DFM-VLA uses discrete flow matching to iteratively refine action tokens in VLA models, outperforming autoregressive and diffusion baselines with 4.44 average success length on CALVIN and 95.7% success on LIBERO.
Edit flows: Flow matching with edit operations.arXiv preprint arXiv:2506.09018
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
Derives exact guidance transition rates for discrete flow matching models that require only one model evaluation per sampling step and unify prior approximation-based methods.
A masked discrete diffusion model adds token editing at inference and grouped cross-entropy training to reach 0.90 GenEval, 86.9 DPG, and 10.76 HPSv3 scores.
CTC-seeded variable-length edit refinement with a diffusion-based Edit Flow decoder achieves WER reductions in non-autoregressive ASR using only two inference steps plus classifier-free guidance.
Enhances Discrete Flow Matching with domain-specific couplings, latent edit-based rates, latent classifier-free guidance, and temperature scaling to reach SOTA on DNA and peptide sequence tasks.
EditSR improves neural symbolic regression accuracy on complex expressions by pretraining an edit-based rectifier on state-transition correction chains that enforce syntactic validity and condition edits only on the current expression state.
Morph is a flexible-size 3D molecular generative model using unbalanced optimal transport on geometric graphs that matches fixed-size SOTA performance while enabling out-of-distribution generation.
ME-DLM augments parallel masked diffusion models with edit-distance-supervised refinements to raise quality on coding and math benchmarks while using far fewer diffusion steps.
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
A new tree-conditioned edit-flow model for ancestral sequence reconstruction achieves reasonable accuracy on substitution-only evolved sequences and superior localization of changes on natural indel-rich sequences.
DPLM-Evo introduces an evolutionary discrete diffusion framework with explicit edit prediction and contextual noising that claims SOTA single-sequence mutation effect prediction on ProteinGym while supporting variable-length evolution simulation.
citing papers explorer
-
EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification
EditSR improves neural symbolic regression accuracy on complex expressions by pretraining an edit-based rectifier on state-transition correction chains that enforce syntactic validity and condition edits only on the current expression state.