In this paper, we show that by employing an away-step update, similar rates can be generalized to arbitrary polytopes with strong empirical performance.

Here, we present an online version of Algo. 1, where the term'online' refers to the fact that the

We introduce Support Decomposition V ariational Inference (SDVI), a new varia-tional inference (VI) approach for probabilistic programs with stochastic support.

Here, we present an online version of Algo. 1, where the term'online' refers to the fact that the

--Conventional augmentative and alternative communication (AAC) systems and language-learning platforms often fail to adapt in real time to the user's cognitive and linguistic needs, especially in neurological conditions such as post-stroke aphasia or amyotrophic lateral sclerosis. Recent advances in noninvasive electroencephalography (EEG)-based brain-computer interfaces (BCIs) and transformer-based large language models (LLMs) offer complementary strengths: BCIs capture users' neural intent with low fatigue, while LLMs generate contextually tailored language content. Objective: We propose and evaluate a novel hybrid framework that leverages real-time EEG signals to drive an LLM-powered language rehabilitation assistant. This system aims to: (1) enable users with severe speech or motor impairments to navigate language-learning modules via mental commands; (2) dynamically personalize vocabulary, sentence-construction exercises, and corrective feedback; and (3) monitor neural markers of cognitive effort to adjust task difficulty on the fly. All individuals have the right to self-expression, social participation, and the agency to impact their environment. For individuals with complex communication needs, augmentative and alternative communication (AAC) systems provide critical tools to facilitate communication. However, traditional AAC methods--such as printed communication boards or eye gaze devices--may not be accessible for individuals with severe speech and physical impairments (SSPI).

This paper explores the implementation of SAR4SLPs (Socially Assistive Robots for Speech-Language Pathologists) to investigate aspects such as engagement, therapeutic strategy discipline, and consistent intervention support. We assessed the current application of technology to clinical and educational settings, especially with respect to how SLPs might use SAR in their therapeutic work. An asynchronous remote community (ARC) collaborated with a cohort of practicing SLPs to consider the feasibility, potential effectiveness, and anticipated challenges with implementing SARs in day-to-day interventions and as practice facilitators. We focus in particular on the expressive functionality of SARs, modeling a foundational strategy that SLPs employ across various intervention targets. This paper highlights clinician-driven insights and design implications for developing SARs that support specific treatment goals through collaborative and iterative design.

Speech is a fundamental aspect of human life, crucial not only for communication but also for cognitive, social, and academic development. Children with speech disorders (SD) face significant challenges that, if unaddressed, can result in lasting negative impacts. Traditionally, speech and language assessments (SLA) have been conducted by skilled speech-language pathologists (SLPs), but there is a growing need for efficient and scalable SLA methods powered by artificial intelligence. This position paper presents a survey of existing techniques suitable for automating SLA pipelines, with an emphasis on adapting automatic speech recognition (ASR) models for children's speech, an overview of current SLAs and their automated counterparts to demonstrate the feasibility of AI-enhanced SLA pipelines, and a discussion of practical considerations, including accessibility and privacy concerns, associated with the deployment of AI-powered SLAs.

Frank-Wolfe (FW) algorithms with linear convergence rates have recently achieved great efficiency in many applications. Garber and Meshi (2016) designed a new decomposition-invariant pairwise FW variant with favorable dependency on the domain geometry. Unfortunately it applies only to a restricted class of polytopes and cannot achieve theoretical and practical efficiency at the same time. In this paper, we show that by employing an away-step update, similar rates can be generalized to arbitrary polytopes with strong empirical performance. A new "condition number" of the domain is introduced which allows leveraging the sparsity of the solution. We applied the method to a reformulation of SVM, and the linear convergence rate depends, for the first time, on the number of support vectors.

Sign language, essential for the deaf and hard-of-hearing, presents unique challenges in translation and production due to its multimodal nature and the inherent ambiguity in mapping sign language motion to spoken language words. Previous methods often rely on gloss annotations, requiring time-intensive labor and specialized expertise in sign language. Gloss-free methods have emerged to address these limitations, but they often depend on external sign language data or dictionaries, failing to completely eliminate the need for gloss annotations. There is a clear demand for a comprehensive approach that can supplant gloss annotations and be utilized for both Sign Language Translation (SLT) and Sign Language Production (SLP). We introduce Universal Gloss-level Representation (UniGloR), a unified and self-supervised solution for both SLT and SLP, trained on multiple datasets including PHOENIX14T, How2Sign, and NIASL2021. Our results demonstrate UniGloR's effectiveness in the translation and production tasks. We further report an encouraging result for the Sign Language Recognition (SLR) on previously unseen data. Our study suggests that self-supervised learning can be made in a unified manner, paving the way for innovative and practical applications in future research.