Search for: All records

Generative models transform random noise into images, while their inversion aims to reconstruct structured noise for recovery and editing. This paper addresses two key tasks: (i) inversion and (ii) editing of real images using stochastic equivalents of rectified flow models (e.g., Flux). While Diffusion Models (DMs) dominate the field of generative modeling for images, their inversion suffers from faithfulness and editability challenges due to nonlinear drift and diffusion. Existing DM inversion methods require costly training of additional parameters or test-time optimization of latent variables. Rectified Flows (RFs) offer a promising alternative to DMs, yet their inversion remains underexplored. We propose RF inversion using dynamic optimal control derived via a linear quadratic regulator, and prove that the resulting vector field is equivalent to a rectified stochastic differential equation. We further extend our framework to design a stochastic sampler for Flux. Our method achieves state-of-the-art performance in zero-shot inversion and editing, surpassing prior works in stroke-to-image synthesis and semantic image editing, with large-scale human evaluations confirming user preference. See our project page https://rf-inversion.github.io/ for code and demo. 

In pretraining data detection, the goal is to detect whether a given sentence is in the dataset used for training a Large Language Model LLM). Recent methods (such as Min-K % and Min-K%++) reveal that most training corpora are likely contaminated with both sensitive content and evaluation benchmarks, leading to inflated test set performance. These methods sometimes fail to detect samples from the pretraining data, primarily because they depend on statistics composed of causal token likelihoods. We introduce Infilling Score, a new test-statistic based on non-causal token likelihoods. Infilling Score can be computed for autoregressive models without re-training using Bayes rule. A naive application of Bayes rule scales linearly with the vocabulary size. However, we propose a ratio test-statistic whose computation is invariant to vocabulary size. Empirically, our method achieves a significant accuracy gain over state-of-the-art methods including Min-K%, and Min-K%++ on the WikiMIA benchmark across seven models with different parameter sizes. Further, we achieve higher AUC compared to reference-free methods on the challenging MIMIR benchmark. Finally, we create a benchmark dataset consisting of recent data sources published after the release of Llama-3; this benchmark provides a statistical baseline to indicate potential corpora used for Llama-3 training. 

The authors propose Reference-Based Modulation (RB-Modulation), a plug-and-play, training-free solution for personalization of diffusion models. Existing training-free methods face challenges in (a) extracting style from reference images without additional style or content text descriptions, (b) avoiding unwanted content leakage from style references, and (c) composing style and content effectively. RB-Modulation addresses these issues using a novel stochastic optimal controller, where a style descriptor encodes the desired attributes through a terminal cost. The induced drift ensures high fidelity to the reference style while adhering to the text prompt. Additionally, the authors introduce a cross-attention-based feature aggregation scheme that decouples content and style from the reference image. With both theoretical justification and empirical validation, RB-Modulation demonstrates precise control of content and style in a training-free manner, while enabling seamless composition—eliminating reliance on external adapters or ControlNets.