Search

Inspirational search, the process of exploring designs to inform and inspire new creative work, is pivotal in mobile user interface (UI) design. However, exploring the vast space of UI references remains a challenge. Existing AI-based UI search methods often miss crucial semantics like target users or the mood of apps. Additionally, these models typically require metadata like view hierarchies, limiting their practical use. We used a multimodal large language model (MLLM) to extract and interpret semantics from mobile UI images. We identified key UI semantics through a formative study and developed a semantic-based UI search system. Through computational and human evaluations, we demonstrate that our approach significantly outperforms existing UI retrieval methods, offering UI designers a more enriched and contextually relevant search experience. We enhance the understanding of mobile UI design semantics and highlight MLLMs' potential in inspirational search, providing a rich dataset of UI semantics for future studies., Comment: In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI '25)

Fault injection attacks induce hardware failures in circuits and exploit these faults to compromise the security of the system. It has been demonstrated that FIAs can bypass system security mechanisms, cause faulty outputs, and gain access to secret information. Certain types of FIAs can be mounted with little effort by tampering with clock signals and or the chip operating conditions. To mitigate such low cost, yet powerful attacks, we propose a fully synthesizable and distributable in situ fault injection monitor that employs a delay locked loop to track the pulsewidth of the clock. We further develop a fully automated design framework to optimize and implement the FIA monitors at any process node. Our design is fabricated and verified in 65 nm CMOS technology with a small footprint of 1500 um2. It can lock to clock frequencies from 2 MHz to 1.26 GHz while detecting all 12 types of possible clock glitches, as well as timing FIA injections via the supply voltage, electromagnetic signals, and chip temperature., Comment: 12 pages, 26 figures

We propose Exemplar-Condensed federated class-incremental learning (ECoral) to distil the training characteristics of real images from streaming data into informative rehearsal exemplars. The proposed method eliminates the limitations of exemplar selection in replay-based approaches for mitigating catastrophic forgetting in federated continual learning (FCL). The limitations particularly related to the heterogeneity of information density of each summarized data. Our approach maintains the consistency of training gradients and the relationship to past tasks for the summarized exemplars to represent the streaming data compared to the original images effectively. Additionally, our approach reduces the information-level heterogeneity of the summarized data by inter-client sharing of the disentanglement generative model. Extensive experiments show that our ECoral outperforms several state-of-the-art methods and can be seamlessly integrated with many existing approaches to enhance performance.

Spatial Transcriptomics (ST) is a method that captures spatial gene expression profiles within histological sections. The discrete spatial distribution and the super-high dimensional sequencing results make ST data challenging to be modeled effectively. In this paper, we manage to model ST in a continuous and compact manner by the proposed tool, SUICA, empowered by the great approximation capability of Implicit Neural Representations (INRs) that can improve both the spatial resolution and the gene expression. Concretely within the proposed SUICA, we incorporate a graph-augmented Autoencoder to effectively model the context information of the unstructured spots and provide informative embeddings that are structure-aware for spatial mapping. We also tackle the extremely skewed distribution in a regression-by-classification fashion and enforce classification-based loss functions for the optimization of SUICA. By extensive experiments of a wide range of common ST platforms, SUICA outperforms both conventional INR variants and SOTA methods for ST super-resolution regarding numerical fidelity, statistical correlation, and bio-conservation. The prediction by SUICA also showcases amplified gene signatures that enriches the bio-conservation of the raw data and benefits subsequent analysis. The code is available at https://github.com/Szym29/SUICA.

In this paper, we introduce Ref-GS, a novel approach for directional light factorization in 2D Gaussian splatting, which enables photorealistic view-dependent appearance rendering and precise geometry recovery. Ref-GS builds upon the deferred rendering of Gaussian splatting and applies directional encoding to the deferred-rendered surface, effectively reducing the ambiguity between orientation and viewing angle. Next, we introduce a spherical Mip-grid to capture varying levels of surface roughness, enabling roughness-aware Gaussian shading. Additionally, we propose a simple yet efficient geometry-lighting factorization that connects geometry and lighting via the vector outer product, significantly reducing renderer overhead when integrating volumetric attributes. Our method achieves superior photorealistic rendering for a range of open-world scenes while also accurately recovering geometry., Comment: Project page: https://ref-gs.github.io/

We investigate fundamental constraints on passive linear time-invariant acoustic systems through the developing alternative linear sum rules for sound absorption and transmission. Our approach, based on the Herglotz function method, yields integral identities without non-linear logarithmic terms or frequency weightings, providing clearer physical insights into system performance limits. The study focuses on unidimensional waveguides with Lorentz resonators, encompassing various practical acoustic structures. The developed sum rules are found to be particularly effective in predicting constraints on the average sound absorption coefficient for broadband absorbers operating in deep-subwavelength structures. Based on these rules, we demonstrate the waterbed effect in such systems, highlighting the inherent compromises between absorption efficiency, bandwidth, and device thickness. Through case studies of resonator arrays and membranes, we illustrate the practical implications of these new sum rules for designing optimal sound absorbers and isolators. The work concludes with a discussion on the challenges and future prospects in passive noise control, suggesting potential pathways to surpass current performance boundaries.

Miniature bioelectronic implants promise revolutionary therapies for cardiovascular and neurological disorders. Wireless power transfer (WPT) is a significant method for miniaturization, eliminating the need for bulky batteries in devices. Despite successful demonstrations of millimetric battery free implants in animal models, the robustness and efficiency of WPT are known to degrade significantly under misalignment incurred by body movements, respiration, heart beating, and limited control of implant orientation during surgery. This article presents an omnidirectional WPT platform for millimetric bioelectronic implants, employing the emerging magnetoelectric (ME) WPT modality, and magnetic field steering technique based on multiple transmitter (TX) coils. To accurately sense the weak coupling in a miniature implant and adaptively control the multicoil TX array in a closed loop, we develop an active echo (AE) scheme using a tiny coil on the implant. Our prototype comprises a fully integrated 14.2 mm3 implantable stimulator embedding a custom low power system on chip (SoC) powered by an ME film, a TX with a custom three channel AE RX chip, and a multicoil TX array with mutual inductance cancellation. The AE RX achieves negative 161 dBm per Hz input referred noise with 64 dB gain tuning range to reliably sense the AE signal, and offers fast polarity detection for driver control. AE simultaneously enhances the robustness, efficiency, and charging range of ME WPT. Under 90 degree rotation from the ideal position, our omnidirectional WPT system achieves 6.8x higher power transfer efficiency (PTE) than a single coil baseline. The tracking error of AE negligibly degrades the PTE by less than 2 percent from using ideal control., Comment: 13 pages, 27 figures

A set of polar rod-shaped liquid crystalline molecules with large dipole moments (mu > 10.4-14.8 D), their molecular structures based on the ferroelectric nematic prototype DIO, are designed, synthesized, and investigated. When the penultimate fluoro-phenyl ring is replaced by phenylpyrimidine moiety, the molecular dipole moment increases from 9.4 D for DIO to 10.4 D for the new molecule and when the terminal fluoro-group is additionally replaced by the nitrile group, the dipole moment rises to 14.8 D. Such a replacement enhances not only the net dipole moment of the molecule, but it also reduces the steric hindrance to rotations of the moieties within the molecule. The superparaelectric nematic (N) and smectic A (SmA) phases of these compounds are found to exhibit colossal dielectric permittivity, obtained both from dielectric spectroscopy, and capacitance measurements using a simple capacitor divider circuit. The electric polarization is measured vs. the field (E). However, no hysteresis in P vs. E is found in the nematic and smectic A phases. The colossal dielectric permittivity persists over the entire fluidic range. The experimental results lead us to conclude that these materials belong to the class of superparaelectrics (SPE) rather than to ferroelectrics due to the absence hysteresis and linear P vs E dependence. The synthesized organic materials are the first fluids for which superparaelectricity is discovered and furthermore these show great potential for the applications in supercapacitors used in storing energy., Comment: 24 pages, 7 figures, 1 table. Submited to JMC C

3D point clouds are increasingly vital for applications like autonomous driving and robotics, yet the raw data captured by sensors often suffer from noise and sparsity, creating challenges for downstream tasks. Consequently, point cloud upsampling becomes essential for improving density and uniformity, with recent approaches showing promise by projecting randomly generated query points onto the underlying surface of sparse point clouds. However, these methods often result in outliers, non-uniformity, and difficulties in handling regions with high curvature and intricate structures. In this work, we address these challenges by introducing the Progressive Local Surface Estimator (PLSE), which more effectively captures local features in complex regions through a curvature-based sampling technique that selectively targets high-curvature areas. Additionally, we incorporate a curriculum learning strategy that leverages the curvature distribution within the point cloud to naturally assess the sample difficulty, enabling curriculum learning on point cloud data for the first time. The experimental results demonstrate that our approach significantly outperforms existing methods, achieving high-quality, dense point clouds with superior accuracy and detail.

Reducing scan time in Positron Emission Tomography (PET) imaging while maintaining high-quality images is crucial for minimizing patient discomfort and radiation exposure. Due to the limited size of datasets and distribution discrepancy across scanners in medical imaging, fine-tuning in a parameter-efficient and effective manner is on the rise. Motivated by the potential of Parameter-Efficient Fine-Tuning (PEFT), we aim to address these issues by effectively leveraging PEFT to improve limited data and GPU resource issues in multi-scanner setups. In this paper, we introduce PETITE, Parameter-Efficient Fine-Tuning for MultI-scanner PET to PET REconstruction that uses fewer than 1% of the parameters. To the best of our knowledge, this study is the first to systematically explore the efficacy of diverse PEFT techniques in medical imaging reconstruction tasks via prevalent encoder-decoder-type deep models. This investigation, in particular, brings intriguing insights into PETITE as we show further improvements by treating encoder and decoder separately and mixing different PEFT methods, namely, Mix-PEFT. Using multi-scanner PET datasets comprised of five different scanners, we extensively test the cross-scanner PET scan time reduction performances (i.e., a model pre-trained on one scanner is fine-tuned on a different scanner) of 21 feasible Mix-PEFT combinations to derive optimal PETITE. We show that training with less than 1% parameters using PETITE performs on par with full fine-tuning (i.e., 100% parameter)

Using the quotient bundle introduced by Wojtkowski, we give necessary and sufficient conditions for a magnetic flow on a closed, oriented surface to be Anosov.

Few-shot medical image segmentation has achieved great progress in improving accuracy and efficiency of medical analysis in the biomedical imaging field. However, most existing methods cannot explore inter-class relations among base and novel medical classes to reason unseen novel classes. Moreover, the same kind of medical class has large intra-class variations brought by diverse appearances, shapes and scales, thus causing ambiguous visual characterization to degrade generalization performance of these existing methods on unseen novel classes. To address the above challenges, in this paper, we propose a \underline{\textbf{P}}rototype correlation \underline{\textbf{M}}atching and \underline{\textbf{C}}lass-relation \underline{\textbf{R}}easoning (i.e., \textbf{PMCR}) model. The proposed model can effectively mitigate false pixel correlation matches caused by large intra-class variations while reasoning inter-class relations among different medical classes. Specifically, in order to address false pixel correlation match brought by large intra-class variations, we propose a prototype correlation matching module to mine representative prototypes that can characterize diverse visual information of different appearances well. We aim to explore prototype-level rather than pixel-level correlation matching between support and query features via optimal transport algorithm to tackle false matches caused by intra-class variations. Meanwhile, in order to explore inter-class relations, we design a class-relation reasoning module to segment unseen novel medical objects via reasoning inter-class relations between base and novel classes. Such inter-class relations can be well propagated to semantic encoding of local query features to improve few-shot segmentation performance. Quantitative comparisons illustrates the large performance improvement of our model over other baseline methods.

Text-to-3D content creation is a rapidly evolving research area. Given the scarcity of 3D data, current approaches often adapt pre-trained 2D diffusion models for 3D synthesis. Among these approaches, Score Distillation Sampling (SDS) has been widely adopted. However, the issue of over-smoothing poses a significant limitation on the high-fidelity generation of 3D models. To address this challenge, LucidDreamer replaces the Denoising Diffusion Probabilistic Model (DDPM) in SDS with the Denoising Diffusion Implicit Model (DDIM) to construct Interval Score Matching (ISM). However, ISM inevitably inherits inconsistencies from DDIM, causing reconstruction errors during the DDIM inversion process. This results in poor performance in the detailed generation of 3D objects and loss of content. To alleviate these problems, we propose a novel method named Exact Score Matching (ESM). Specifically, ESM leverages auxiliary variables to mathematically guarantee exact recovery in the DDIM reverse process. Furthermore, to effectively capture the dynamic changes of the original and auxiliary variables, the LoRA of a pre-trained diffusion model implements these exact paths. Extensive experiments demonstrate the effectiveness of ESM in text-to-3D generation, particularly highlighting its superiority in detailed generation.

This study proposes a framework for enhancing the stroke quality of badminton players by generating personalized motion guides, utilizing a multimodal wearable dataset. These guides are based on counterfactual algorithms and aim to reduce the performance gap between novice and expert players. Our approach provides joint-level guidance through visualizable data to assist players in improving their movements without requiring expert knowledge. The method was evaluated against a traditional algorithm using metrics to assess validity, proximity, and plausibility, including arithmetic measures and motion-specific evaluation metrics. Our evaluation demonstrates that the proposed framework can generate motions that maintain the essence of original movements while enhancing stroke quality, providing closer guidance than direct expert motion replication. The results highlight the potential of our approach for creating personalized sports motion guides by generating counterfactual motion guidance for arbitrary input motion samples of badminton strokes., Comment: ICRA Wearable Workshop 2024 - 1st Workshop on Advancing Wearable Devices and Applications through Novel Design, Sensing, Actuation, and AI

With impressive achievements made, artificial intelligence is on the path forward to artificial general intelligence. Sora, developed by OpenAI, which is capable of minute-level world-simulative abilities can be considered as a milestone on this developmental path. However, despite its notable successes, Sora still encounters various obstacles that need to be resolved. In this survey, we embark from the perspective of disassembling Sora in text-to-video generation, and conducting a comprehensive review of literature, trying to answer the question, \textit{From Sora What We Can See}. Specifically, after basic preliminaries regarding the general algorithms are introduced, the literature is categorized from three mutually perpendicular dimensions: evolutionary generators, excellent pursuit, and realistic panorama. Subsequently, the widely used datasets and metrics are organized in detail. Last but more importantly, we identify several challenges and open problems in this domain and propose potential future directions for research and development., Comment: A comprehensive list of text-to-video generation studies in this survey is available at https://github.com/soraw-ai/Awesome-Text-to-Video-Generation

Spiking neural networks (SNNs) offer a promising energy-efficient alternative to artificial neural networks (ANNs), in virtue of their high biological plausibility, rich spatial-temporal dynamics, and event-driven computation. The direct training algorithms based on the surrogate gradient method provide sufficient flexibility to design novel SNN architectures and explore the spatial-temporal dynamics of SNNs. According to previous studies, the performance of models is highly dependent on their sizes. Recently, direct training deep SNNs have achieved great progress on both neuromorphic datasets and large-scale static datasets. Notably, transformer-based SNNs show comparable performance with their ANN counterparts. In this paper, we provide a new perspective to summarize the theories and methods for training deep SNNs with high performance in a systematic and comprehensive way, including theory fundamentals, spiking neuron models, advanced SNN models and residual architectures, software frameworks and neuromorphic hardware, applications, and future trends. The reviewed papers are collected at https://github.com/zhouchenlin2096/Awesome-Spiking-Neural-Networks, Comment: Accepted by Frontiers in Neuroscience

Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be taxing on deployed devices. One way to overcome this challenge is by adapting the computation level to the specific needs of the input image rather than the current one-size-fits-all approach. To this end, we introduce ECO-M2F or EffiCient TransfOrmer Encoders for Mask2Former-style models. Noting that the encoder module of M2F-style models incur high resource-intensive computations, ECO-M2F provides a strategy to self-select the number of hidden layers in the encoder, conditioned on the input image. To enable this self-selection ability for providing a balance between performance and computational efficiency, we present a three step recipe. The first step is to train the parent architecture to enable early exiting from the encoder. The second step is to create an derived dataset of the ideal number of encoder layers required for each training example. The third step is to use the aforementioned derived dataset to train a gating network that predicts the number of encoder layers to be used, conditioned on the input image. Additionally, to change the computational-accuracy tradeoff, only steps two and three need to be repeated which significantly reduces retraining time. Experiments on the public datasets show that the proposed approach reduces expected encoder computational cost while maintaining performance, adapts to various user compute resources, is flexible in architecture configurations, and can be extended beyond the segmentation task to object detection.

A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions. With efficiency being a high priority for scaling such models, we observed that the state-of-the-art method Mask2Former uses 50% of its compute only on the transformer encoder. This is due to the retention of a full-length token-level representation of all backbone feature scales at each encoder layer. With this observation, we propose a strategy termed PROgressive Token Length SCALing for Efficient transformer encoders (PRO-SCALE) that can be plugged-in to the Mask2Former segmentation architecture to significantly reduce the computational cost. The underlying principle of PRO-SCALE is: progressively scale the length of the tokens with the layers of the encoder. This allows PRO-SCALE to reduce computations by a large margin with minimal sacrifice in performance (~52% encoder and ~27% overall GFLOPs reduction with no drop in performance on COCO dataset). Experiments conducted on public benchmarks demonstrates PRO-SCALE's flexibility in architectural configurations, and exhibits potential for extension beyond the settings of segmentation tasks to encompass object detection. Code here: https://github.com/abhishekaich27/proscale-pytorch, Comment: Accepted to ICLR 2025

The intricate interplay between spin and lattice degrees of freedom in two-dimensional magnetic materials plays a pivotal role in modifying their magnetic characteristics, engendering hybrid quasiparticles, and implementing functional devices. Herein, we present our comprehensive and in-depth investigations on magnetic and lattice excitations of MnPSe3-xSx (x = 0, 0.5, and 1.5) alloys, utilizing temperature- and polarization-dependent Raman scattering. Our experimental results reveal the occurrence of multiple phase transitions, evidenced by notable changes in phonon self-energy and the appearance or splitting of phonon modes. These emergent phases are tied to the development of long and short-range spin-spin correlations, as well as to spin reorientations or magnetic instabilities. Our analysis of two-magnon excitations as a function of temperature and composition showcases their hybridization with phonons whose degree weakens with increasing x. Moreover, the suppression of spin-dependent phonon intensity in chemically most-disordered MnPSe3-xSx (x = 1.5) suggests that chalcogen substitution offers a control knob of tuning spin and phonon dynamics by modulating concurrently superexchange pathways and a degree of trigonal distortions.

We describe our contribution as industrial stakeholders to the existing open-source GPU4PySCF project (https: //github.com/pyscf/gpu4pyscf), a GPU-accelerated Python quantum chemistry package. We have integrated GPU acceleration into other PySCF functionality including Density Functional Theory (DFT), geometry optimization, frequency analysis, solvent models, and density fitting technique. Through these contributions, GPU4PySCF v1.0 can now be regarded as a fully functional and industrially relevant platform which we demonstrate in this work through a range of tests. When performing DFT calculations on modern GPU platforms, GPU4PySCF delivers 30 times speedup over a 32-core CPU node, resulting in approximately 90% cost savings for most DFT tasks. The performance advantages and productivity improvements have been found in multiple industrial applications, such as generating potential energy surfaces, analyzing molecular properties, calculating solvation free energy, identifying chemical reactions in lithium-ion batteries, and accelerating neural-network methods. With the improved design that makes it easy to integrate with the Python and PySCF ecosystem, GPU4PySCF is natural choice that we can now recommend for many industrial quantum chemistry applications., Comment: 40 pages, 14 figures

Despite the widespread applications of machine learning force field (MLFF) on solids and small molecules, there is a notable gap in applying MLFF to complex liquid electrolytes. In this work, we introduce BAMBOO (ByteDance AI Molecular Simulation Booster), a novel framework for molecular dynamics (MD) simulations, with a demonstration of its capabilities in the context of liquid electrolytes for lithium batteries. We design a physics-inspired graph equivariant transformer architecture as the backbone of BAMBOO to learn from quantum mechanical simulations. Additionally, we pioneer an ensemble knowledge distillation approach and apply it on MLFFs to improve the stability of MD simulations. Finally, we propose the density alignment algorithm to align BAMBOO with experimental measurements. BAMBOO demonstrates state-of-the-art accuracy in predicting key electrolyte properties such as density, viscosity, and ionic conductivity across various solvents and salt combinations. Our current model, trained on more than 15 chemical species, achieves the average density error of 0.01 g/cm$^3$ on various compositions compared with experimental data. Moreover, our model demonstrates transferability to molecules not included in the quantum mechanical dataset. We envision this work as paving the way to a "universal MLFF" capable of simulating properties of common organic liquids.

Recent advances in text-conditioned image generation diffusion models have begun paving the way for new opportunities in modern medical domain, in particular, generating Chest X-rays (CXRs) from diagnostic reports. Nonetheless, to further drive the diffusion models to generate CXRs that faithfully reflect the complexity and diversity of real data, it has become evident that a nontrivial learning approach is needed. In light of this, we propose CXRL, a framework motivated by the potential of reinforcement learning (RL). Specifically, we integrate a policy gradient RL approach with well-designed multiple distinctive CXR-domain specific reward models. This approach guides the diffusion denoising trajectory, achieving precise CXR posture and pathological details. Here, considering the complex medical image environment, we present "RL with Comparative Feedback" (RLCF) for the reward mechanism, a human-like comparative evaluation that is known to be more effective and reliable in complex scenarios compared to direct evaluation. Our CXRL framework includes jointly optimizing learnable adaptive condition embeddings (ACE) and the image generator, enabling the model to produce more accurate and higher perceptual CXR quality. Our extensive evaluation of the MIMIC-CXR-JPG dataset demonstrates the effectiveness of our RL-based tuning approach. Consequently, our CXRL generates pathologically realistic CXRs, establishing a new standard for generating CXRs with high fidelity to real-world clinical scenarios.