Related papers: Fast and flexible selection with a single switch
Spiking neural networks (SNNs) offer an energy-efficient alternative to traditional neural networks due to their event-driven computing paradigm. However, recent advancements in spiking transformers have focused on improving accuracy with…
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…
We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks. Our approach introduces enhancement across several dimensions: By adopting Shifted Window Attention with zero-initialization, we achieve cross-window…
Task-free online continual learning has recently emerged as a realistic paradigm for addressing continual learning in dynamic, real-world environments, where data arrive in a non-stationary stream without clear task boundaries and can only…
We give new bounds for the single-nomination model of impartial selection, a problem proposed by Holzman and Moulin (Econometrica, 2013). A selection mechanism, which may be randomized, selects one individual from a group of $n$ based on…
The development of the industrial Internet of Things (IoT) calls for higher spectrum efficiency (SE). Faster than Nyquist (FTN) and non-orthogonal multiple access (NOMA) are both promising paradigms to improve the SE without any extra…
The attention mechanism in text generation is memory-bounded due to its sequential characteristics. Therefore, off-chip memory accesses should be minimized for faster execution. Although previous methods addressed this by pruning…
This paper proposes a portable hardware token for user authentication, it is based on the use of keystroke dynamics to verify users in a bio-metric manner. The proposed approach allows for a multifactor authentication scheme in which users…
In order to avoid the "Midas Touch" problem, gaze-based interfaces for selection often introduce a dwell time: a fixed amount of time the user must fixate upon an object before it is selected. Past interfaces have used a uniform dwell time…
Sparse decision tree learning provides accurate and interpretable predictive models that are ideal for high-stakes applications by finding the single most accurate tree within a (soft) size limit. Rather than relying on a single "best"…
This paper introduces a novel interaction method for virtual and augmented reality called look-and-twist, which is directly analogous to point-and-click operations using a mouse and desktop. It is based on head rotation alone and is…
The annotation of large scale histopathology image datasets remains a major bottleneck in developing robust deep learning models for clinically relevant tasks, such as mitotic figure classification. Folder-based annotation workflows are…
Inspired by the principles of speed reading, we introduce Skim-RNN, a recurrent neural network (RNN) that dynamically decides to update only a small fraction of the hidden state for relatively unimportant input tokens. Skim-RNN gives…
The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN…
Non-orthogonal multiple access (NOMA) technique is important for achieving a high data rate in next-generation wireless communications. A key challenge to fully utilizing the effectiveness of the NOMA technique is the optimization of the…
Interactive image segmentation algorithms rely on the user to provide annotations as the guidance. When the task of interactive segmentation is performed on a small touchscreen device, the requirement of providing precise annotations could…
Recently presented Token-Oriented Object Notation (TOON) aims to replace JSON as a serialization format for passing structured data to LLMs with significantly reduced token usage. While showing solid accuracy in LLM comprehension, there is…
Text-to-motion generation, which translates textual descriptions into human motions, has been challenging in accurately capturing detailed user-imagined motions from simple text inputs. This paper introduces StickMotion, an efficient…
This work presents One-press control, a tactile input method for pressure-sensitive keyboards based on the detection and classification of pressing movements on the already held-down key. To seamlessly integrate the added control input with…
User modeling is important for news recommendation. Existing methods usually first encode user's clicked news into news embeddings independently and then aggregate them into user embedding. However, the word-level interactions across…