetitive topics, insufficient topic discovery, and damaged model interpretability. In this paper, we propose a new neural topic model, Embedding Clustering Regularization Topic Model (ECRTM). Besides the existing reconstruction error, we propose a novel Embedding Clustering Regularization (ECR), which forces each topic embedding to be the center of a separately aggregated word embedding cluster in the semantic space. This enables each produced topic to contain distinct word semantics, which alleviates topic collapsing. Regularized by ECR, our ECRTM generates diverse and coherent topics together with high-quality topic distributions of documents. Extensive experiments on benchmark datasets demonstrate that ECRTM effectively addresses the topic collapsing issue and consistently surpasses state-of-the-art baselines in terms of topic quality, topic distributions of documents, and downstream classification tasks.

Figure 1 illustrates the distinction of Open-domain question answering is a well-known our approach providing both knowledge to a unified task in natural language processing, aiming to answer reader as context. We retrieve a list of relevant factoid questions from an open set of domains. QA-pairs (called as QA-history), then treat the One commonly used approach for this task is the few retrieved QA examples, as if it is a relevant retrieve-then-read pipeline (also known as Openbook document passage. QA) to retrieve relevant knowledge, then reason Meanwhile, the closest approach to use multiple answers over the knowledge. Given the wide knowledge sources is concatenating the multisources range of topics that open-domain questions can uniformly into a single decoder (Oguz cover, a key to a successful answering model is: et al., 2020), but we argue knowledge selection is to access and utilize diverse knowledge sources critically missing. To motivate, Figure 1 shows the effectively. QA-history, from which answer'Eric Liddell' is Toward this goal, existing work can be categorized explicitly identified, while it is more implicit in the by the knowledge source used: document such that another name such as'Hugh Hudson' is known to often confuse QA models. It Document Corpus-based QA (Doc-QA): This is critical for the QA model to calibrate prediction type of work utilizes a general-domain Document quality as an indicator to decide when to use a Corpus (e.g., Wikipedia) (Karpukhin

It is very important to access a rich music dataset that is useful in a wide variety of applications. Currently, available datasets are mostly focused on storing vocal or instrumental recording data and ignoring the requirement of its visual representation and retrieval. This paper attempts to build an XML-based public dataset, called SANGEET, that stores comprehensive information of Hindustani Sangeet (North Indian Classical Music) compositions written by famous musicologist Pt. Vishnu Narayan Bhatkhande. SANGEET preserves all the required information of any given composition including metadata, structural, notational, rhythmic, and melodic information in a standardized way for easy and efficient storage and extraction of musical information. The dataset is intended to provide the ground truth information for music information research tasks, thereby supporting several data-driven analysis from a machine learning perspective. We present the usefulness of the dataset by demonstrating its application on music information retrieval using XQuery, visualization through Omenad rendering system. Finally, we propose approaches to transform the dataset for performing statistical and machine learning tasks for a better understanding of Hindustani Sangeet. The dataset can be found at https://github.com/cmisra/Sangeet.