Related papers: KeySense: LLM-Powered Hands-Down, Ten-Finger Typin…

We present CoSense-LLM, an edge-first framework that turns continuous multimodal sensor streams (for example Wi-Fi CSI, IMU, audio, RFID, and lightweight vision) into compact, verifiable semantic tokens and coordinates with large language…

Sensors (e.g., light, gyroscope, accelerometer) and sensing-enabled applications on a smart device make the applications more user-friendly and efficient. However, the current permission-based sensor management systems of smart devices only…

Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintain performance. Existing methods use random linear hashing to…

Tactile sensing is critical in advanced interactive systems by emulating the human sense of touch to detect stimuli. Vision-based tactile sensors are promising for providing multimodal capabilities and high robustness, yet existing…

Equal access to digital technologies is critical for education, employment, and social participation. However, mainstream interfaces are visually oriented, creating steep learning curves and frequent obstacles for screen reader users, and…

Keystroke biometrics is a promising approach for user identification and verification, leveraging the unique patterns in individuals' typing behavior. In this paper, we propose a Transformer-based network that employs self-attention to…

Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks, yet their ability to perform multi-step logical reasoning remains an open challenge. Although Chain-of-Thought prompting has…

Autistic individuals often experience difficulties in conveying and interpreting emotional tone and non-literal nuances. Many also mask their communication style to avoid being misconstrued by others, spending considerable time and mental…

We study the performance and user experience of two popular mainstream text entry devices, desktop keyboards and touchscreen keyboards, for use in Virtual Reality (VR) applications. We discuss the limitations arising from limited visual…

Large vision-language models (VLMs) enable joint processing of text and images. However, incorporating vision data significantly increases the prompt length, resulting in a longer time to first token (TTFT). This bottleneck can be…

Weakly-supervised text classification trains a classifier using the label name of each target class as the only supervision, which largely reduces human annotation efforts. Most existing methods first use the label names as static…

A touch sensitive screen displays the information on the screen and also receives the input by sensing a user's touch on the same screen. This mechanism facilitates system interaction directly through the screen without needing a mouse or…

Large Language Models (LLMs) are increasingly integrated into everyday applications, but their prevalent cloud-based deployment raises growing concerns around data privacy and long-term sustainability. Running LLMs locally on mobile and…

Prompting is the primary way to utilize the multitask capabilities of language models (LMs), but prompts occupy valuable space in the input context window, and repeatedly encoding the same prompt is computationally inefficient. Finetuning…

Universal jamming grippers excel at grasping unknown objects due to their compliant bodies. Traditional tactile sensors can compromise this compliance, reducing grasping performance. We present acoustic sensing as a form of morphological…

The behavior of LLMs does not depend solely on the model itself. Components of the inference system, such as the inference engine, attention backend, and hardware platform, subtly influence how inputs are processed. These components differ…

Large Language Models (LLMs) can generate text by transferring style attributes like formality resulting in formal or informal text. However, instructing LLMs to generate text that when spoken, is more intelligible in an acoustically…

It is well known that LLM-based systems are data-hungry. Recent LLM-based TTS works typically employ complex data processing pipelines to obtain high-quality training data. These sophisticated pipelines require excellent models at each…

Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which…

Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with…