Related papers: LiQSS: Post-Transformer Linear Quantum-Inspired St…
We introduce Pointer, a novel architecture that achieves linear $O(NK)$ complexity for long-range sequence modeling while maintaining superior performance without requiring pre-training. Unlike standard attention mechanisms that compute…
State-space models effectively model multivariate time series by updating over time a representation of the system state from which predictions are made. The state representation is usually a vector without any explicit structure.…
Post-training quantization makes large reasoning models practical under tight memory and latency budgets, but it can distort the online signals that drive adaptive test-time compute allocation. Under a fixed cap on the number of newly…
A proper parametrization of state transition matrices of linear state-space models (SSMs) followed by standard nonlinearities enables them to efficiently learn representations from sequential data, establishing the state-of-the-art on a…
Transformer has been successfully applied to speech separation recently with its strong long-dependency modeling capacity using a self-attention mechanism. However, Transformer tends to have heavy run-time costs due to the deep encoder…
While the researchers have set their sights on future wireless networks of 2030, communications through reconfigurable intelligent surfaces (RISs) appears as one of the potential enabling technologies for 6G wireless networking. This…
Predicting performance-related behavior of the underlying network structure becomes more and more indispensable in terms of the aspired application outcome quality. However, the reliable forecast of QoS metrics like packet transfer delay in…
There has been a recent surge of interest in time series modeling using the Transformer architecture. However, forecasting multivariate time series with Transformer presents a unique challenge as it requires modeling both temporal…
To enable an intelligent, programmable and multi-vendor radio access network (RAN) for 6G networks, considerable efforts have been made in standardization and development of open RAN (O-RAN). So far, however, the applicability of O-RAN in…
Reconfigurable intelligent surface (RIS)-assisted communication appears as one of the potential enablers for sixth generation (6G) wireless networks by providing a new way to optimize the communication system performance. This paper aims to…
Reconfigurable intelligent surfaces (RISs) modify signal reflections to enhance wireless communication capabilities. Classical RIS phase optimization is highly non convex and challenging in dynamic environments due to high interference and…
The attention-based Transformer model has achieved promising results for speech recognition (SR) in the offline mode. However, in the streaming mode, the Transformer model usually incurs significant latency to maintain its recognition…
The traditional black-box and monolithic approach to Radio Access Networks (RANs) has heavily limited flexibility and innovation. The Open RAN paradigm, and the architecture proposed by the O-RAN ALLIANCE, aim to address these limitations…
Future 6G networks envisions to blur the line between communication and sensing, leveraging ubiquitous OFDM waveforms for both high throughput data and environmental awareness. In this work, we do a thorough analysis of Communication based…
This study investigates the integration of a high altitude platform station (HAPS), a non-terrestrial network (NTN) node, into the cell-switching paradigm for energy saving. By doing so, the sustainability and ubiquitous connectivity…
Reconfigurable intelligent surfaces (RISs) have emerged as a promising technology to enhance the performance of sixth-generation (6G) and beyond communication systems. The passive nature of RISs and their large number of reflecting elements…
Temporal network link prediction is an important task in the field of network science, and has a wide range of applications in practical scenarios. Revealing the evolutionary mechanism of the network is essential for link prediction, and…
Multivariate time series prediction has applications in a wide variety of domains and is considered to be a very challenging task, especially when the variables have correlations and exhibit complex temporal patterns, such as seasonality…
We introduce a variational wave function based on Neural-Network Quantum States (NQS) to study lattice systems whose local Hilbert space contains both spin and fermionic degrees of freedom. Our approach is based on the use of the…
Efficiently serving neural network models with low latency is becoming more challenging due to increasing model complexity and parameter count. Model quantization offers a solution which simultaneously reduces memory footprint and compute…