相关论文: ToPSen: Task-Oriented Priming and Sensory Alignmen…

Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable inefficiencies: using excessive tokens leads to unnecessary…

Text-to-image diffusion models often struggle to achieve accurate semantic alignment between generated images and text prompts while maintaining efficiency for deployment on resource-constrained hardware. Existing approaches either incur…

Task-oriented dialogue (TOD) systems facilitate goal-driven interactions between users and machines. While recent advances in deep learning have improved the performance, TOD systems often struggle in low-resource scenarios with limited…

Context: As the demand for digital solutions adapted to different user profiles increases, creating more inclusive and diverse software development teams becomes an important initiative to improve software product accessibility. Problem:…

While vision models are highly capable, their internal mechanisms remain poorly understood -- a challenge which sparse autoencoders (SAEs) have helped address in language, but which remains underexplored in vision. We address this gap by…

Individuals who are differently-able in vision cannot proceed with their day-to-day activities as smoothly as other people do. Especially independent walking is a hard target to achieve with their visual impairment. Assistive electronic…

Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing. The primary reasons behind this are: (1) minimal efforts in…

Several problems in signal processing are addressed by expert systems which take into account a set of priors on the sought signals and systems. For instance, blind source separation is often tackled by means of a mono-objective formulation…

Tokenization is a fundamental component of language models for code. It involves breaking down the input into units that are later passed to the language model stack to learn high-dimensional representations used in various contexts, from…

Classical lens design minimizes optical aberrations to produce sharp images, but is typically decoupled from downstream computer vision tasks. Existing end-to-end optical design learns optical encoding through joint optimization, but often…

Project-based learning improves student engagement and learning outcomes, yet allocating students to appropriately challenging projects while forming cognitively diverse teams remains difficult at scale. Traditional allocation methods…

One of the major impediments to the development of new task-oriented dialogue (TOD) systems is the need for human evaluation at multiple stages and iterations of the development process. In an effort to move toward automated evaluation of…

Traditional autonomous driving pipelines decouple camera design from downstream perception, relying on fixed optics and handcrafted ISPs that prioritize human viewable imagery rather than machine semantics. This separation discards…

Vision-Language Models (VLMs) have advanced rapidly within the unified Transformer architecture, yet their deployment on resource-constrained devices remains challenging due to high computational complexity. While pruning has emerged as an…

The paper collects preparatory work for interdisciplinary collaboration between three partners, between (1) expertise in improving accessibility of studies for impaired individuals, (2) expertise in developing educational mathematics…

Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, which hurts tasks like open-vocabulary semantic segmentation; and (2) high token counts for…

People with vision impairments (VIPs) often rely on their remaining vision when interacting with user interfaces. Simulating visual impairments is an effective tool for designers, fostering awareness of the challenges faced by VIPs. While…

Code pre-trained models (CodePTMs) have recently demonstrated a solid capacity to process various software intelligence tasks, e.g., code clone detection, code translation, and code summarization. The current mainstream method that deploys…

This paper provided empirical knowledge of the user experience for using collaborative visualization in a distributed asymmetrical setting through controlled user studies. With the ability to access various computing devices, such as…

Natural human interactions for Mixed Reality Applications are overwhelmingly multimodal: humans communicate intent and instructions via a combination of visual, aural and gestural cues. However, supporting low-latency and accurate…