2 papers
cs.CV2025
D2C: Unlocking the Potential of Continuous Autoregressive Image Generation with Discrete Tokens
Panpan Wang, Liqiang Niu, Fandong Meng +3
In the domain of image generation, latent-based generative models occupy a dominant status; however, these models rely heavily on image tokenizer. To meet modeling requirements, au…
cs.LG2024
Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting
Tianyi Yin, Jingwei Wang, Yunlong Ma +6
Encoding time series into tokens and using language models for processing has been shown to substantially augment the models' ability to generalize to unseen tasks. However, existi…