Výsledky vyhledávání

Report

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling

Autor: Huang, Sili, Hu, Jifeng, Yang, Zhejian, Yang, Liwei, Luo, Tao, Chen, Hechang, Sun, Lichao, Yang, Bo

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement in online e

Externí odkaz: http://arxiv.org/abs/2406.00079

Zobrazit plný text záznamu

Report

Optimal Transport-Guided Conditional Score-Based Diffusion Models

Autor: Gu, Xiang, Yang, Liwei, Sun, Jian, Xu, Zongben

Conditional score-based diffusion model (SBDM) is for conditional generation of target data with paired data as condition, and has achieved great success in image translation. However, it requires the paired data as condition, and there would be insu

Externí odkaz: http://arxiv.org/abs/2311.01226

Zobrazit plný text záznamu

Reference

Yang, Liwei (1965– ) [Yang, Liwei]

Publikováno v: A Dictionary of Space Exploration, 3 ed., 2018.

Externí odkaz: http://www.oxfordreference.com/view/10.1093/acref/9780191842764.001.0001/acref-9780191842764-e-2174

Zobrazit plný text záznamu

Report

DeepFire2: A Convolutional Spiking Neural Network Accelerator on FPGAs

Autor: Aung, Myat Thu Linn, Gerlinghoff, Daniel, Qu, Chuping, Yang, Liwei, Huang, Tian, Goh, Rick Siow Mong, Luo, Tao, Wong, Weng-Fai

Brain-inspired spiking neural networks (SNNs) replace the multiply-accumulate operations of traditional neural networks by integrate-and-fire neurons, with the goal of achieving greater energy efficiency. Specialized hardware implementations of those

Externí odkaz: http://arxiv.org/abs/2305.05187

Zobrazit plný text záznamu

Report

Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learning

Autor: Yang, Liwei, Gu, Xiang, Sun, Jian

Deep networks trained on the source domain show degraded performance when tested on unseen target domain data. To enhance the model's generalization ability, most existing domain generalization methods learn domain invariant features by suppressing d

Externí odkaz: http://arxiv.org/abs/2303.01906

Zobrazit plný text záznamu