Genre
Transductive Learning Is Compact
We demonstrate that supervised learning in the transductive model enjoys such structure.
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