A conditional rectified flow matching framework learns inverse dynamics for soft robots as a generative map, cutting trajectory tracking error by more than half versus MLP, LSTM, and Transformer baselines while enabling stable high-speed open-loop execution.
Flow matching for generative modeling
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
PoDAR disentangles audio signal power from semantic content in latents using power augmentation and consistency objectives, yielding 2x faster convergence and gains of 0.055 speaker similarity and 0.22 UTMOS when applied to Stable Audio VAE with F5-TTS.
citing papers explorer
-
A Flow Matching Framework for Soft-Robot Inverse Dynamics
A conditional rectified flow matching framework learns inverse dynamics for soft robots as a generative map, cutting trajectory tracking error by more than half versus MLP, LSTM, and Transformer baselines while enabling stable high-speed open-loop execution.
-
PoDAR: Power-Disentangled Audio Representation for Generative Modeling
PoDAR disentangles audio signal power from semantic content in latents using power augmentation and consistency objectives, yielding 2x faster convergence and gains of 0.055 speaker similarity and 0.22 UTMOS when applied to Stable Audio VAE with F5-TTS.