Genre
CIFD: Controlled Information Flow to Enhance Knowledge Distillation
Knowledge Distillation is the mechanism by which the insights gained from a larger teacher model are transferred to a smaller student model.
Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation Haoran Chen 1,2 Xintong Han 3 Zuxuan Wu1,2 Y u-Gang Jiang
Then, MP A denoises the learned prompts through an auto-encoding process and aligns them by maximizing the agreement of all the reconstructed prompts.
Breaking the Communication-Privacy-Accuracy Tradeoff with f-Differential Privacy
On one hand, the local data of users may contain sensitive information, and privacy-preserving mechanisms are needed.
Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems
While agents' learning is data-driven, sampling from millions
State-space Models with Layer-wise Nonlinearity are Universal Approximators with Exponential Decaying Memory
State-space models have gained popularity in sequence modelling due to their simple and efficient network structures. However, the absence of nonlinear activation along the temporal direction limits the model's capacity.