Abstract: Effective movement primitives should be capable of encoding and generating a rich repertoire of trajectories conditioned on task-defining parameters such as vision or language inputs. While ...
This paper presents FLOAT, an audio-driven talking portrait video generation method based on flow matching generative model. We shift the generative modeling from the pixel-based latent space to a ...
Abstract: Deep generative models provide a promising approach to de novo 3D peptide design. Most of them jointly model the distributions of peptide's position, orientation, and conformation, ...
CEO Spencer Rascoff highlighted the completion of the company's reset phase and emphasized the transition into revitalizing product experiences, stating, "We completed the reset phase by putting user ...
FMPose3D creates a 3D pose from a single 2D image. It leverages fast Flow Matching, generating multiple plausible 3D poses via an ODE in just a few steps, then aggregates them using a ...
We introduce CoVoMix2: a fully non-autoregressive framework for zero-shot multi-talker dialogue generation. It directly predicts mel-spectrograms from multi-stream transcriptions using a flow-matching ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results