sequence models
PulseAugur coverage of sequence models — every cluster mentioning sequence models across labs, papers, and developer communities, ranked by signal.
-
In-Context Learning Explored for AI Intrinsic Curiosity
Researchers have explored whether in-context learning (ICL) capabilities of sequence models can support intrinsic curiosity in machine learning. While traditional methods for automated data selection, or "intrinsic curi…
-
New method improves sequence model state tracking over long horizons
Researchers have developed a novel method for state tracking in sequence models, addressing limitations in handling long-horizon, non-abelian transformations. Their approach, a held-out transition-pair falsifier, trains…
-
New SHARP framework enhances AI's long-range temporal pattern recognition
Researchers have introduced SHARP, a novel framework designed to improve how sequence models learn long-range temporal patterns in streaming data. SHARP separates memory accumulation from pattern recognition, allowing f…
-
New Paper Formalizes Sufficiency Gap in Sequence Models
A new research paper introduces a formal mathematical framework to address the "sufficiency gap" in sequence models, particularly concerning their ability to handle unobserved latent states. The paper proposes an extern…