8 papers
Self-conditioned Flow Map Language Models via Fixed-point Flows
Jaehoon Yoo, Wonjung Kim, Floor Eijkelboom +4
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 est…
Posterior Refinement: Fast Language Generation via Any-Order Flow Maps
Manan Agarwal, Sheel Shah, Chanhyuk Lee +6
Non-autoregressive generation offers a powerful paradigm for iterative refinement, allowing models to recursively critique, erase and regenerate arbitrary subsets of tokens. Howeve…
Flow Map Language Models: One-step Language Modeling via Continuous Denoising
Chanhyuk Lee, Jaehoon Yoo, Manan Agarwal +6
Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive models. Despite their promise, t…
Infinite Mask Diffusion for Few-Step Distillation
Jaehoon Yoo, Wonjung Kim, Chanhyuk Lee +1
Masked Diffusion Models (MDMs) have emerged as a promising alternative to autoregressive models in language modeling, offering the advantages of parallel decoding and bidirectional…
Training-Free Refinement of Flow Matching with Divergence-based Sampling
Yeonwoo Cha, Jaehoon Yoo, Semin Kim +3
Flow-based models learn a target distribution by modeling a marginal velocity field, defined as the average of sample-wise velocities connecting each sample from a simple prior to…
ReDi: Rectified Discrete Flow
Jaehoon Yoo, Wonjung Kim, Seunghoon Hong
Discrete Flow-based Models (DFMs) are powerful generative models for high-quality discrete data but typically suffer from slow sampling speeds due to their reliance on iterative de…