Cover Image

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	McAllister, David, Aittala, Miika, Karras, Tero, Hellsten, Janne, Kanazawa, Angjoo, Aila, Timo, Laine, Samuli
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Neural and Evolutionary Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Analyzing and Improving the Training Dynamics of Diffusion Models
by: Karras, Tero, et al.
Published: (2023)

Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
by: Kynkäänniemi, Tuomas, et al.
Published: (2024)

Guiding a Diffusion Model with a Bad Version of Itself
by: Karras, Tero, et al.
Published: (2024)

Anytime Analysis on BinVal: Adaptive Parameters Help
by: Kötzing, Timo, et al.
Published: (2026)

Enhancing Generalization and Scalability for Multi-Objective Optimization with Population Pre-Training
by: Hong, Haokai, et al.
Published: (2023)

Benchmarking MOEAs for solving continuous multi-objective RL problems
by: Hernández, Carlos, et al.
Published: (2025)

EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning
by: Zheng, Bowen, et al.
Published: (2025)

Impact of Training Instance Selection on Automated Algorithm Selection Models for Numerical Black-box Optimization
by: Dietrich, Konstantin, et al.
Published: (2024)

Drain-Vortex Optimization: A Population-Based Metaheuristic Inspired by Multi-Drain Free-Vortex Flow
by: Omidi, Mohsen, et al.
Published: (2026)

Analysis of Search Heuristics in the Multi-Armed Bandit Setting
by: Brandt, Jasmin, et al.
Published: (2026)

Vector Symbolic Finite State Machines in Attractor Neural Networks
by: Cotteret, Madison, et al.
Published: (2022)

TT-SNN: Tensor Train Decomposition for Efficient Spiking Neural Network Training
by: Lee, Donghyun, et al.
Published: (2024)

Parallel Training in Spiking Neural Networks
by: Huang, Yanbin, et al.
Published: (2026)

Proven Advantage of Multiobjective Evolutionary Algorithms for Problems with Different Degrees of Conflict
by: Zheng, Weijie
Published: (2024)

Is the Fitness Dependent Optimizer Ready for the Future of Optimization?
by: Awlla, Ardalan H., et al.
Published: (2025)

The Effect of Training Schedules on Morphological Robustness and Generalization
by: Barba, Edoardo, et al.
Published: (2024)

Evaluating Different Fault Injection Abstractions on the Assessment of DNN SW Hardening Strategies
by: Esposito, Giuseppe, et al.
Published: (2024)

Multiplayer Battle Game-Inspired Optimizer for Complex Optimization Problems
by: Xu, Yuefeng, et al.
Published: (2023)

Online Training of Hopfield Networks using Predictive Coding
by: Ganjidoost, Ehsan, et al.
Published: (2024)

Trochoid Search Optimization
by: Layeb, Abdesslem
Published: (2023)

Flow-Lenia.png: Evolving Multi-Scale Complexity by Means of Compression
by: Adachi, Tadashi, et al.
Published: (2024)

UCPO: A Universal Constrained Combinatorial Optimization Method via Preference Optimization
by: Fang, Zhanhong, et al.
Published: (2025)

Bombardier Beetle Optimizer: A Novel Bio-Inspired Algorithm for Global Optimization
by: Shehadeh, Hisham A., et al.
Published: (2025)

Parallel Spiking Unit for Efficient Training of Spiking Neural Networks
by: Li, Yang, et al.
Published: (2024)

Multi-population GAN Training: Analyzing Co-Evolutionary Algorithms
by: Casas, Walter P., et al.
Published: (2025)

Cannistraci-Hebb Training on Ultra-Sparse Spiking Neural Networks
by: Hua, Yuan, et al.
Published: (2025)

Scaling SNNs Trained Using Equilibrium Propagation to Convolutional Architectures
by: Lin, Jiaqi, et al.
Published: (2024)

Full Integer Arithmetic Online Training for Spiking Neural Networks
by: Gomez, Ismael, et al.
Published: (2025)

MRSO: Balancing Exploration and Exploitation through Modified Rat Swarm Optimization for Global Optimization
by: Abdulla, Hemin Sardar, et al.
Published: (2024)

Spiking Brain Compression: Post-Training Second-order Compression for Spiking Neural Networks
by: Shi, Lianfeng, et al.
Published: (2025)

Directly Training Temporal Spiking Neural Network with Sparse Surrogate Gradient
by: Li, Yang, et al.
Published: (2024)

Training Deep Normalization-Free Spiking Neural Networks with Lateral Inhibition
by: Liu, Peiyu, et al.
Published: (2025)

CMA-ES for Safe Optimization
by: Uchida, Kento, et al.
Published: (2024)

Leo: Lagrange Elementary Optimization
by: Aladdin, Aso M., et al.
Published: (2023)

Evolutionary Generative Optimization: Towards Fully Data-Driven Evolutionary Optimization via Generative Learning
by: Jiang, Tao, et al.
Published: (2025)

$SpikePack$: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility
by: Shen, Guobin, et al.
Published: (2025)

Meta-Black-Box Optimization Can Do Search Guidance for Expensive Constrained Multi-Objective Optimization
by: Du, Yukun, et al.
Published: (2026)

Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks
by: Qiu, Xuerui, et al.
Published: (2023)

Efficiently Training Time-to-First-Spike Spiking Neural Networks from Scratch
by: Che, Kaiwei, et al.
Published: (2024)

Continuous-Time Neural Networks Can Stably Memorize Random Spike Trains
by: Aguettaz, Hugo, et al.
Published: (2024)