홈 › Papers

DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models

2026-01-31 · Alicja Polowczyk, Agnieszka Polowczyk, Piotr Borycki, Joanna Waczyńska, Jacek Tabor, Przemysław Spurek arxiv

Despite impressive results from recent text-to-image models like FLUX, visual and anatomical artifacts remain a significant hurdle for practical and professional use. Existing methods for artifact reduction, typically work in a post-hoc manner, consequently failing to intervene effectively during the core image formation process. Notably, current techniques require problematic and invasive modifications to the model weights, or depend on a computationally expensive and time-consuming process of regional refinement. To address these limitations, we propose DIAMOND, a training-free method that applies trajectory correction to mitigate artifacts during inference. By reconstructing an estimate of the clean sample at every step of the generative trajectory, DIAMOND actively steers the generation process away from latent states that lead to artifacts. Furthermore, we extend the proposed method to standard Diffusion Models, demonstrating that DIAMOND provides a robust, zero-shot path to high-fidelity, artifact-free image synthesis without the need for additional training or weight modifications in modern generative architectures. Code is available at https://gmum.github.io/DIAMOND/

📄 PDF Abstract BibTeX arXiv:2602.00883

Code (0)

등록된 구현이 없습니다.

Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps

2026-02-05 · Peter Holderrieth, Douglas Chen, Luca Eyring, Ishin Shah 외 arxiv

Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward alignment. We argue that efficient…

Vectors Are Not Neutral: Sensitive-Information Inference from Exported LLM Representations in Summarization

2026-05-26 · Weixin Liu, Bowen Qu, Juming Xiong, Congning Ni 외 arxiv

Large language model (LLM) summarization systems may pass compact vector representations of private inputs to downstream retrieval, monitoring, audit, or analytic workflows. Even when source documents remain access-restr…

parameter-efficient fine-tuning

Multi-Flow Transmission in Wireless Interference Networks: A Convergent Graph Learning Approach

2023-03-27 · Raz Paul, Kobi Cohen, Gil Kedar

We consider the problem of of multi-flow transmission in wireless networks, where data signals from different flows can interfere with each other due to mutual interference between links along their routes, resulting in …

Graph Learning Graph Neural Network Reinforcement Learning (RL)

Semi-Modular Inference: enhanced learning in multi-modular models by tempering the influence of components

2020-03-15 · Chris Carmona, Geoff K. Nicholls

Bayesian statistical inference loses predictive optimality when generative models are misspecified. Working within an existing coherent loss-based generalisation of Bayesian inference, we show existing Modular/Cut-model …

Bayesian Inference Meta-Learning

Multi-Scales Data Augmentation Approach In Natural Language Inference For Artifacts Mitigation And Pre-Trained Model Optimization

2022-12-16 · Zhenyuan Lu

Machine learning models can reach high performance on benchmark natural language processing (NLP) datasets but fail in more challenging settings. We study this issue when a pre-trained model learns dataset artifacts in n…

Data Augmentation Model Optimization Natural Language Inference Sentence