4 papers
Parameter-Efficient Distributional RL via Normalizing Flows and a Geometry-Aware Cramér Surrogate
Simo Alami C., Rim Kaddah, Jesse Read +1
Distributional Reinforcement Learning (DistRL) improves upon expectation-based methods by modeling full return distributions, but standard approaches often remain far from parsimon…
ReConForM : Real-time Contact-aware Motion Retargeting for more Diverse Character Morphologies
Théo Cheynel, Thomas Rossi, Baptiste Bellot-Gurlet +2
Preserving semantics, in particular in terms of contacts, is a key challenge when retargeting motion between characters of different morphologies. Our solution relies on a low-dime…
Analysis of Classifier-Free Guidance Weight Schedulers
Xi Wang, Nicolas Dufour, Nefeli Andreou +4
Classifier-Free Guidance (CFG) enhances the quality and condition adherence of text-to-image diffusion models. It operates by combining the conditional and unconditional prediction…
LEAD: Latent Realignment for Human Motion Diffusion
Nefeli Andreou, Xi Wang, Victoria Fernández Abrevaya +3
Our goal is to generate realistic human motion from natural language. Modern methods often face a trade-off between model expressiveness and text-to-motion alignment. Some align te…