Related papers: Uncertainty-Aware Token Importance Estimation in S…

Although existing deep learning-based Ultra-Wide Band (UWB) channel estimation methods achieve high accuracy, their computational intensity clashes sharply with the resource constraints of low-cost edge devices. Motivated by this, this…

Topology inference is a powerful tool to better understand the behaviours of network systems (NSs). Different from most of prior works, this paper is dedicated to inferring the directed topology of NSs from noisy observations, where the…

Diffusion large language models promise faster generation by refining many token positions in parallel, but this parallelism introduces a hidden control problem: which proposed tokens should be transferred into the partially decoded…

Detecting and segmenting dysfluencies is crucial for effective speech therapy and real-time feedback. However, most methods only classify dysfluencies at the utterance level. We introduce StutterCut, a semi-supervised framework that…

Foundational models based on the transformer architecture are currently the state-of-the-art in general language modeling, as well as in scientific areas such as material science and climate. However, training and deploying these models is…

Prompt injection poses a critical threat to the safe deployment of large language models, yet existing detection approaches are typically evaluated under limited settings that do not reflect real-world operating constraints. In this work,…

Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e.g., pruning inattentive tokens or merging similar tokens. However, when applied to downstream tasks,…

The high dynamics and heterogeneous interactions in the complicated urban systems have raised the issue of uncertainty quantification in spatiotemporal human mobility, to support critical decision-makings in risk-aware web applications such…

As reasoning modules, such as the chain-of-thought mechanism, are applied to large language models, they achieve strong performance on various tasks such as answering common-sense questions and solving math problems. The main challenge now…

In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks. However, the traditional self-attention mechanism, which processes both…

Brain-inspired spiking neural networks (SNNs) have recently drawn more and more attention due to their event-driven and energy-efficient characteristics. The integration of storage and computation paradigm on neuromorphic hardwares makes…

The estimation of uncertainties associated with predictions from quantitative structure-activity relationship (QSAR) models can accelerate the drug discovery process by identifying promising experiments and allowing an efficient allocation…

Uncertainty reduction is vital for improving system reliability and reducing risks. To identify the best target for uncertainty reduction, uncertainty importance measure is commonly used to prioritize the significance of input variable…

Uncertainty quantification is crucial for building reliable and trustable machine learning systems. We propose to estimate uncertainty in recurrent neural networks (RNNs) via stochastic discrete state transitions over recurrent timesteps.…

Deep learning has achieved remarkable success in modeling sequential data, including event sequences, temporal point processes, and irregular time series. Recently, transformers have largely replaced recurrent networks in these tasks.…

Stochastic simulation has been widely used to analyze the performance of complex stochastic systems and facilitate decision making in those systems. Stochastic simulation is driven by the input model, which is a collection of probability…

Graph Transformers (GTs), which integrate message passing and self-attention mechanisms simultaneously, have achieved promising empirical results in graph prediction tasks. However, the design of scalable and topology-aware node…

Bidimensional spiking models currently gather a lot of attention for their simplicity and their ability to reproduce various spiking patterns of cortical neurons, and are particularly used for large network simulations. These models…

The knob tuning aims to optimize database performance by searching for the most effective knob configuration under a certain workload. Existing works suffer two significant problems. On the one hand, there exist multiple similar even…

Although vision transformers (ViT) have shown remarkable success in various vision tasks, their computationally expensive self-attention hinder their deployment on resource-constrained devices. Token reduction, which discards less important…