Search

Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model Platform to help developers build customized world models for their Physical AI setups. We position a world foundation model as a general-purpose world model that can be fine-tuned into customized world models for downstream applications. Our platform covers a video curation pipeline, pre-trained world foundation models, examples of post-training of pre-trained world foundation models, and video tokenizers. To help Physical AI builders solve the most critical problems of our society, we make our platform open-source and our models open-weight with permissive licenses available via https://github.com/NVIDIA/Cosmos.

Let $p$ be a prime. We classify the finite groups having exactly two irreducible $p$-Brauer characters of degree larger than one. The case, where the finite groups have orders not divisible by $p$, was done by P. P\'alfy in 1981.

A chip-integrated acousto-optic phase modulator tailored for visible optical wavelengths has been developed. Utilizing the lithium niobate on sapphire platform, the modulator employs a 7 GHz surface acoustic wave, excited by an interdigital transducer and aligned perpendicular to the waveguide. This design achieves efficient phase modulation of visible light within a compact device length of merely 200 microns, while holds the advantages of easy fabrication and high stability due to simple unsuspended structure. Remarkably, in this high-frequency acoustic regime, the acoustic wavelength becomes comparable to the optical wavelength, resulting in a notable single-sideband modulation behavior. This observation underscores the phase delay effects in the acousto-optics interactions, and opens up new aspects for realizing functional visible photonic devices and its integration with atom- and ion-based quantum platforms., Comment: 10 pages, 6 figures

A theory based on the superposition principle is developed to uncover the basic physics of the wave behavior in a finite grating of N unit cells. The theory reveals that bound states in the continuum (BICs) of infinite quality factor (Q-factor) can be supported by such grating when the perfect reflection is introduced at its boundaries. If geometrical perturbations are introduced in the structure, the dark BICs transit to bright quasi-BICs of finite Q-factor, whose spectral behaviors are nearly the same as that of quasi-BICs supported by infinite gratings. When the boundaries are replaced with metallic mirrors of high reflectivity, the Q-factor of the resonant mode is reduced to be finite; however, it can be much larger than that in the corresponding nanostructure of open boundaries and can be tuned in a large range by varying the number of unit cells or boundary conditions.

We introduce Edify Image, a family of diffusion models capable of generating photorealistic image content with pixel-perfect accuracy. Edify Image utilizes cascaded pixel-space diffusion models trained using a novel Laplacian diffusion process, in which image signals at different frequency bands are attenuated at varying rates. Edify Image supports a wide range of applications, including text-to-image synthesis, 4K upsampling, ControlNets, 360 HDR panorama generation, and finetuning for image customization.

For an irreducible complex character $\chi$ of a finite group $G$, the codegree of $\chi$ is defined by $|G:\ker(\chi)|/\chi(1)$, where $\ker(\chi)$ is the kernel of $\chi$. Given a prime $p$, we provide a classification of finite groups in which every irreducible complex character has either $p'$-degree or $p'$-codegree.

Attaining superconducting critical temperatures (Tc) beyond the limit around 14 K observed thus far in spinel compounds AB2X4 (A, B = transition metals, X = O/chalcogen) could elucidate interaction intricacies and inform materials design. This work spotlights CuIr2S4, which exhibits a distinct metal-insulator transition below 230 K, as an unconventional candidate for activation under high pressure. Through transport, diffraction, and spectroscopy experiments conducted at pressures up to 224 GPa, we unveil pressure-tuning that suppressed CuIr2S4's transition, yielding two superconducting phases with an un-precedented Tc for spinels. Initially, 3.8 K onset rose monotonically, reaching 18.2 K at 133 GPa. Unexpectedly, a distinct phase with Tc = 2.2 K distinctly emerged at higher pressures, intimating unconventional couplings. Our findings suggest that both geometric frustration and electron-electron interactions play crucial roles in the superconductivity observed in CuIr2S4. The findings stretch perceived temperature limits in spinels and provide structure-property insights to guide the optimiza-tion of quantum materials interactions for tailored targeted functionalities., Comment: 12 pages, 7 gifures

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images.

Diffusion models, praised for their success in generative tasks, are increasingly being applied to robotics, demonstrating exceptional performance in behavior cloning. However, their slow generation process stemming from iterative denoising steps poses a challenge for real-time applications in resource-constrained robotics setups and dynamically changing environments. In this paper, we introduce the One-Step Diffusion Policy (OneDP), a novel approach that distills knowledge from pre-trained diffusion policies into a single-step action generator, significantly accelerating response times for robotic control tasks. We ensure the distilled generator closely aligns with the original policy distribution by minimizing the Kullback-Leibler (KL) divergence along the diffusion chain, requiring only $2\%$-$10\%$ additional pre-training cost for convergence. We evaluated OneDP on 6 challenging simulation tasks as well as 4 self-designed real-world tasks using the Franka robot. The results demonstrate that OneDP not only achieves state-of-the-art success rates but also delivers an order-of-magnitude improvement in inference speed, boosting action prediction frequency from 1.5 Hz to 62 Hz, establishing its potential for dynamic and computationally constrained robotic applications. We share the project page at https://research.nvidia.com/labs/dir/onedp/.

Personalized text-to-image generation models enable users to create images that depict their individual possessions in diverse scenes, finding applications in various domains. To achieve the personalization capability, existing methods rely on finetuning a text-to-image foundation model on a user's custom dataset, which can be non-trivial for general users, resource-intensive, and time-consuming. Despite attempts to develop finetuning-free methods, their generation quality is much lower compared to their finetuning counterparts. In this paper, we propose Joint-Image Diffusion (\jedi), an effective technique for learning a finetuning-free personalization model. Our key idea is to learn the joint distribution of multiple related text-image pairs that share a common subject. To facilitate learning, we propose a scalable synthetic dataset generation technique. Once trained, our model enables fast and easy personalization at test time by simply using reference images as input during the sampling process. Our approach does not require any expensive optimization process or additional modules and can faithfully preserve the identity represented by any number of reference images. Experimental results show that our model achieves state-of-the-art generation quality, both quantitatively and qualitatively, significantly outperforming both the prior finetuning-based and finetuning-free personalization baselines., Comment: CVPR 24

We propose a scalar dark matter model featuring a hidden gauge symmetry, denoted as U(1)_X, with two complex scalars, Phi and S. In this framework, Phi spontaneously breaks the U(1)_X gauge symmetry, while S serves as a viable dark matter candidate. Particularly, the kinetic and direct mixings between the U(1)_X and U(1)_Y gauge groups provide a portal between dark matter and the Standard Model particles. These mixings offer a plausible explanation for the W boson mass anomaly observed by the CDF Collaboration. We study the comprehensive phenomenological constraints of this model from colliders and dark matter detection experiments, including Z' searches at the LHC, the 125 GeV Higgs boson measurements, the relic density of dark matter and the indirect detection of dark matter annihilation. By randomly scanning the parameter space, we find that the regions where m_(Z') > 4750 GeV and m_(Z') < 4750 GeV for g_x close to 1 remain viable and can be tested by future experiments., Comment: 22 pages, 10 figures

Bulk magnetic and thermodynamic measurements, along with mean-field calculations, were conducted on the ferromagnetic K3Gd5(PO4)6 powders. No magnetic ordering was observed until 2 K, while the application of an external field B > 1 T resulted in the splitting of the Gd3+ ground state multiplet and induced a non-cooperative Schottky effect. The average nearest-neighbor exchange strength |J1/kB| is determined to be 0.017 K, which leads to a remarkably large low field magnetic entropy change {\Delta}Sm = 36.2 J kg-1 K-1 under applied field change B = 2 T at temperature T = 2 K, as well as a maximum adiabatic temperature change Tad = 10.9 K. We contend that ferromagnetic gadolinium orthophosphates serve as a promising reservoir for exploring advanced magnetic refrigerants applicable under low magnetic fields., Comment: 7 pages, 5 figures

At the core of portrait photography is the search for ideal lighting and viewpoint. The process often requires advanced knowledge in photography and an elaborate studio setup. In this work, we propose Holo-Relighting, a volumetric relighting method that is capable of synthesizing novel viewpoints, and novel lighting from a single image. Holo-Relighting leverages the pretrained 3D GAN (EG3D) to reconstruct geometry and appearance from an input portrait as a set of 3D-aware features. We design a relighting module conditioned on a given lighting to process these features, and predict a relit 3D representation in the form of a tri-plane, which can render to an arbitrary viewpoint through volume rendering. Besides viewpoint and lighting control, Holo-Relighting also takes the head pose as a condition to enable head-pose-dependent lighting effects. With these novel designs, Holo-Relighting can generate complex non-Lambertian lighting effects (e.g., specular highlights and cast shadows) without using any explicit physical lighting priors. We train Holo-Relighting with data captured with a light stage, and propose two data-rendering techniques to improve the data quality for training the volumetric relighting system. Through quantitative and qualitative experiments, we demonstrate Holo-Relighting can achieve state-of-the-arts relighting quality with better photorealism, 3D consistency and controllability., Comment: CVPR2024