In this work, we present a novel direction to build an image tokenizer directly on top of a frozen vision foundation model, which is a largely underexplored area. Specifically, we employ a frozen vision foundation model as the encoder of our tokenizer. To enhance its effectiveness, we introduce two key components: (1) a region-adaptive quantization framework that reduces redundancy in the pre-trained features on regular 2D grids, and (2) a semantic reconstruction objective that aligns the tokenizer's outputs with the foundation model's representations to preserve semantic fidelity. Based on these designs, our proposed image tokenizer, VFMTok, achieves substantial improvements in image reconstruction and generation quality, while also enhancing token efficiency. It further boosts autoregressive (AR) generation--achieving a gFID of 1.36 on ImageNet benchmarks, while accelerating model convergence by three times, and enabling high-fidelity class-conditional synthesis without the need for classifier-free guidance (CFG). The code is available at https://github.com/CVMI-Lab/VFMTok.

Medical image reconstruction from measurement data is a vital but challenging inverse problem. Deep learning approaches have achieved promising results, but often requires paired measurement and high-quality images, which is typically simulated through a forward model, i.e., retrospective reconstruction. However, training on simulated pairs commonly leads to performance degradation on real prospective data due to the retrospective-to-prospective gap caused by incomplete imaging knowledge in simulation. To address this challenge, this paper introduces imaging Knowledge-Informed Dynamic Optimal Transport (KIDOT), a novel dynamic optimal transport framework with optimality in the sense of preserving consistency with imaging physics in transport, that conceptualizes reconstruction as finding a dynamic transport path. KIDOT learns from unpaired data by modeling reconstruction as a continuous evolution path from measurements to images, guided by an imaging knowledge-informed cost function and transport equation. This dynamic and knowledge-aware approach enhances robustness and better leverages unpaired data while respecting acquisition physics. Theoretically, we demonstrate that KIDOT naturally generalizes dynamic optimal transport, ensuring its mathematical rationale and solution existence. Extensive experiments on MRI and CT reconstruction demonstrate KIDOT's superior performance.

Physics-driven deep learning (PD-DL) approaches have become popular for improved reconstruction of fast magnetic resonance imaging (MRI) scans. Though PD-DL offers higher acceleration rates than existing clinical fast MRI techniques, their use has been limited outside specialized MRI centers. A key challenge is generalization to rare pathologies or different populations, noted in multiple studies, with fine-tuning on target populations suggested for improvement. However, current approaches for PD-DL training require access to raw k-space measurements, which is typically only available at specialized MRI centers that have research agreements for such data access. This is especially an issue for rural and under-resourced areas, where commercial MRI scanners only provide access to a final reconstructed image.

Let, y be a point in that intersection. Since, by definition, ˆr(x0,) is the radius of the smallest ball with 1/2 + probability mass of f(x0 + P) over all possible centers in Rk and ˆRis the radius of the smallest such ball centered at ˆf(x), we must have ˆr(x0,) ˆR. Consider the smallest ball B(z0,ˆr(x, 1)) that encloses at least 1/2 + 1 probability mass of f(x+ P). Since, r is the radius of the minimum enclosing ball that contains at least half of the points in Z, we have r ˆr(x, 1). Now, using the definition of ˆRand following the same reasoning as theorem 2, we can say that, d( ˆf(x), ˆf(x0)) βˆr(x0,) + ˆR (1 + β) ˆR.

A primary challenge for visual-based Reinforcement Learning (RL) is to generalize effectively across unseen environments. Although previous studies have explored different auxiliary tasks to enhance generalization, few adopt image reconstruction due to concerns about exacerbating overfitting to task-irrelevant features during training. Perceiving the pre-eminence of image reconstruction in representation learning, we propose SMG (\blue{S}eparated \blue{M}odels for \blue{G}eneralization), a novel approach that exploits image reconstruction for generalization. SMG introduces two model branches to extract task-relevant and task-irrelevant representations separately from visual observations via cooperatively reconstruction. Built upon this architecture, we further emphasize the importance of task-relevant features for generalization. Specifically, SMG incorporates two additional consistency losses to guide the agent's focus toward task-relevant areas across different scenarios, thereby achieving free from overfitting. Extensive experiments in DMC demonstrate the SOTA performance of SMG in generalization, particularly excelling in video-background settings. Evaluations on robotic manipulation tasks further confirm the robustness of SMG in real-world applications.

This restricts the tokenizer's ability to effectively leverage the redundancy

We learn a proximal map that works well with real images based on residual networks.

KAN oversaw the project and contributed valuable feedback. MindEye was developed using a training and validation set of Subject 1's data, with the test set (and other subjects' data) untouched until final PyTorch code for the MLP backbone and projector is depicted in Algorithm 1. Specifics on how we DALL-E 2. This makes our prior much faster at inference time. For simplicity we use bidirectional attention in our final model. To map to Stable Diffusion's V AE latent space we use a low-level pipeline with the same architecture as the high level pipeline. Recent works in low-level vision (super-resolution, denoising, deblurring, etc.) have observed that This performs worse than only applying the loss in latent space and also requires significantly more GPU memory.