Image, video and audio generation — diffusion models, flow matching and the systems built on top of them.
Mobile infrared-visible imaging typically pairs a compact infrared sensor with a high-resolution visible camera for complementary perception. While cross-sensor misalignment caused by different optics, viewpoints, fields of view, and exposure timings hinders practical deployment.
Concept unlearning is increasingly used to limit the reproduction of protected or unsafe visual concepts in text-to-image models. Existing evaluations, however, mostly study targets that dominate the whole image, such as styles, broad object categories, or portrait-like identities, leaving company logos comparatively underexamined.
arXiv:2607. 22199v1 Announce Type: new Abstract: Score-based diffusion models have achieved remarkable empirical success in generative modeling, yet their approximation-theoretic foundations remain incomplete.
arXiv:2605. 12183v2 Announce Type: replace Abstract: Drifting Models have emerged as a new paradigm for one-step generative modeling, achieving strong image quality without iterative inference.
arXiv:2607. 22436v1 Announce Type: cross Abstract: This work addresses the generation of theoretical correlation matrices with prescribed sparsity patterns associated to graph structures.
arXiv:2607. 21941v1 Announce Type: new Abstract: Chemists and materials scientists increasingly use machine learning models, such as graph neural networks (GNNs), to predict properties of molecules and the outcomes of their reactions.
arXiv:2607. 22143v1 Announce Type: new Abstract: Molecular glue degraders have emerged as a promising strategy for targeted protein degradation by inducing ternary complex formation between an E3 ubiquitin ligase and a target protein.
arXiv:2509. 22352v3 Announce Type: replace Abstract: Survival analysis is a cornerstone of clinical research by modeling time-to-event outcomes such as metastasis, disease relapse, or patient death.
arXiv:2601. 12311v2 Announce Type: replace-cross Abstract: The emergence of 6G-enabled vehicular metaverses enables Autonomous Vehicles (AVs) to operate across physical and virtual spaces through space-air-ground-sea integrated networks.
arXiv:2607.
arXiv:2607. 22149v1 Announce Type: new Abstract: Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to learning spurious biases in the dataset.
arXiv:2607. 22287v1 Announce Type: new Abstract: Graph-based recommendations are widely adopted in real-world industrial applications.
arXiv:2607. 21634v1 Announce Type: new Abstract: Masked discrete diffusion for molecular graph generation typically applies a uniform corruption schedule to all tokens in a lossless graph-to-sequence representation, implicitly treating structurally heterogeneous molecular components as equally difficult and equally important to reconstruct.
arXiv:2607. 22035v1 Announce Type: new Abstract: Currently, most foundation models can reproduce or strongly depend on copyrighted training content, but output similarity alone is insufficient for infringement detection, because similar outputs may also arise from public-domain concepts, common stylistic conventions, or ordinary statistical generalization.
arXiv:2607. 21644v1 Announce Type: new Abstract: We present a goal-agnostic control framework for partial differential equations (PDEs) built around a joint-embedding predictive architecture (JEPA).
arXiv:2607. 21636v1 Announce Type: new Abstract: Synthetic tabular data is valued for preserving not only each column's marginal distribution but the dependencies between columns -- structure that carries much of the discriminative signal for minority classes in imbalanced domains such as fraud and clinical risk.
arXiv:2607. 21721v1 Announce Type: cross Abstract: Learned generative priors are increasingly used for ill-posed Bayesian inverse problems, their posterior uncertainty treated as earned from data.
High-resolution image and video diffusion models, including SD3, FLUX, and recent video diffusion transformers, have substantially improved generative quality but remain expensive at inference time because they repeatedly evaluate attention-heavy denoisers over many sampling steps. We address this inefficiency by exploiting redundancy in intermediate diffusion features rather than changing model weights or retraining.
Text-to-image diffusion models expose many inference-time sampling parameters, including prompts, negative prompts, classifier-free guidance scales, and noise schedules. These parameters are typically manually chosen once and then held fixed across prompts and denoising timesteps, even though different prompts and stages of generation can benefit from different parameter values.
arXiv:2602. 20114v2 Announce Type: replace-cross Abstract: Machine unlearning (MU) refers to the post-training capability to remove (the influence of) training examples that are incorrect, biased, or leak sensitive/private information.