Results 61 to 70 of about 55,006 (96)

Decomposing the Training of Deep Learned Turbo codes via a Feasible MAP Decoder

International Symposium on Turbo Codes and Iterative Information Processing, 2023
Most deep-learned error-correcting codes (DL-ECCs) use binary cross-entropy (BCE) between the true input bits and the soft decoded outputs of the learned encoder/decoder pair as a loss function during training.
Abhijeet Mulgund, Natasha Devroye, György Turán, Milos Zefran   +3 more
semanticscholar   +1 more source

Robust Recovery of Structured Sparse Signals With Uncertain Sensing Matrix: A Turbo-VBI Approach

IEEE Transactions on Wireless Communications, 2020
In many applications in wireless communications, we need to recover a structured sparse signal from a linear measurement model with uncertain sensing matrix. There are two challenges of designing an algorithm framework for this problem.
An Liu, Guanying Liu, Lixiang Lian, V. Lau, Min-Jian Zhao   +4 more
semanticscholar   +1 more source

Frequency–Time Domain Turbo Equalization for Underwater Acoustic Communications

IEEE Journal of Oceanic Engineering, 2020
Hybrid turbo equalization is a novel and effective approach for communication systems as it can benefit from two turbo equalizers at different stages of iterative process.
Junyi Xi, Shefeng Yan, Lijun Xu, Zhen Zhang, Di Zeng   +4 more
semanticscholar   +1 more source

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

International Conference on Learning Representations
In this paper, we propose AutoDAN-Turbo, a black-box jailbreak method that can automatically discover as many jailbreak strategies as possible from scratch, without any human intervention or predefined scopes (e.g., specified candidate strategies), and ...
Xiaogeng Liu, Peiran Li, Edward Suh, Yevgeniy Vorobeychik, Z. Mao, Somesh Jha, P. McDaniel, Huan Sun, Bo Li, Chaowei Xiao   +9 more
semanticscholar   +1 more source

T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback

Neural Information Processing Systems
Diffusion-based text-to-video (T2V) models have achieved significant success but continue to be hampered by the slow sampling speed of their iterative sampling processes.
Jiachen Li, Weixi Feng, Tsu-Jui Fu, Xinyi Wang, Sugato Basu, Wenhu Chen, William Yang Wang   +6 more
semanticscholar   +1 more source

T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design

arXiv.org
In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model.
Jiachen Li, Qian Long, Jian Zheng, Xiaofeng Gao, Robinson Piramuthu, Wenhu Chen, William Yang Wang   +6 more
semanticscholar   +1 more source

Cloud-Assisted Cooperative Localization for Vehicle Platoons: A Turbo Approach

IEEE Transactions on Signal Processing, 2020
Due to the high resolution of angles of arrivals (AoAs) provided by the massive MIMO base station in 5 G wireless systems, it is promising to integrate 5G-based localization technology into autonomous driving to improve the accuracy and robustness of ...
An Liu, Lixiang Lian, V. Lau, Guanying Liu, Min-Jian Zhao   +4 more
semanticscholar   +1 more source

Design of Spatially Coupled Turbo Product Codes for Optical Communications

International Symposium on Turbo Codes and Iterative Information Processing, 2021
A new design is proposed for spatial coupled turbo product codes matching the challenging constraints of forward error correcting codes for optical communication applications.
G. Montorsi, S. Benedetto
semanticscholar   +1 more source

Deep residual ensemble model for predicting remaining useful life of turbo fan engines

International Journal of Turbo & Jet-Engines
Capturing degradation trends from the Condition monitored signals is a proven technique for predicting the Remining Useful Life (RUL) of the equipment, which has gained more prominence in Prognostics and Health Management (PHM) in Industry 4.0.
Sharanya Selvaraj, Jyothi Narayanan Thulasi, Muruga lal Jeyan Johnrose Vijayakumari, Karthikeyan Selvaraj   +3 more
semanticscholar   +1 more source

Improving the Halogen-Magnesium Exchange by using New Turbo-Grignard Reagents.

Chemistry, 2018
This Minireview describes the scope of the halogen-magnesium exchange. It shows that the use of the turbo-Grignard reagent (iPrMgCl⋅LiCl) greatly enhances the rate of the Br- and I-Mg exchange.
Dorothée S. Ziegler, Baosheng Wei, P. Knochel   +2 more
semanticscholar   +1 more source