More Like this

1. Adapting Language Models to Compress Contexts

   https://doi.org/10.18653/v1/2023.emnlp-main.232  

   Chevalier, Alexis; Wettig, Alexander; Ajith, Anirudh; Chen, Danqi (December 2023, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing)
2. Learning to compress videos without computing motion

   https://doi.org/10.1016/j.image.2022.116633  

   Chen, Meixu; Goodall, Todd; Patney, Anjul; Bovik, Alan C. (April 2022, Signal Processing: Image Communication)
3. High-Ratio Lossy Compression: Exploring the Autoencoder to Compress Scientific Data

   https://doi.org/10.1109/TBDATA.2021.3066151  

   Liu, Tong; Wang, Jinzhen; Liu, Qing; Alibhai, Shakeel; Lu, Tao; He, Xubin (January 2021, IEEE Transactions on Big Data)

   null (Ed.)
4. Neural Networks Optimally Compress the Sawbridge

   https://doi.org/10.1109/DCC50243.2021.00022  

   Wagner, Aaron B.; Balle, Johannes (March 2021, Data Compression Conference)

   null (Ed.)
5. Compress-and-Forward via Multilevel Coding

   Wan, H.; Host-Madsen, A.; Nosratinia, A. (July 2019, IEEE International Symposium on Information Theory)

   We investigate the performance of discrete (coded) modulations in the full-duplex compress-forward relay channel using multilevel coding. We numerically analyze the rates assigned to component binary codes of all levels. LDPC codes are used as the component binary codes to provide error protection. The compression at the relay is done via a nested scalar quantizer whose output is mapped to a codeword through LDPC codes. A compound Tanner graphical model and information-exchange algorithm are described for joint decoding of both messages sent from the source and relay. Simulation results show that the performance of the proposed system based on multilevel coding is better than that based on BICM, and is separated from the SNR threshold of the known CF achievable rate by two factors consisting approximately of the sum of the shaping gain (due to scalar quantization) and the separation of the LDPC code implementation from AWGN capacity. 

   more » « less