flow matching models
PulseAugur coverage of flow matching models — every cluster mentioning flow matching models across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New framework unifies image generation capabilities; research tackles distillation challenges
Researchers have introduced DanceOPD, a novel on-policy generative field distillation framework designed to unify diverse image generation capabilities like text-to-image, local editing, and global editing within a sing…
-
New Geometry Framework Explains Phase Transitions in Generative Models
Researchers have developed a new geometric framework to understand phase transitions in continuous-state generative models like diffusion and flow-matching models. They propose that sharp transitions in generated sample…
-
New framework enables interpretable single-cell counterfactual editing
Researchers have developed scCBGM, a novel framework for interpretable single-cell counterfactual editing using concept bottleneck generative models. This approach adapts concept bottleneck architectures for single-cell…
-
New research advances flow matching models with theoretical and algorithmic improvements
Researchers have developed new theoretical foundations and practical algorithms for flow matching models, a type of generative model. One paper establishes convergence guarantees for neural network-parameterized conditi…
-
New framework uses reward optimization for concept erasure in image models
Researchers have introduced FlowErase-RL, a novel framework that reframes concept erasure in flow matching models as a reward optimization problem. This approach utilizes a dynamic dual-path reward mechanism to suppress…
-
FlowErase-RL uses reward optimization for concept erasure in image models
Researchers have introduced FlowErase-RL, a novel framework that reframes concept erasure in text-to-image generation models as a reward optimization problem. This approach utilizes a dynamic dual-path reward mechanism …
-
New watermarking embeds signals in generative model dynamics
Researchers have developed a novel watermarking technique for generative models that embeds signals directly into the learned continuous dynamics, specifically the velocity field of flow matching models. This method for…
-
TRACE framework enhances conformal prediction with diffusion and flow matching
Researchers have introduced TRACE, a novel framework for conformal prediction designed to handle multi-dimensional outputs. This method defines nonconformity by aligning transport dynamics within diffusion and flow matc…