Search

In this paper, we show different fine-tuning methods for Stable Diffusion XL; this includes inference steps, and caption customization for each image to align with generating images in the style of a commercial 2D icon training set. We also show how important it is to properly define what "high-quality" really is especially for a commercial-use environment. As generative AI models continue to gain widespread acceptance and usage, there emerge many different ways to optimize and evaluate them for various applications. Specifically text-to-image models, such as Stable Diffusion XL and DALL-E 3 require distinct evaluation practices to effectively generate high-quality icons according to a specific style. Although some images that are generated based on a certain style may have a lower FID score (better), we show how this is not absolute in and of itself even for rasterized icons. While FID scores reflect the similarity of generated images to the overall training set, CLIP scores measure the alignment between generated images and their textual descriptions. We show how FID scores miss significant aspects, such as the minority of pixel differences that matter most in an icon, while CLIP scores result in misjudging the quality of icons. The CLIP model's understanding of "similarity" is shaped by its own training data; which does not account for feature variation in our style of choice. Our findings highlight the need for specialized evaluation metrics and fine-tuning approaches when generating high-quality commercial icons, potentially leading to more effective and tailored applications of text-to-image models in professional design contexts., Comment: 11 pages, 22 figures

We introduce ReXTime, a benchmark designed to rigorously test AI models' ability to perform temporal reasoning within video events. Specifically, ReXTime focuses on reasoning across time, i.e. human-like understanding when the question and its corresponding answer occur in different video segments. This form of reasoning, requiring advanced understanding of cause-and-effect relationships across video segments, poses significant challenges to even the frontier multimodal large language models. To facilitate this evaluation, we develop an automated pipeline for generating temporal reasoning question-answer pairs, significantly reducing the need for labor-intensive manual annotations. Our benchmark includes 921 carefully vetted validation samples and 2,143 test samples, each manually curated for accuracy and relevance. Evaluation results show that while frontier large language models outperform academic models, they still lag behind human performance by a significant 14.3% accuracy gap. Additionally, our pipeline creates a training dataset of 9,695 machine generated samples without manual effort, which empirical studies suggest can enhance the across-time reasoning via fine-tuning., Comment: Project page: https://rextime.github.io/

Due to the large perpendicular magnetic anisotropy originating from spin-orbit coupling, magnetoelastic coupling is generally reported in easy-plane magnets with rectangular lattice where the easy magnetization is coupled with the lattice direction, while the acquisition of a novel coupling, beyond the easy-plane ferromagnets, in two-dimensional (2D) materials remains unknown. Here, by employing the density functional theory calculations, we demonstrate this feasibility with the discovery of long-range ferromagnetic ordering and elastic strain-mediated chiral-like atomic distortions behavior in a newly tetragonal As-Fe-As trilayer (t-FeAs monolayer), which shows large perpendicular magnetic anisotropy, robust ferromagnetic ordering, and in-plane ferroelasticity. We firstly point out that obvious limits exist when using the four magnetic configurations to determine the magnetic ground state for a rectangular spin lattice even if more exchange interaction parameters are included. A four-state mapping analysis is carefully examined for t-FeAs, where the calculated Curie temperature, Tc, is 435 K, which is higher than most reported 2D magnets, and can be further tuned by appropriate strains. Intriguingly, the chiral-like atomic distortion behavior of the Fe sub-layer is scanning tunneling microscopy characterizable, which can switch the magnetization axis between the out-of-plane and in-plane direction. This unusual finding of ferroelastic manipulation of both the atomic displacement and spin properties makes t-FeAs a promising candidate for future spintronics and also provides the possibility for exploring unprecedented coupling physics., Comment: 18 pages, 7 figures

In several languages, omitting a verb phrase (VP) in double centre-embedded structures creates a grammaticality illusion. Similar illusion also exhibited in Mandarin missing-NP double centre-embedded structures. However, there is no consensus on its very nature. Instead of treating it as grammaticality illusion, we argue that ambiguous interpretations of verbs can best account for this phenomenon in Mandarin. To further support this hypothesis, we conducted two electroencephalography (EEG) experiments on quasi double centre-embedded structures whose complexity is reduced by placing the self-embedding relative clauses into the sentence's subject position. Experiment 1 showed that similar phenomenon even exhibited in this structure, evidenced by an absence of P600 effect and a presence of N400 effect. In Experiment 2, providing semantic cues to reduce ambiguity dispelled this illusion, as evidenced by a P600 effect. We interpret the results under garden-path theory and propose that word-order difference may account for this cross-linguistic variation.

The quantum wave function of multiple particles provides additional information which is inaccessible to detectors working alone. Here, we introduce the coincidence wavefront sensing (CWS) method to reconstruct the phase of the multiphoton transverse spatial wave function. The spatially resolved coincidence photon counting is involved. Numerical simulations of two-photon cases using the weak measurement wavefront sensor are performed to test its correctness, and the phase information hidden in the correlation are revealed. Our work provides a direct spatial way to characterize multipartite quantum systems, and leads to fundamental studies like experimental Bohmian mechanics and applications in quantum optical technologies., Comment: 9 pages, 3 figures. Note for the third version (v3): After publication, we found the author names of the 22nd reference was misspelled, and the experimental setup of another referring letter was misinterpreted in the main text. So we corrected the names of the 22nd reference and removed the 46th reference along with its description in the main text. (c) 2023 American Physical Society

With the development of gene sequencing technology, an explosive growth of gene data has been witnessed. And the storage of gene data has become an important issue. Traditional gene data compression methods rely on general software like G-zip, which fails to utilize the interrelation of nucleotide sequence. Recently, many researchers begin to investigate deep learning based gene data compression method. In this paper, we propose a transformer-based gene compression method named GeneFormer. Specifically, we first introduce a modified transformer structure to fully explore the nucleotide sequence dependency. Then, we propose fixed-length parallel grouping to accelerate the decoding speed of our autoregressive model. Experimental results on real-world datasets show that our method saves 29.7% bit rate compared with the state-of-the-art method, and the decoding speed is significantly faster than all existing learning-based gene compression methods.

Exceptional points (EPs), at which more than one eigenvalue and eigenvector coalesce, are unique spectral features of Non-Hermiticity (NH) systems. They exist widely in open systems with complex energy spectra. We experimentally demonstrate the appearance of paired EPs in a periodical driven degenerate optical cavity along the synthetic orbital angular momentum (OAM) dimension with a tunable parameter. The complex-energy band structures and the key features of EPs, i.e. their Fermi arcs, parity-time symmetry breaking transition, energy swapping, and half-integer band windings are directly observed by detecting the cavity's transmission spectrum. Our results advance the fundamental understanding of NH physics and demonstrate the flexibility of using the photonic synthetic dimensions to implement NH systems.

We present a self-trainable method, Mask2Hand, which learns to solve the challenging task of predicting 3D hand pose and shape from a 2D binary mask of hand silhouette/shadow without additional manually-annotated data. Given the intrinsic camera parameters and the parametric hand model in the camera space, we adopt the differentiable rendering technique to project 3D estimations onto the 2D binary silhouette space. By applying a tailored combination of losses between the rendered silhouette and the input binary mask, we are able to integrate the self-guidance mechanism into our end-to-end optimization process for constraining global mesh registration and hand pose estimation. The experiments show that our method, which takes a single binary mask as the input, can achieve comparable prediction accuracy on both unaligned and aligned settings as state-of-the-art methods that require RGB or depth inputs. Our code is available at https://github.com/lijenchang/Mask2Hand.

Composite visualization is a popular design strategy that represents complex datasets by integrating multiple visualizations in a meaningful and aesthetic layout, such as juxtaposition, overlay, and nesting. With this strategy, numerous novel designs have been proposed in visualization publications to accomplish various visual analytic tasks. These well-crafted composite visualizations have formed a valuable collection for designers and researchers to address real-world problems and inspire new research topics and designs. However, there is a lack of understanding of design patterns of composite visualization, thus failing to provide holistic design space and concrete examples for practical use. In this paper, we opted to revisit the composite visualizations in VIS publications and answered what and how visualizations of different types are composed together. To achieve this, we first constructed a corpus of composite visualizations from IEEE VIS publications and decomposed them into a series of basic visualization types (e.g., bar chart, map, and matrix). With this corpus, we studied the spatial (e.g., separated or overlaying) and semantic relationships (e.g., with same types or shared axis) between visualizations and proposed a taxonomy consisting of eight different design patterns (e.g., repeated, stacked, accompanied, and nested). Furthermore, we analyzed and discussed common practices of composite visualizations, such as the distribution of different patterns and correlations between visualization types. From the analysis and examples, we obtained insights into different design patterns on the utilities, advantages, and disadvantages. Finally, we developed an interactive system to help visualization developers and researchers conveniently explore collected examples and design patterns.

Synthetic dimensions based on particles' internal degrees of freedom, such as frequency, spatial modes and arrival time, have attracted significant attention. They offer ideal large-scale lattices to simulate nontrivial topological phenomena. Exploring more synthetic dimensions is one of the paths toward higher dimensional physics. In this work, we design and experimentally control the coupling among synthetic dimensions consisting of the intrinsic photonic orbital angular momentum and spin angular momentum degrees of freedom in a degenerate optical resonant cavity, which generates a periodically driven spin-orbital coupling system. We directly characterize the system's properties, including the density of states, energy band structures and topological windings, through the transmission intensity measurements. Our work demonstrates a novel mechanism for exploring the spatial modes of twisted photons as the synthetic dimension, which paves the way to design rich topological physics in a highly compact platform.