Related papers: What matters for Representation Alignment: Global …

Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic…

Our findings indicate that adopting "advanced" computational elements fails to significantly improve registration accuracy. Instead, well-established registration-specific designs offer fair improvements, enhancing results by a marginal…

Utilization of classification latent space information for downstream reconstruction and generation is an intriguing and a relatively unexplored area. In general, discriminative representations are rich in class-specific features but are…

The Platonic Representation Hypothesis suggests that independently trained neural networks converge to increasingly similar latent spaces. However, current strategies for mapping these representations are inherently pairwise, scaling…

Large kernel convolutions offer a scalable alternative to vision transformers for high-resolution 3D volumetric analysis, yet naively increasing kernel size often leads to optimization instability. Motivated by the spatial bias inherent in…

Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inherent visual uncertainty at masked positions, feature…

Structure-guided image completion aims to inpaint a local region of an image according to an input guidance map from users. While such a task enables many practical applications for interactive editing, existing methods often struggle to…

We focus on the foundational task of Scene Staging: given a reference scene image and a text condition specifying an actor category to be generated in the scene and its spatial relation to the scene, the goal is to synthesize an output…

Real-world image degradation is often unknown, spatially non-uniform, and compositional, requiring all-in-one restoration models to adapt a single set of weights to diverse local corruption patterns without test-time degradation labels.…

Generative tabular augmentation is appealing in data-scarce domains, yet the prevailing focus on distributional fidelity does not reliably translate into better downstream models. We formalize a fidelity-utility gap: common generative…

Modern ultra-high-resolution image synthesis relies heavily on the robust generative capacity of large-scale pre-trained Latent Diffusion Models (LDMs). While recent representation alignment methods have proven effective by distilling…

We propose MESA and DMESA as novel feature matching methods, which utilize Segment Anything Model (SAM) to effectively mitigate matching redundancy. The key insight of our methods is to establish implicit-semantic area matching prior to…

Self-supervised learning has emerged as a major technique for the task of learning from unlabeled data, where the current methods mostly revolve around alignment of representations and input recon struction. Although such approaches have…

Reasoning-based image quality assessment (IQA) models trained through reinforcement learning (RL) exhibit exceptional generalization, yet the underlying mechanisms and critical factors driving this capability remain underexplored in current…

Structured embedding transformations offer a promising approach for enhancing the efficiency and coherence of language model inference. The introduction of Structural Embedding Projection (SEP) provides a mechanism for refining token…

Confusing classes that are ubiquitous in real world often degrade performance for many vision related applications like object detection, classification, and segmentation. The confusion errors are not only caused by similar visual patterns…

Generative Adversarial Networks (GAN) have been employed for face super resolution but they bring distorted facial details easily and still have weakness on recovering realistic texture. To further improve the performance of GAN based…

Accurate, fair, and explainable allocation of candidates to roles represents a fundamental challenge across multiple domains including corporate hiring, academic admissions, fellowship awards, and volunteer placement systems. Current…

Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously…

Perceptual image quality assessment (IQA) is the task of predicting the visual quality of an image as perceived by a human observer. Current state-of-the-art techniques are based on deep representations trained in discriminative manner.…