NDR-SHKF replaces the static forgetting factor in Sage-Husa Kalman Filters with a learned vector-valued memory attenuation policy from a bifurcated recurrent network trained end-to-end on whitened innovations to minimize estimation error.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
DeconDTN-Toolkit simulates provenance shifts to expose ERM vulnerabilities and provides tools plus a robust OOD indicator for mitigating confounding by data provenance.
Including copying tasks in training enables transformers to learn letter-string analogies, improving generalization to new alphabets with a 3-layer model outperforming some frontier models.
SHINE trains a scalable in-context hypernetwork to generate high-quality LoRA adapters from contexts in one pass, enabling efficient LLM adaptation that saves time and compute compared to standard fine-tuning.
A systematic evaluation of GPU memory and utilization estimators across analytical, library-based, and ML paradigms identifies key limitations in generalization, integration overhead, and hardware variability for training-aware resource management.
citing papers explorer
-
SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
SHINE trains a scalable in-context hypernetwork to generate high-quality LoRA adapters from contexts in one pass, enabling efficient LLM adaptation that saves time and compute compared to standard fine-tuning.