When humans acquire first language(s), they first In contrast, subword LMs of all sizes perform learn to recognize single words before understanding much worse in a syntax-independent lexical decision the grammatical processes governing them setting and only reach comparable accuracy (Tomasello, 1992; Behrens, 2021). This simple when stimuli are measured through surprisal, "unexpectedness" fact about language acquisition has found surprisingly in syntactic contexts. By comparing little attention in the increasing amount of word and syntactic learning (measured via BLiMP, work that treats LMs as models of language learners Warstadt et al., 2020), we further find that character (Warstadt and Bowman, 2022; Portelance and models quickly acquire lexical knowledge Jasbi, 2024). While word learning in children is and only later develop syntactic knowledge. In well studied, the implicit word learning processes subword models, however, word learning happens in LMs are not. Current studies overwhelmingly focus later and concurrently with syntax learning, bringing on syntax (Mueller et al., 2022; Choshen et al., further evidence against the cognitive plausibility 2022), or investigate word learning in close connection of subword tokenization. This shows how to syntax through surprisal (Chang and Bergen, elementary decisions (like choice of tokenization) 2022; Portelance et al., 2023; Shafiabadi and Wisniewski, can tremendously influence the learning dynamics 2025; Ficarra et al., 2025). Architecturewise, and trajectories that can be observed in LMs, a fact a key limitation to the precise study of word that should receive more scrutiny in studies of LMs learning is subword tokenization (e.g.

The rapid evolution of large language models (LLMs) has transformed human-computer interaction (HCI), but the interaction with LLMs is currently mainly focused on text-based interactions, while other multi-model approaches remain under-explored. This paper introduces VTutor, an open-source Software Development Kit (SDK) that combines generative AI with advanced animation technologies to create engaging, adaptable, and realistic APAs for human-AI multi-media interactions. VTutor leverages LLMs for real-time personalized feedback, advanced lip synchronization for natural speech alignment, and WebGL rendering for seamless web integration. Supporting various 2D and 3D character models, VTutor enables researchers and developers to design emotionally resonant, contextually adaptive learning agents. This toolkit enhances learner engagement, feedback receptivity, and human-AI interaction while promoting trustworthy AI principles in education. VTutor sets a new standard for next-generation APAs, offering an accessible, scalable solution for fostering meaningful and immersive human-AI interaction experiences. The VTutor project is open-sourced and welcomes community-driven contributions and showcases.

State of the art Named Entity Recognition (NER) models have achieved an impressive ability to extract common phrases from text that belong to labels such as location, organization, time, and person. However, typical NER systems that rely on having seen a specific entity in their training data in order to label an entity perform poorly on rare or unseen entities ta in order to label an entity perform poorly on rare or unseen entities (Derczynski et al., 2017). This paper attempts to improve recognition of person names, a diverse category that can grow any time someone is born or changes their name. In order for downstream tasks to not exhibit bias based on cultural background, a model should perform well on names from a variety of backgrounds. In this paper I experiment with the training data and input structure of an English Bi-LSTM name recognition model. I look at names from 103 countries to compare how well the model performs on names from different cultures, specifically in the context of a downstream task where extracted names will be matched to information on file. I find that a model with combined character and word input outperforms word-only models and may improve on accuracy compared to classical NER models that are not geared toward identifying unseen entity values.

Creating a diverse and comprehensive dataset of hand gestures for dynamic human-machine interfaces in the automotive domain can be challenging and time-consuming. To overcome this challenge, we propose using synthetic gesture datasets generated by virtual 3D models. Our framework utilizes Unreal Engine to synthesize realistic hand gestures, offering customization options and reducing the risk of overfitting. Multiple variants, including gesture speed, performance, and hand shape, are generated to improve generalizability. In addition, we simulate different camera locations and types, such as RGB, infrared, and depth cameras, without incurring additional time and cost to obtain these cameras. Experimental results demonstrate that our proposed framework, SynthoGestures\footnote{\url{https://github.com/amrgomaaelhady/SynthoGestures}}, improves gesture recognition accuracy and can replace or augment real-hand datasets. By saving time and effort in the creation of the data set, our tool accelerates the development of gesture recognition systems for automotive applications.

Autocomplete is a task where the user inputs a piece of text, termed prompt, which is conditioned by the model to generate semantically coherent continuation. Existing works for this task have primarily focused on datasets (e.g., email, chat) with high frequency user prompt patterns (or focused prompts) where word-based language models have been quite effective. In this work, we study the more challenging open-domain setting consisting of low frequency user prompt patterns (or broad prompts, e.g., prompt about 93rd academy awards) and demonstrate the effectiveness of character-based language models. We study this problem under memory-constrained settings (e.g., edge devices and smartphones), where character-based representation is effective in reducing the overall model size (in terms of parameters). We use WikiText-103 benchmark to simulate broad prompts and demonstrate that character models rival word models in exact match accuracy for the autocomplete task, when controlled for the model size. For instance, we show that a 20M parameter character model performs similar to an 80M parameter word model in the vanilla setting. We further propose novel methods to improve character models by incorporating inductive bias in the form of compositional information and representation transfer from large word models. Datasets and code used in this work are available at https://github.com/UBC-NLP/char_autocomplete.

Pretrained character-level language models were recently shown to be competitive with popular subword models across a range of NLP tasks. However, there has been little research on their effectiveness for neural machine translation (NMT). This work performs an extensive comparison across multiple languages and experimental conditions of state-of-the-art character- and subword-level pre-trained models (ByT5 and mT5, respectively) on NMT, showing the effectiveness of character-level modeling in translation, particularly in cases where training data is limited. In our analysis, we show how character models' performance gains are reflected in better translations of orthographically similar words and rare words. While evaluating the importance of source texts in driving model predictions, we highlight ByT5 word-level patterns suggesting an ability to modulate word and character-level information during the translation, providing insights into a potential weakness of character-level modeling. We conclude by assessing the efficiency tradeoff of character models, suggesting their usage in non-time-critical scenarios to boost translation quality.

We introduce a method to automatically improve character models for a handwritten script without the use of transcriptions and using a minimum of document specific training data. We show that we can use searches for the words in a dictionary to identify portions of the document whose transcriptions are unambiguous. Using templates extracted from those regions, we retrain our character prediction model to drastically improve our search retrieval performance for words in the document.

Subword-level models have been the dominant paradigm in NLP. However, character-level models have the benefit of seeing each character individually, providing the model with more detailed information that ultimately could lead to better models. Recent works have shown character-level models to be competitive with subword models, but costly in terms of time and computation. Character-level models with a downsampling component alleviate this, but at the cost of quality, particularly for machine translation. This work analyzes the problems of previous downsampling methods and introduces a novel downsampling method which is informed by subwords. This new downsampling method not only outperforms existing downsampling methods, showing that downsampling characters can be done without sacrificing quality, but also leads to promising performance compared to subword models for translation.

When looking into the world of content creation we find ourselves drawn toward the personality and relatability of those we watch. We follow these people through good times and bad because of that human connection we share. Unbeknownst to some though, there is a wide variety of AI posing as people to do jobs like reporting the news. One of these jobs is content creation with robots starting to become more prevalent in many spaces online taking over many communities once occupied solely by humans. This is not an overnight phenomenon either, it has been a gradual rise in popularity as the technology has become more accessible for companies to implement.

According to the "Digital Virtual Human Depth Industry Report", by 2030, the overall market size of China's digital virtual human will reach 270 billion. The digital virtual human has the appearance of a human being, and even the fineness of the skin is close to that of a real person. It has human behavior and can be expressed through language, facial expressions or body movements; it has human thoughts and can interact with human beings in real time, which is almost the same as human beings. The mainstream technology-driven routes of virtual digital humans are divided into AI-driven and human-driven digital human. Human-driven digital people are driven by real people. The main principle is that the real person communicates with the user in real time according to the user video sent by the video surveillance system, and at the same time, the expression and action of the real person are presented on the virtual digital human image through the motion capture collection system, so as to interact with the user.