Discrete Flow Matching
PulseAugur coverage of Discrete Flow Matching — every cluster mentioning Discrete Flow Matching across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New H-Glow framework accelerates graph generation using hazard guidance
Researchers have developed H-Glow, a new framework designed to accelerate graph generation using hazard-guided discrete flow matching. This approach decomposes continuous-time Markov chain generators into hazards and co…
-
New Trajectory Matching Method Enhances Discrete Generation in ML
Researchers have introduced a new method called trajectory matching for discrete flow matching (DFM) in machine learning. This approach allows for more complex and structured discrete generation actions, such as attachi…
-
DFM-VLA introduces iterative action refinement for robot manipulation
Researchers have introduced DFM-VLA, a novel approach for robot manipulation that utilizes discrete flow matching to iteratively refine action tokens. Unlike previous methods that fix tokens once generated, DFM-VLA mode…
-
New research explores discrete flow matching and RL for generative models
Two research papers explore advancements in generative modeling, focusing on discrete structures and flow-based models. The first paper introduces context-weighted discrete flow matching to improve generation quality on…
-
New TR-CIE sampler enhances discrete flow matching quality with limited function evaluations · 3 sources tracked
Researchers have developed a new sampling method called the Time-Reparameterized Cumulative Intensity Extrapolation (TR-CIE) sampler for discrete flow matching (DFM). This method aims to enhance sampling quality in gene…
-
New TTS research explores discrete flow matching for efficiency
Two new research papers explore advancements in zero-shot text-to-speech (TTS) technology, focusing on discrete flow matching techniques. The first paper introduces DiFlow-TTS, a framework that uses a discrete flow matc…
-
New DFM framework advances biological sequence design
Researchers have developed a new generative framework called Discrete Flow Matching (DFM) for designing biological sequences. This enhanced DFM incorporates domain-specific preferences and a latent edit-based parameteri…