paper-with-me

Papers

D-Flow: Differentiating through Flows for Controlled Generation

2024-02-21 · Heli Ben-Hamu, Omri Puny, Itai Gat, Brian Karrer, Uriel Singer, Yaron Lipman

Taming the generation outcome of state of the art Diffusion and Flow-Matching (FM) models without having to re-train a task-specific model unlocks a powerful tool for solving inverse problems, conditional generation, and controlled generation in general. In this work we introduce D-Flow, a simple framework for controlling the generation process by differentiating through the flow, optimizing for the source (noise) point. We motivate this framework by our key observation stating that for Diffusion/FM models trained with Gaussian probability paths, differentiating through the generation process projects gradient on the data manifold, implicitly injecting the prior into the optimization process. We validate our framework on linear and non-linear controlled generation problems including: image and audio inverse problems and conditional molecule generation reaching state of the art performance across all.

📄 PDF Abstract BibTeX arXiv:2402.14017

Code (2)

annegnx/PnP-Flow jax
feifeiobama/RectifID pytorch

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Normalizing Flows for Knockoff-free Controlled Feature Selection

2021-06-03 · Derek Hansen, Brian Manzo, Jeffrey Regier

Controlled feature selection aims to discover the features a response depends on while limiting the false discovery rate (FDR) to a predefined level. Recently, multiple deep-learning-based methods have been proposed to p…

Density Estimationfeature selectionvalid

Training Free Guided Flow Matching with Optimal Control

2024-10-23 · Luran Wang, Chaoran Cheng, Yizhen Liao, Yanru Qu 외

Controlled generation with pre-trained Diffusion and Flow Matching models has vast applications. One strategy for guiding ODE-based generative models is through optimizing a target loss $R(x_1)$ while staying close to th…

Image ManipulationProtein Design

Compos3D: Interactive Part-Based Composition for Creative Control in Generative 3D Models

2026-07-13 · Faraz Faruqi, Sean J. Liu, George Fitzmaurice, Justin Matejka arxiv

While generative AI has unlocked new opportunities for 3D content creation, current workflows often rely on multiple regenerations, which provides limited control and unpredictable outcomes. We present Compos3D, a system…

OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows

2025-10-03 · John Nguyen, Marton Havasi, Tariq Berrada, Luke Zettlemoyer 외 arxiv

We present OneFlow, the first non-autoregressive multimodal model that enables variable-length and concurrent mixed-modal generation. Unlike autoregressive models that enforce rigid causal ordering between text and image…

Image Generation

ChannelFlow-Tools: A Configuration-Driven Pipeline for Generating Machine-Learning-Ready Datasets of 3D Obstructed Channel Flows

2025-09-17 · Shubham Kavane, Kajol Kulkarni, Harald Koestler arxiv

Data-driven surrogate models are increasingly used in computational fluid dynamics, and their reliability depends on the quality of the training data. These models are typically trained on fixed, pre-generated datasets. …