During the last stage of RLHF, a large language model is aligned to huma...
With multilingual machine translation (MMT) models continuing to grow in...
Image Coding for Machines (ICM) aims to compress images for AI tasks ana...
While numerous architectures for long-range language models (LRLMs) have...
Traditional media coding schemes typically encode image/video into a
sem...
Recent work in multilingual machine translation (MMT) has focused on the...
Language models are generally trained on short, truncated input sequence...
While large-scale pretrained language models have significantly improved...
Recent progress in language modeling has been driven not only by advance...
Traditional single image super-resolution (SISR) methods that focus on
s...
Over the past several years, we have witnessed the impressive progress o...
The discrepancy between maximum likelihood estimation (MLE) and task mea...
Versatile Video Coding (H.266/VVC) standard achieves better image qualit...
Recent work has questioned the importance of the Transformer's multi-hea...