Image, video and audio generation — diffusion models, flow matching and the systems built on top of them.
Text-to-image (T2I) workflows are increasingly deployed on serverless platforms because users often compose customized workflows and invoke them intermittently. Existing platforms typically deploy each workflow as an opaque GPU function, provisioning, placing, and scaling all constituent models in the workflow together.
Many discrete reasoning tasks, such as code generation, are inherently non-causal: programmers move between high-level structure and local details, a process we call any-order inference. For autoregressive language models, which lack a native any-order interface, non-causal abilities such as infilling and next-edit prediction require hand-designed mechanisms.
Audio deepfake detectors often degrade when generators, corpora, or recording conditions change. We use a Diffusion Transformer (DiT), trained only on bona fide speech, as a frozen reconstruction probe.
World models must learn the joint dynamics of states, actions, events, and observations, yet existing video, robotics, and simulation datasets usually capture only part of this structure. We introduce CG-World, a large-scale world-state dataset and protocol derived from industrial computer graphics production pipelines.
arXiv:2607. 24898v1 Announce Type: cross Abstract: State-of-the-art toxicity detectors for text-to-image generation adopt a one-size-fits-all approach: a single universal model applying fixed safety guidelines to all users.
arXiv:2607. 25157v1 Announce Type: new Abstract: Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretraining with bidirectional denoising.
arXiv:2607. 24762v1 Announce Type: new Abstract: Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as matrix multiplication, convolution, and normalization.
arXiv:2607. 24774v1 Announce Type: new Abstract: Nuclear radiation, the energy released during atomic decay, poses persistent risks to public health and the environment, and concerns have only grown since the Fukushima accident and the recent commencement of treated-water discharge.
arXiv:2501. 17296v4 Announce Type: replace-cross Abstract: Multiphysics simulations play an essential role in accurately modeling complex interactions across diverse scientific and engineering domains Although neural operators especially the Fourier Neural Operator FNO have significantly improved computational efficiency they often fail to effectively capture intricate correlations inherent in coupled physical processes To address this limitation we introduce COMPOL a novel coupled multiphysics operator learning framework COMPOL extends conventional operator architectures by incorporating sophisticated recurrent and attentionbased aggregation mechanisms effectively modeling interdependencies among interacting physical processes within latent feature spaces Our approach is architectureagnostic and seamlessly integrates into various neural operator frameworks that involve latent space transformations Extensive experiments on diverse benchmarksincluding biological reactiondiffusion systems patternforming chemical reactions multiphase geological flows and thermohydromechanical processes demonstrate that COMPOL consistently achieves superior predictive accuracy compared to stateoftheart methods.
arXiv:2607. 25522v1 Announce Type: cross Abstract: The rapid advancement of video generation models has led to the increasing misuse of image-to-video (I2V) models.
arXiv:2607. 24807v1 Announce Type: cross Abstract: We develop the mathematical and physical formulation of cognitive cost optimization that underlies the path-integral model of consciousness.
arXiv:2607. 24790v1 Announce Type: new Abstract: Low-Earth orbit (LEO) satellite Internet has become an important infrastructure for enabling ubiquitous connectivity to align with the International Telecommunications Union vision for 6G telecommunications networks.
arXiv:2607. 24777v1 Announce Type: new Abstract: Architected metamaterials derive their functions from structure, creating vast opportunities to program physical responses through topology design.
arXiv:2607. 24763v1 Announce Type: new Abstract: Masked diffusion language models (MDLMs) are advancing rapidly, yet the evaluation standards needed to reliably interpret their progress have not kept pace.
arXiv:2607. 25479v1 Announce Type: cross Abstract: Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text encoders, and exported computation graphs are distributed by third parties and reused across downstream services.
arXiv:2606. 12109v2 Announce Type: replace-cross Abstract: Pre-trained Vision-Language-Action (VLA) models provide useful semantic and spatial priors, yet their parallel-gripper action interfaces do not specify how those priors should be realized by a dexterous hand.
arXiv:2509. 11285v2 Announce Type: replace-cross Abstract: Class-Incremental Learning (CIL) in deep neural networks is conventionally framed as an iterative gradient-based optimization problem, incurring high computational cost, hyperparameter sensitivity, and risk of catastrophic forgetting.
arXiv:2607. 25948v1 Announce Type: cross Abstract: Any-to-any models predict any modality from any combination of others within a single network, a formulation used in multimodal vision and vision-language models, and increasingly in scientific domains such as ecology and astronomy.
arXiv:2607. 25641v1 Announce Type: cross Abstract: While text-to-image models exhibit remarkable visual fidelity, they frequently violate fundamental physical commonsense.
arXiv:2607. 26055v1 Announce Type: cross Abstract: Generalist manipulation policies increasingly take the form of action-chunking flow policies built on large pretrained backbones.