English
Related papers

Related papers: Fast Beam Training and Performance Analysis for Ex…

200 papers

Millimeter-wave communications rely on beamforming gain from both transmitters and receivers to compensate for severe propagation loss. To achieve adequate gain, beam training is required to identify propagation directions. The main…

Signal Processing · Electrical Eng. & Systems 2020-04-06 Han Yan , Veljko Boljanovic , Danijela Cabric

The training of large language models (LLMs) is expensive. In this paper, we study data-efficient approaches for pre-training LLMs, i.e., techniques that aim to optimize the Pareto frontier of model quality and training resource/data…

The transition to Extremely Large Antenna Arrays (ELAA) in 6G introduces significant near-field effects, necessitating robust near-field beam training strategies in multi-path environments. Because signal phases are frequently compromised…

Signal Processing · Electrical Eng. & Systems 2026-03-10 Zijun Wang , Shawn Tsai , Ye Hu , Rui Zhang

This paper presents a novel radio frequency (RF) beam training algorithm for sparse multiple input multiple output (MIMO) channels using unitary RF beamforming codebooks at transmitter (Tx) and receiver (Rx). The algorithm leverages…

Information Theory · Computer Science 2022-11-22 Krishan K. Tiwari , Eckhard Grass , John S. Thompson , Rolf Kraemer

Large Language Models (LLMs) have achieved remarkable success across diverse applications, yet their deployment remains challenging due to substantial computational costs, memory requirements, and energy consumption. Recent empirical…

Machine Learning · Computer Science 2026-03-24 Kaito Tanaka , Masato Ito , Yuji Nishimura , Keisuke Matsuda , Aya Nakayama

Millimeter-wave communication has the potential to deliver orders of magnitude increases in mobile data rates. A key design challenge is to enable rapid beam alignment with phased arrays. Traditional millimeter-wave systems require a high…

Signal Processing · Electrical Eng. & Systems 2020-10-06 Han Yan , Benjamin W. Domae , Danijela Cabric

The natural integration of extremely large antenna arrays (ELAAs) and terahertz (THz) communications can potentially achieve Tbps data rates in 6G networks. However, due to the extremely large array aperture and wide bandwidth, a new…

Information Theory · Computer Science 2024-06-04 Mingyao Cui , Linglong Dai

The phenomena of Spectral Bias, where the higher frequency components of a function being learnt in a feedforward Artificial Neural Network (ANN) are seen to converge more slowly than the lower frequencies, is observed ubiquitously across…

Machine Learning · Computer Science 2023-07-20 Kaumudi Joshi , Vukka Snigdha , Arya Kumar Bhattacharya

Approximate computing methods have shown great potential for deep learning. Due to the reduced hardware costs, these methods are especially suitable for inference tasks on battery-operated devices that are constrained by their power budget.…

Machine Learning · Computer Science 2023-04-11 Tianmu Li , Shurui Li , Puneet Gupta

Beam training based on hierarchical codebook for millimeter wave (mmWave) massive MIMO is investigated. Unlike the existing work using the same hierarchical codebook to estimate different multi-path components (MPCs), dynamic hierarchical…

Signal Processing · Electrical Eng. & Systems 2019-01-08 Kangjian Chen , Chenhao Qi

Combining millimetre-wave (mmWave) communications with an extremely large-scale antenna array (ELAA) presents a promising avenue for meeting the spectral efficiency demands of the future sixth generation (6G) mobile communications. However,…

Information Theory · Computer Science 2024-04-25 Wang Liu , Cunhua Pan , Hong Ren , Cheng-Xiang Wang , Jiangzhou Wang , Xiaohu You

Millimeter-Wave (mm-Wave) frequency bands provide an opportunity for much wider channel bandwidth compared with the traditional sub-6 GHz band. Communication at mm-Waves is, however, quite challenging due to the severe propagation path…

Information Theory · Computer Science 2017-10-19 Xiaoshen Song , Saeid Haghighatshoar , Giuseppe Caire

As one popular modeling approach for end-to-end speech recognition, attention-based encoder-decoder models are known to suffer the length bias and corresponding beam problem. Different approaches have been applied in simple beam search to…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-24 Wei Zhou , Ralf Schlüter , Hermann Ney

Training Large Language Models (LLMs) incurs significant cost; hence, any strategy that accelerates model convergence is helpful. In this paper, we investigate the ability of a simple idea checkpoint averaging along the trajectory of a…

Machine Learning · Computer Science 2023-12-13 Sunny Sanyal , Atula Neerkaje , Jean Kaddour , Abhishek Kumar , Sujay Sanghavi

LoRA is a technique that reduces the number of trainable parameters in a neural network by introducing low-rank adapters to linear layers. This technique is used both for fine-tuning and full training of large language models. This paper…

Machine Learning · Computer Science 2024-06-17 Daria Cherniuk , Aleksandr Mikhalev , Ivan Oseledets

High entropy alloys (HEA) represent a class of materials with promising properties, such as high strength and ductility, radiation damage tolerance, etc. At the same time, a combinatorially large variety of compositions and a complex…

Materials Science · Physics 2025-10-03 Franco Moitzi , Lorenz Romaner , Andrei V. Ruban , Oleg E. Peil

The training and fine-tuning of large language models (LLMs) often involve diverse textual data from multiple sources, which poses challenges due to conflicting gradient directions, hindering optimization and specialization. These…

Computation and Language · Computer Science 2025-02-04 Yinghao Li , Vianne Gao , Chao Zhang , MohamadAli Torkamani

In this paper, multiuser beam training based on hierarchical codebook for millimeter wave massive multi-input multi-output is investigated, where the base station (BS) simultaneously performs beam training with multiple user equipments…

Information Theory · Computer Science 2025-11-17 Chenhao Qi , Kangjian Chen , Octavia A. Dobre , Geoffrey Ye Li

Beam training of 802.11 ad is a technology that helps accelerate the analog weighting vector (AWV) selection process under the constraint of the existing code-book for AWV. However, 5G milli-meter wave (mmWave)…

Information Theory · Computer Science 2022-11-30 Lyutianyang Zhang , Sumit Roy

Optimal hyperparameter selection is critical for maximizing the performance of neural networks in computer vision, particularly as architectures become more complex. This work explores the use of large language models (LLMs) for…

Machine Learning · Computer Science 2025-09-30 Roman Kochnev , Arash Torabi Goodarzi , Zofia Antonina Bentyn , Dmitry Ignatov , Radu Timofte