arXiv AI
Gumbel Straight Flow: Distilling Autoregressive Models into One-step Flow Maps
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 2
Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition
arXiv:2607. 00535v1 Announce Type: cross Abstract: Few-step flow-map generators, such as consistency models and MeanFlow, accelerate sampling by directly learning long-range transport maps between noise and data.
arXiv Machine Learning
Sep 15
Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning
Discrete Beckmann Transport Models (DBTM) are introduced as a new type of discrete diffusion and flow model that can generate language in a single step by mapping any point to a fixed point on the simplex vertices. Unlike previous approaches, DBTM eliminates the need for a pretrained teacher model and time conditioning by minimizing a conservation equation directly from data. The model can be partially trained and iterated until convergence, and it can be extended to a partial‑context interpolant that refines outputs with additional function evaluations. Experiments on language modeling and reasoning tasks show that DBTM achieves higher quality and accuracy than existing discrete diffusion and continuous flow baselines.
arXiv AI
Sep 2
Training-Free Refinement of Flow Matching with Divergence-based Sampling
The paper introduces Flow Divergence Sampler (FDS), a training‑free method that refines intermediate states in flow‑matching models by using the divergence of the marginal velocity field to detect and correct misguidance toward low‑density regions. FDS operates during inference, requires no additional training, and can be applied as a plug‑and‑play module with standard solvers and existing flow backbones. Experiments show that FDS consistently improves fidelity in tasks such as text‑to‑image synthesis and inverse problems.
arXiv Machine Learning
Jun 29
Masked Language Flow Models
arXiv:2606. 27617v1 Announce Type: cross Abstract: Masked Diffusion Models (MDMs) promise fast, parallel language generation, but their reverse transition factorises across token positions -- an approximation that breaks down in the few-step sampling regime where parallel generation ought to provide the greatest efficiency gains.
arXiv AI
Jul 2
Self-conditioned Flow Map Language Models via Fixed-point Flows
arXiv:2607. 00714v1 Announce Type: cross Abstract: Self-conditioning is a core technique that enhances continuous flow-based language models, where the model learns to denoise generated text by conditioning on its own denoising estimate.
arXiv AI
3d ago
Acceleration of Diffusion Language Model through Discrete Average Generator
arXiv:2609.38364v1 Announce Type: cross Abstract: Discrete diffusion models and flow matching have emerged as powerful frameworks for generative modeling over discrete state spaces, yet efficient few...