A compositional diffusion world model integrates three specialized memory experts via contrastive product-of-experts to improve temporal consistency, past recall, and navigation while scaling to long contexts without quadratic costs.
Neural Computation , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
LILAC+ combines context-based, adaptation-speed, and budget-to-state safety constraints to reduce violations in continual RL under nonstationary conditions, demonstrated in simulated driving tasks.
Attention-based BiLSTM classifies Steam review sentiment at 83% accuracy with interpretable attention weights highlighting key words.
citing papers explorer
-
Composition of Memory Experts for Diffusion World Models
A compositional diffusion world model integrates three specialized memory experts via contrastive product-of-experts to improve temporal consistency, past recall, and navigation while scaling to long contexts without quadratic costs.
-
Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety Constraints
LILAC+ combines context-based, adaptation-speed, and budget-to-state safety constraints to reduce violations in continual RL under nonstationary conditions, demonstrated in simulated driving tasks.
-
Enhancing Game Review Sentiment Classification on Steam Platform with Attention-Based BiLSTM
Attention-based BiLSTM classifies Steam review sentiment at 83% accuracy with interpretable attention weights highlighting key words.