Pureformer-VC: Non-parallel One-Shot Voice Conversion with Pure Transformer Blocks and Triplet Discriminative Training

Kavli Affiliate: Jia Liu | First 5 Authors: Wenhan Yao, Zedong Xing, Xiarun Chen, Jia Liu, Yongqiang He | Summary: One-shot voice conversion(VC) aims to change the timbre of any source speech to match that of the target speaker with only one speech sample. Existing style transfer-based VC methods relied on speech representation disentanglement and […]


Continue.. Pureformer-VC: Non-parallel One-Shot Voice Conversion with Pure Transformer Blocks and Triplet Discriminative Training

Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs

Kavli Affiliate: Zhuo Li | First 5 Authors: Zhuo Li, Yuhao Du, Jinpeng Hu, Xiang Wan, Anningzhe Gao | Summary: Large language models (LLMs) have shown success in generating high-quality responses. In order to achieve better alignment with LLMs with human preference, various works are proposed based on specific optimization process, which, however, is not […]


Continue.. Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs

Broad-line Region of the Quasar PG 2130+099. II. Doubling the Size Over Four Years?

Kavli Affiliate: Luis C. Ho | First 5 Authors: Zhu-Heng Yao, Sen Yang, Wei-Jian Guo, Yong-Jie Chen, Yu-Yang Songsheng | Summary: Over the past three decades, multiple reverberation mapping (RM) campaigns conducted for the quasar PG 2130+099 have exhibited inconsistent findings with time delays ranging from $sim$10 to $sim$200 days. To achieve a comprehensive understanding […]


Continue.. Broad-line Region of the Quasar PG 2130+099. II. Doubling the Size Over Four Years?

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

Kavli Affiliate: Zhuo Li | First 5 Authors: Mouxiang Chen, Lefei Shen, Zhuo Li, Xiaoyun Joy Wang, Jianling Sun | Summary: Foundation models have emerged as a promising approach in time series forecasting (TSF). Existing approaches either fine-tune large language models (LLMs) or build large-scale time-series datasets to develop TSF foundation models. However, these methods […]


Continue.. VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

Kavli Affiliate: Zhuo Li | First 5 Authors: Mouxiang Chen, Lefei Shen, Zhuo Li, Xiaoyun Joy Wang, Jianling Sun | Summary: Foundation models have emerged as a promising approach in time series forecasting (TSF). Existing approaches either repurpose large language models (LLMs) or build large-scale time series datasets to develop TSF foundation models for universal […]


Continue.. VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

Kavli Affiliate: Zhuo Li | First 5 Authors: Mouxiang Chen, Lefei Shen, Zhuo Li, Xiaoyun Joy Wang, Jianling Sun | Summary: Foundation models have emerged as a promising approach in time series forecasting (TSF). Existing approaches either repurpose large language models (LLMs) or build large-scale time series datasets to develop TSF foundation models for universal […]


Continue.. VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

Kavli Affiliate: Zhuo Li | First 5 Authors: Mouxiang Chen, Lefei Shen, Zhuo Li, Xiaoyun Joy Wang, Jianling Sun | Summary: Foundation models have emerged as a promising approach in time series forecasting (TSF). Existing approaches either repurpose large language models (LLMs) or build large-scale time series datasets to develop TSF foundation models for universal […]


Continue.. VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters