Cover Image

Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Karczewski, Rafał, Heinonen, Markus, Garg, Vikas
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Diffusion Models as Cartoonists: The Curious Case of High Density Regions
by: Karczewski, Rafał, et al.
Published: (2024)

What Ails Generative Structure-based Drug Design: Expressivity is Too Little or Too Much?
by: Karczewski, Rafał, et al.
Published: (2024)

The Spacetime of Diffusion Models: An Information Geometry Perspective
by: Karczewski, Rafał, et al.
Published: (2025)

Let Physics Guide Your Protein Flows: Topology-aware Unfolding and Generation
by: Verma, Yogesh, et al.
Published: (2025)

VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning
by: Zong, Yongshuo, et al.
Published: (2024)

ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs
by: Verma, Yogesh, et al.
Published: (2024)

Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models
by: Laabid, Najwa, et al.
Published: (2024)

The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs
by: Dickson, Craig
Published: (2025)

Diffusion Twigs with Loop Guidance for Conditional Graph Generation
by: Mercatali, Giangiacomo, et al.
Published: (2024)

Margin-calibrated Classifier Guidance for Property-driven Synthesis Planning
by: Laabid, Najwa, et al.
Published: (2026)

Improving Discrete Diffusion Models via Structured Preferential Generation
by: Rissanen, Severi, et al.
Published: (2024)

From Core to Detail: Unsupervised Disentanglement with Entropy-Ordered Flows
by: Galperin, Daniel, et al.
Published: (2026)

E(3)-equivariant models cannot learn chirality: Field-based molecular generation
by: Dumitrescu, Alexandru, et al.
Published: (2024)

Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs
by: Rissanen, Severi, et al.
Published: (2024)

Generating Fine Details of Entity Interactions
by: Gu, Xinyi, et al.
Published: (2025)

Differentiable JPEG: The Devil is in the Details
by: Reich, Christoph, et al.
Published: (2023)

Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified Attention
by: Jo, Kyungmin, et al.
Published: (2025)

Repulsive Ensembles for Bayesian Inference in Physics-informed Neural Networks
by: Pilar, Philipp, et al.
Published: (2025)

Temporally Detailed Hypergraph Neural ODEs for Disease Progression Modeling
by: Xiao, Tingsong, et al.
Published: (2025)

Steering Dynamical Regimes of Diffusion Models by Breaking Detailed Balance
by: Lu, Haiqi, et al.
Published: (2026)

VertexRegen: Mesh Generation with Continuous Level of Detail
by: Zhang, Xiang, et al.
Published: (2025)

Heat Kernel Goes Topological
by: Krahn, Maximilian, et al.
Published: (2025)

The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations
by: LaBonte, Tyler, et al.
Published: (2024)

Soviet Illegal Whaling: The Devil and the Details
by: Ivashchenko, Yulia V., et al.
Published: (2011)

Diffusion for World Modeling: Visual Details Matter in Atari
by: Alonso, Eloi, et al.
Published: (2024)

Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity
by: Rubin, Noa, et al.
Published: (2025)

Generative Dataset Distillation: Balancing Global Structure and Local Details
by: Li, Longzhen, et al.
Published: (2024)

Input-gradient space particle inference for neural network ensembles
by: Trinh, Trung, et al.
Published: (2023)

SPATA: Systematic Pattern Analysis for Detailed and Transparent Data Cards
by: Vitorino, João, et al.
Published: (2025)

The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery
by: Zheng, Haiyang, et al.
Published: (2026)

Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
by: Qiu, Zihan, et al.
Published: (2025)

The Devil is in the Details: Zooming out in Leadership Research
by: Hannes Leroy, et al.
Published: (2025)

The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization
by: Huang, Shengyi, et al.
Published: (2024)

Attention to Detail: Fine-Scale Feature Preservation-Oriented Geometric Pre-training for AI-Driven Surrogate Modeling
by: Chen, Yu-hsuan, et al.
Published: (2025)

Derived Fields Preserve Fine-Scale Detail in Budgeted Neural Simulators
by: Wang, Wenshuo, et al.
Published: (2026)

Heterophily-informed Message Passing
by: Wang, Haishan, et al.
Published: (2025)

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
by: Cho, Jang Hyun, et al.
Published: (2025)

Missing Fine Details in Images: Last Seen in High Frequencies
by: Medi, Tejaswini, et al.
Published: (2025)

SynthEval: A Framework for Detailed Utility and Privacy Evaluation of Tabular Synthetic Data
by: Lautrup, Anton Danholt, et al.
Published: (2024)

Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance
by: Zhong, Jincheng, et al.
Published: (2025)