COMAD discovers and reuses coordination skills from mixed offline MARL data via auto-encoders and density-based estimation to achieve continual learning with better transfer.
Kingma and Max Welling
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
Semi-discrete Flow Matching produces terminal assignment regions that are topologically simple (open, simply connected, homeomorphic to the ball under assumption) yet geometrically distinct from optimal transport Laguerre cells, as they can be non-convex with curved boundaries.
A semi-supervised VAE trained on Skyrme EOS data reconstructs equations of state with mean absolute percentage errors under 0.14% using two supervised observables (M_max, R_1.4) and one variational latent variable.
A diffusion model serves as the encoder in an autoencoder when trained alternately with the decoder to resolve opposing update directions while retaining the standard diffusion training objective.
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
DSEE is a flow-based emulator that generates stellar evolution tracks and isochrones as probabilistic outputs from a single model trained on millions of simulations, enabling fast interpolation and uncertainty-aware analyses.
MI-VAE generates physics-constrained synthetic trajectories from scarce real data to improve offline RL policy performance on planetary lander tasks over standard VAEs.
In 1D lattice φ⁴ theory, Gaussian independent Fourier mode models fail mainly from growing structured mode dependencies rather than non-Gaussian marginals, defining three regimes that mark where traditional methods remain usable.
Auto-encoder approximates SEOBNRv4 waveforms for four-parameter aligned-spin binaries, delivering 4 orders of magnitude speedup at median mismatch of 10^{-2}.
VAE models quantized for Edge TPUs deliver over 42x compression of GNSS signals with F2-score 0.915 for classifying 72 interference types, nearly matching uncompressed performance of 0.923.
citing papers explorer
-
Offline Multi-agent Continual Cooperation via Skill Partition and Reuse
COMAD discovers and reuses coordination skills from mixed offline MARL data via auto-encoders and density-based estimation to achieve continual learning with better transfer.
-
Tessellations of Semi-Discrete Flow Matching
Semi-discrete Flow Matching produces terminal assignment regions that are topologically simple (open, simply connected, homeomorphic to the ball under assumption) yet geometrically distinct from optimal transport Laguerre cells, as they can be non-convex with curved boundaries.
-
A Semi-Supervised Variational Autoencoder for Generating Neutron Star Equations of State
A semi-supervised VAE trained on Skyrme EOS data reconstructs equations of state with mean absolute percentage errors under 0.14% using two supervised observables (M_max, R_1.4) and one variational latent variable.
-
The Diffusion Encoder
A diffusion model serves as the encoder in an autoencoder when trained alternately with the decoder to resolve opposing update directions while retaining the standard diffusion training objective.
-
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
-
Dartmouth Stellar Evolution Emulator (DSEE) 1: Generative Stellar Evolution Model Database
DSEE is a flow-based emulator that generates stellar evolution tracks and isochrones as probabilistic outputs from a single model trained on millions of simulations, enabling fast interpolation and uncertainty-aware analyses.
-
Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models
MI-VAE generates physics-constrained synthetic trajectories from scarce real data to improve offline RL policy performance on planetary lander tasks over standard VAEs.
-
When Independent Gaussian Models Break Down: Characterizing Regime-Dependent Modeling Failures in $\phi^4$ Theory
In 1D lattice φ⁴ theory, Gaussian independent Fourier mode models fail mainly from growing structured mode dependencies rather than non-Gaussian marginals, defining three regimes that mark where traditional methods remain usable.
-
Auto-encoder model for faster generation of effective one-body gravitational waveform approximations
Auto-encoder approximates SEOBNRv4 waveforms for four-parameter aligned-spin binaries, delivering 4 orders of magnitude speedup at median mismatch of 10^{-2}.
-
GenAI for Energy-Efficient and Interference-Aware Compressed Sensing of GNSS Signals on a Google Edge TPU
VAE models quantized for Edge TPUs deliver over 42x compression of GNSS signals with F2-score 0.915 for classifying 72 interference types, nearly matching uncompressed performance of 0.923.
- Inverse Design of Inorganic Compounds with Generative AI