MATE uses permutation-invariant sum-aggregated memory of transition embeddings to solve CMDPs with online adaptation and computational advantages over Transformers and RNNs.
IEEE transactions on neural networks , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Fully Looped Transformer stabilizes looped transformer training up to 12 iterations via fully looped architecture and attention injection, yielding up to 13.2% better downstream performance.
LLMs disperse meaning-preserving prompts internally instead of clustering them, which produces an excessively high upper bound on output log-probability differences via Taylor expansion and Cauchy-Schwarz.
citing papers explorer
-
MATE: Solving Contextual Markov Decision Processes with Memory of Accumulated Transition Embeddings
MATE uses permutation-invariant sum-aggregated memory of transition embeddings to solve CMDPs with online adaptation and computational advantages over Transformers and RNNs.
-
Simply Stabilizing the Loop via Fully Looped Transformer
Fully Looped Transformer stabilizes looped transformer training up to 12 iterations via fully looped architecture and attention injection, yielding up to 13.2% better downstream performance.
-
Understanding the Prompt Sensitivity
LLMs disperse meaning-preserving prompts internally instead of clustering them, which produces an excessively high upper bound on output log-probability differences via Taylor expansion and Cauchy-Schwarz.