AI

Disclaimer: This is part of my notes on AI research papers. I do this to learn and communicate what I understand. Feel free to comment if you have any suggestion, that would be very much appreciated. The following post is a comment on the paper The Era of 1-Bit LLMs: All Large Language Models Are in 1.58 Bits by Shuming Ma, Hongyu Wang, Lingxiao Ma, Lei Wang, Wenhui Wang, Shaohan Huang, Li Dong, Ruiping Wang, Jilong Xue, and Furu Wei....

Disclaimer: This is part of my notes on AI research papers. I do this to learn and communicate what I understand. Feel free to comment if you have any suggestion, that would be very much appreciated. The following post is a comment on the paper Bitnet: Scaling 1 Bit Transformers for Large Language Models by Hongyu Wang, Shuming Ma, Li Dong, Shaohan Huang, Huaijie Wang, Lingxiao Ma, Fang Yang, Ruiping Wang, Yi Wu, and Furu Wei....

Disclaimer: This is part of my notes on AI research papers. I do this to learn and communicate what I understand. Feel free to comment if you have any suggestion, that would be very much appreciated. The following post is a comment on the paper LlaVA-Gemma: Accelerating Multimodal Foundation Models With a Compact Language Model by Musashi Hinck, Matthew L. Olson, David Cobbley, Shao-Yen Tseng, and Vasudev Lal. Hinck et. al....

Disclaimer: This is part of my notes on AI research papers. I do this to learn and communicate what I understand. Feel free to comment if you have any suggestion, that would be very much appreciated. The following post is a comment on the paper Auto Encoding Variational Bayes by Diederik P. Kingma and Max Welling. What introduces their contributions is the following question: How can we perform efficient approximate inference and learning with directed probabilistic models whose continuous latent variables and/or parameters have intractable posterior distributions?...

Disclaimer: This is part of my notes on AI research papers. I do this to learn and communicate what I understand. Feel free to comment if you have any suggestion, that would be very much appreciated. The following post is a comment on the paper SSSE: Efficiently Erasing Samples From Trained Machine Learning Models by Alexandra Peste, Dan Alistarh, and Christoph H. Lampert. Peste et. al. propose Single-Step Sample Erasure (SSSE), a method to efficiently and effectively erase samples from trained machine learning models....