A great thing about catching a cold in December, as a critic, is that it's a perfect time to play NyQuil-induced catch-up with all the screeners I'd yet to watch. Cynthia Erivo is as good as everyone says in Wicked. Hundreds of Beavers is funny and incredibly well calculated, astute in its ability to shape-shift just enough to never get tedious. The Wild Robot is emotionally satisfying--but it made me lament a world in which even a robot has to have her programming overridden by the American social imperative to be a "mother." The Remarkable Life of Ibelin is a worthy reminder of what the old internet, the internet of my own upbringing, used to feel like: communal, social, mysterious.

This technical report presents our initial attempt to build a spoken large language model (LLM) for Taiwanese Mandarin, specifically tailored to enable real-time, speech-to-speech interaction in multi-turn conversations. Our end-to-end model incorporates a decoder-only transformer architecture and aims to achieve seamless interaction while preserving the conversational flow, including full-duplex capabilities allowing simultaneous speaking and listening. The paper also details the training process, including data preparation with synthesized dialogues and adjustments for real-time interaction. We also developed a platform to evaluate conversational fluency and response coherence in multi-turn dialogues. We hope the release of the report can contribute to the future development of spoken LLMs in Taiwanese Mandarin.

Recent years have seen significant progress in Text-To-Audio (TTA) synthesis, enabling users to enrich their creative workflows with synthetic audio generated from natural language prompts. Despite this progress, the effects of data, model architecture, training objective functions, and sampling strategies on target benchmarks are not well understood. With the purpose of providing a holistic understanding of the design space of TTA models, we set up a large-scale empirical experiment focused on diffusion and flow matching models. Our contributions include: 1) AF-Synthetic, a large dataset of high quality synthetic captions obtained from an audio understanding model; 2) a systematic comparison of different architectural, training, and inference design choices for TTA models; 3) an analysis of sampling methods and their Pareto curves with respect to generation quality and inference speed. We leverage the knowledge obtained from this extensive analysis to propose our best model dubbed Elucidated Text-To-Audio (ETTA). When evaluated on AudioCaps and MusicCaps, ETTA provides improvements over the baselines trained on publicly available data, while being competitive with models trained on proprietary data. Finally, we show ETTA's improved ability to generate creative audio following complex and imaginative captions -- a task that is more challenging than current benchmarks.

With the rapid development of online social networks and the inadequacies in content moderation mechanisms, the detection of fake news has emerged as a pressing concern for the public. Various methods have been proposed for fake news detection, including text-based approaches as well as a series of graph-based approaches. However, the deceptive nature of fake news renders text-based approaches less effective. Propagation tree-based methods focus on the propagation process of individual news, capturing pairwise relationships but lacking the capability to capture high-order complex relationships. Large heterogeneous graph-based approaches necessitate the incorporation of substantial additional information beyond news text and user data, while hypergraph-based approaches rely on predefined hypergraph structures. To tackle these issues, we propose a novel dynamic hypergraph-based multi-view fake news detection model (DHy-MFND) that learns news embeddings across three distinct views: text-level, propagation tree-level, and hypergraph-level. By employing hypergraph structures to model complex high-order relationships among multiple news pieces and introducing dynamic hypergraph structure learning, we optimize predefined hypergraph structures while learning news embeddings. Additionally, we introduce contrastive learning to capture authenticity-relevant embeddings across different views. Extensive experiments on two benchmark datasets demonstrate the effectiveness of our proposed DHy-MFND compared with a broad range of competing baselines.

In Sex Reviews, writers offer a sober critical assessment of the sex scenes in new films and television series. This installment contains spoilers for Babygirl. Nestled amid a nice little set of Christmas releases is Babygirl, an erotic thriller set during the holidays, written and directed by Halina Reijn of Bodies, Bodies, Bodies fame. The film stars Nicole Kidman as Romy, a work-addicted CEO of a robotics company, who lives with her play-directing, gray-goatee-sporting husband Jacob (Antonio Banderas) and two teenage daughters in a gorgeous Manhattan apartment. Romy's creeping dissatisfaction with the rounds of Botox, therapy, and meetings that make up her life comes to a head when she meets Samuel, an intern at her company, played by hyper-handsome English actor Harris Dickinson. In fits and starts, the Gen X Romy and Gen Z Samuel discover that they have a very particular type of chemistry: She wants to be told what to do, and he's willing to tell her.

Whether a large and fuzzy social media sensation or deep-sea slug slunking around the ocean's Midnight Zone, there are still so many exciting animals on Earth just waiting for their close-up. In that spirit, here are the 11 of the most exciting animal stories that Popular Science covered this year. A wildlife filmmaker and biology doctoral student took what could be the first picture of a newborn great white shark. Filmmaker Carlos Gauna and University of California, Riverside biology doctoral student Phillip Sternes were looking for sharks near Santa Barbara on California's central coast. Most great whites are gray on top with white bellies, but Gauana's drone camera showed a roughly 5-foot-long shark pup that had more white on its body than normal.

This was the year that gen Z had their "Brat summer", or so we were led to believe. Inspired by the hit album by pop sensation Charli xcx, the trend was seen to embody all the messiness of modern youth: trashy, chaotic and bright green. But on the teenager's social media platform of choice, TikTok, a more sepia music trend has been taking root. Despite having an endless amount of music to pair with their short, scrollable videos, TikTok users have been raiding the back catalogues of artists from yesteryear including Bronski Beat and Sade to soundtrack their posts. This year set a new high for use of old tracks on British TikTok posts, with tunes more than five years old accounting for 19 out of its 50 top tracks this year.

Handwritten document recognition (HDR) is one of the most challenging tasks in the field of computer vision, due to the various writing styles and complex layouts inherent in handwritten texts. Traditionally, this problem has been approached as two separate tasks, handwritten text recognition and layout analysis, and struggled to integrate the two processes effectively. This paper introduces HAND (Hierarchical Attention Network for Multi-Scale Document), a novel end-to-end and segmentation-free architecture for simultaneous text recognition and layout analysis tasks. Our model's key components include an advanced convolutional encoder integrating Gated Depth-wise Separable and Octave Convolutions for robust feature extraction, a Multi-Scale Adaptive Processing (MSAP) framework that dynamically adjusts to document complexity and a hierarchical attention decoder with memory-augmented and sparse attention mechanisms. These components enable our model to scale effectively from single-line to triple-column pages while maintaining computational efficiency. Additionally, HAND adopts curriculum learning across five complexity levels. To improve the recognition accuracy of complex ancient manuscripts, we fine-tune and integrate a Domain-Adaptive Pre-trained mT5 model for post-processing refinement. Extensive evaluations on the READ 2016 dataset demonstrate the superior performance of HAND, achieving up to 59.8% reduction in CER for line-level recognition and 31.2% for page-level recognition compared to state-of-the-art methods. The model also maintains a compact size of 5.60M parameters while establishing new benchmarks in both text recognition and layout analysis. Source code and pre-trained models are available at : https://github.com/MHHamdan/HAND.

What is appropriateness? Humans navigate a multi-scale mosaic of interlocking notions of what is appropriate for different situations. We act one way with our friends, another with our family, and yet another in the office. Likewise for AI, appropriate behavior for a comedy-writing assistant is not the same as appropriate behavior for a customer-service representative. What determines which actions are appropriate in which contexts? And what causes these standards to change over time? Since all judgments of AI appropriateness are ultimately made by humans, we need to understand how appropriateness guides human decision making in order to properly evaluate AI decision making and improve it. This paper presents a theory of appropriateness: how it functions in human society, how it may be implemented in the brain, and what it means for responsible deployment of generative AI technology.

As working with large datasets becomes standard, the task of accurately retrieving images containing objects of interest by an open set textual query gains practical importance. The current leading approach utilizes a pre-trained CLIP model without any adaptation to the target domain, balancing accuracy and efficiency through additional post-processing. In this work, we propose FOR: Finetuning for Object-centric Open-vocabulary Image Retrieval, which allows finetuning on a target dataset using closed-set labels while keeping the visual-language association crucial for open vocabulary retrieval. FOR is based on two design elements: a specialized decoder variant of the CLIP head customized for the intended task, and its coupling within a multi-objective training framework. Together, these design choices result in a significant increase in accuracy, showcasing improvements of up to 8 mAP@50 points over SoTA across three datasets. Additionally, we demonstrate that FOR is also effective in a semi-supervised setting, achieving impressive results even when only a small portion of the dataset is labeled.