Country
B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory
We leverage ideas from Stochastic Realization Theory to develop a class of models called B'MOJO to seamlessly combine eidetic and fading memory within an elementary composable module. The overall architecture can be used to implement models that can access short-term eidetic memory "in-context," permanent structural memory "in-weights,"
Probing the Decision Boundaries of In-context Learning in Large Language Models
Recent language models, such as GPT -3+ [Brown et al., 2020, Achiam et al., 2023], have demonstrated Recent attempts to understand in-context learning have focused on various aspects. On the practical side, research has investigated the impact of different factors on in-context learning.
Activation Map Compression through Tensor Decomposition for Deep Learning
The application of low-order decomposition results in considerable memory savings while preserving the features essential for learning, and also offers theoretical guarantees to convergence.
Addressing Hidden Confounding with Heterogeneous Observational Datasets for Recommendation
The collected data in recommender systems generally suffers selection bias. Considerable works are proposed to address selection bias induced by observed user and item features, but they fail when hidden features (e.g., user age or salary) that affect
The tiny tuxedo cat who became a naval hero
A 17-year-old British sailor saved Simon from the Hong Kong docks when he was likely a year old. Breakthroughs, discoveries, and DIY tips sent six days a week. One day in March of 1948, George Hickinbottom, a British sailor, was walking around the docks of Stonecutters Island in Hong Kong. When the 17-year-old spotted a small black-and-white tuxedo cat, barely out of kittenhood, he decided to smuggle the hungry, scrawny animal aboard his ship, the HMS . Hickinbottom didn't get in trouble.
