10 papers
One-Step Generation via Riemannian Wasserstein Gradient Flows
David Li, Chanhyuk Lee, Jaehoon Yoo +7
Recently, Drifting Models and Wasserstein Gradient Flows have attracted substantial attention because they move iterative distributional refinement to training and amortize it into…
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…
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…
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…
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…
Reward-Agnostic Prompt Optimization for Text-to-Image Diffusion Models
Semin Kim, Yeonwoo Cha, Jaehoon Yoo +1
We investigate a general approach for improving user prompts in text-to-image (T2I) diffusion models by finding prompts that maximize a reward function specified at test-time. Alth…
Simulation-Free Training of Neural ODEs on Paired Data
Semin Kim, Jaehoon Yoo, Jinwoo Kim +3
In this work, we investigate a method for simulation-free training of Neural Ordinary Differential Equations (NODEs) for learning deterministic mappings between paired data. Despit…
Learning to Compose: Improving Object Centric Learning by Injecting Compositionality
Whie Jung, Jaehoon Yoo, Sungjin Ahn +1
Learning compositional representation is a key aspect of object-centric learning as it enables flexible systematic generalization and supports complex visual reasoning. However, mo…