Search

With rapid digitization and digitalization, drawing a fine line between the digital and the physical world has become nearly impossible. It has become essential more than ever to integrate all spheres of life into a single Digital Thread to address pressing challenges of modern society: accessible and inclusive healthcare in terms of equality and equity. Techno-social advancements and mutual acceptance have enabled the infusion of digital models to simulate social settings with minimum resource utilization to make effective decisions. However, a significant gap exists in feeding back the models with appropriate real-time changes. In other words, active behavioral modeling of modern society is lacking, influencing community healthcare as a whole. By creating virtual replicas of (physical) behavioral systems, digital twins can enable real-time monitoring, simulation, and optimization of urban dynamics. This paper explores the potential of digital twins to promote inclusive healthcare for evolving smart cities. We argue that digital twins can be used to: Identify and address disparities in access to healthcare services, Facilitate community participation, Simulate the impact of urban policies and interventions on different groups of people, and Aid policy-making bodies for better access to healthcare. This paper proposes several ways to use digital twins to stitch the actual and virtual societies. Several discussed concepts within this framework envision an active, integrated, and synchronized community aware of data privacy and security. The proposal also provides high-level step-wise transitions that will enable this transformation., Comment: 13 pages, 1 figure. This is accepted to publish at the proceedings of the 6th International Conference on Artificial Intelligence and Applied Mathematics in Engineering (ICAIAME 2024)

Transformer based methods have enabled users to create, modify, and comprehend text and image data. Recently proposed Large Reconstruction Models (LRMs) further extend this by providing the ability to generate high-quality 3D models with the help of a single object image. These models, however, lack the ability to manipulate or edit the finer details, such as adding standard design patterns or changing the color and reflectance of the generated objects, thus lacking fine-grained control that may be very helpful in domains such as augmented reality, animation and gaming. Naively training LRMs for this purpose would require generating precisely edited images and 3D object pairs, which is computationally expensive. In this paper, we propose Instructive3D, a novel LRM based model that integrates generation and fine-grained editing, through user text prompts, of 3D objects into a single model. We accomplish this by adding an adapter that performs a diffusion process conditioned on a text prompt specifying edits in the triplane latent space representation of 3D object models. Our method does not require the generation of edited 3D objects. Additionally, Instructive3D allows us to perform geometrically consistent modifications, as the edits done through user-defined text prompts are applied to the triplane latent representation thus enhancing the versatility and precision of 3D objects generated. We compare the objects generated by Instructive3D and a baseline that first generates the 3D object meshes using a standard LRM model and then edits these 3D objects using text prompts when images are provided from the Objaverse LVIS dataset. We find that Instructive3D produces qualitatively superior 3D objects with the properties specified by the edit prompts., Comment: Accepted at WACV 2025. First two authors contributed equally

The Solar Ultraviolet Imaging Telescope (SUIT) is an instrument on the Aditya-L1 mission of the Indian Space Research Organization (ISRO) launched on September 02, 2023. SUIT continuously provides, near-simultaneous full-disk and region-of-interest images of the Sun, slicing through the photosphere and chromosphere and covering a field of view up to 1.5 solar radii. For this purpose, SUIT uses 11 filters tuned at different wavelengths in the 200{--}400~nm range, including the Mg~{\sc ii} h~and~k and Ca~{\sc ii}~H spectral lines. The observations made by SUIT help us understand the magnetic coupling of the lower and middle solar atmosphere. In addition, for the first time, it allows the measurements of spatially resolved solar broad-band radiation in the near and mid ultraviolet, which will help constrain the variability of the solar ultraviolet irradiance in a wavelength range that is central for the chemistry of the Earth's atmosphere. This paper discusses the details of the instrument and data products., Comment: 37 pages, Accepted for Publication in Solar Physics

Non-local systems of conservation laws play a crucial role in modeling flow mechanisms across various scenarios. The well-posedness of such problems is typically established by demonstrating the convergence of robust first-order schemes. However, achieving more accurate solutions necessitates the development of higher-order schemes. In this article, we present a fully discrete, second-order scheme for a general class of non-local conservation law systems in multiple spatial dimensions. The method employs a MUSCL-type spatial reconstruction coupled with Runge-Kutta time integration. The proposed scheme is proven to preserve positivity in all the unknowns and exhibits L-infinity stability. Numerical experiments conducted on both the non-local scalar and system cases illustrate the8 importance of second-order scheme when compared to its first-order counterpart.

Detecting sarcasm effectively requires a nuanced understanding of context, including vocal tones and facial expressions. The progression towards multimodal computational methods in sarcasm detection, however, faces challenges due to the scarcity of data. To address this, we present AMuSeD (Attentive deep neural network for MUltimodal Sarcasm dEtection incorporating bi-modal Data augmentation). This approach utilizes the Multimodal Sarcasm Detection Dataset (MUStARD) and introduces a two-phase bimodal data augmentation strategy. The first phase involves generating varied text samples through Back Translation from several secondary languages. The second phase involves the refinement of a FastSpeech 2-based speech synthesis system, tailored specifically for sarcasm to retain sarcastic intonations. Alongside a cloud-based Text-to-Speech (TTS) service, this Fine-tuned FastSpeech 2 system produces corresponding audio for the text augmentations. We also investigate various attention mechanisms for effectively merging text and audio data, finding self-attention to be the most efficient for bimodal integration. Our experiments reveal that this combined augmentation and attention approach achieves a significant F1-score of 81.0% in text-audio modalities, surpassing even models that use three modalities from the MUStARD dataset., Comment: This is a preprint version of the paper, submitted and under review at the IEEE Transactions on Affective Computing

Object detectors, which are widely used in real-world applications, are vulnerable to backdoor attacks. This vulnerability arises because many users rely on datasets or pre-trained models provided by third parties due to constraints on data and resources. However, most research on backdoor attacks has focused on image classification, with limited investigation into object detection. Furthermore, the triggers for most existing backdoor attacks on object detection are manually generated, requiring prior knowledge and consistent patterns between the training and inference stages. This approach makes the attacks either easy to detect or difficult to adapt to various scenarios. To address these limitations, we propose novel twin trigger generative networks in the frequency domain to generate invisible triggers for implanting stealthy backdoors into models during training, and visible triggers for steady activation during inference, making the attack process difficult to trace. Specifically, for the invisible trigger generative network, we deploy a Gaussian smoothing layer and a high-frequency artifact classifier to enhance the stealthiness of backdoor implantation in object detectors. For the visible trigger generative network, we design a novel alignment loss to optimize the visible triggers so that they differ from the original patterns but still align with the malicious activation behavior of the invisible triggers. Extensive experimental results and analyses prove the possibility of using different triggers in the training stage and the inference stage, and demonstrate the attack effectiveness of our proposed visible trigger and invisible trigger generative networks, significantly reducing the mAP_0.5 of the object detectors by 70.0% and 84.5%, including YOLOv5 and YOLOv7 with different settings, respectively., Comment: 13 pages, 8 figures

Video understanding has made huge strides in recent years, relying largely on the power of the transformer architecture. As this architecture is notoriously expensive and video is highly redundant, research into improving efficiency has become particularly relevant. This has led to many creative solutions, including token merging and token selection. While most methods succeed in reducing the cost of the model and maintaining accuracy, an interesting pattern arises: most methods do not outperform the random sampling baseline. In this paper we take a closer look at this phenomenon and make several observations. First, we develop an oracle for the value of tokens which exposes a clear Pareto distribution where most tokens have remarkably low value, and just a few carry most of the perceptual information. Second, we analyze why this oracle is extremely hard to learn, as it does not consistently coincide with visual cues. Third, we observe that easy videos need fewer tokens to maintain accuracy. We build on these and further insights to propose a lightweight video model we call LITE that can select a small number of tokens effectively, outperforming state-of-the-art and existing baselines across datasets (Kinetics400 and Something-Something-V2) in the challenging trade-off of computation (GFLOPs) vs accuracy.

Transition metal telluride compositions are explored extensively for their unique magnetic behavior. Since chromium telluride (Cr2Te3) exhibits a near-room-temperature phase transition, the material can be effectively used in applications such as magnetic refrigeration. Compared to existing magnetocaloric materials, Heusler alloys, and rare-earth-based alloys, the large-scale synthesis of Cr2Te3 involves less complexity, resulting in a stable composition. Compared to existing tellurides, Cr2Te3 exhibited a large magnetic entropy change of 2.36 J/kg-K at a very small magnetic field of 0.1 T. The refrigeration capacity (RC) of 160 J/kg was determined from entropy change versus temperature curve. The results were comparable with the existing Cr compounds. The telluride system, Cr2Te3 compared to pure gadolinium, reveals an enhanced room temperature magnetocaloric effect (MCE) with a broad working temperature range. The heating cycle of MCE was successfully visualized using a thermal imaging setup. To confirm the observed magnetic properties of Cr2Te3, first-principles calculations were conducted. Through density functional theory (DFT) studies, we were able to determine both Curie temperature (TC) and Neel temperature (TN) which validated our experimental transitions at the same temperatures. Structural transition was also observed using first principles DFT calculation which is responsible for magnetic behavior.

Diffusion models have recently emerged as a potent tool in generative modeling. However, their inherent iterative nature often results in sluggish image generation due to the requirement for multiple model evaluations. Recent progress has unveiled the intrinsic link between diffusion models and Probability Flow Ordinary Differential Equations (ODEs), thus enabling us to conceptualize diffusion models as ODE systems. Simultaneously, Physics Informed Neural Networks (PINNs) have substantiated their effectiveness in solving intricate differential equations through implicit modeling of their solutions. Building upon these foundational insights, we introduce Physics Informed Distillation (PID), which employs a student model to represent the solution of the ODE system corresponding to the teacher diffusion model, akin to the principles employed in PINNs. Through experiments on CIFAR 10 and ImageNet 64x64, we observe that PID achieves performance comparable to recent distillation methods. Notably, it demonstrates predictable trends concerning method-specific hyperparameters and eliminates the need for synthetic dataset generation during the distillation process. Both of which contribute to its easy-to-use nature as a distillation approach for Diffusion Models. Our code and pre-trained checkpoint are publicly available at: https://github.com/pantheon5100/pid_diffusion.git.

Twists are defects that are used to encode and process quantum information in topological codes like surface and color codes. Color codes can host three basic types of twists viz., charge-permuting, color-permuting and domino twists. In this paper, we study domino twists from the viewpoint of computation. Specifically, we give a systematic construction for domino twists in qubit color codes. We also present protocols for measurement of logical qubits. Finally, we show that all Clifford gates can be implemented by braiding twists., Comment: Submitted to QIP journal on Feb 29, 2024. This is the revised manuscript

Each year, millions of individuals lose the ability to speak intelligibly due to causes such as neuromuscular disease, stroke, trauma, and head/neck cancer surgery (e.g. laryngectomy) or treatment (e.g. radiotherapy toxicity to the speech articulators). Effective communication is crucial for daily activities, and losing the ability to speak leads to isolation, depression, anxiety, and a host of detrimental sequelae. Noninvasive surface electromyography (sEMG) has shown promise to restore speech output in these individuals. The goal is to collect sEMG signals from multiple articulatory sites as people silently produce speech and then decode the signals to enable fluent and natural communication. Currently, many fundamental properties of orofacial neuromuscular signals relating to speech articulation remain unanswered. They include questions relating to 1) the data structure of the orofacial sEMG signals, 2)the signal distribution shift of sEMG across individuals, 3) ability of sEMG signals to span the entire English language phonetic space during silent speech articulations, and 4) the generalization capability of non-invasive sEMG based silent speech interfaces. We address these questions through a series of experiments involving healthy human subjects. We show that sEMG signals evince graph data structure and that the signal distribution shift is given by a change of basis. Furthermore, we show that silently voiced articulations spanning the entire English language phonetic space can be decoded using small neural networks which can be trained with little data and that such architectures work well across individuals. To ensure transparency and reproducibility, we open-source all the data and codes used in this study.

To increase driver awareness in a fully autonomous vehicle, we developed several haptic interaction prototypes that signal what the car is planning to do next. The goal was to use haptic cues so that the driver could be situation aware but not distracted from the non-driving tasks they may be engaged in. This paper discusses the three prototypes tested and the guiding metaphor behind each concept. We also highlight the Wizard of Oz protocol adopted to test the haptic interaction prototypes and some key findings from the pilot study., Comment: Copyright held by authors, AutomotiveUI'15 September 1-3, 2015, Nottingham, UK, ACM 978-1-4503-3736-6

This paper introduces mmWave-Whisper, a system that demonstrates the feasibility of full-corpus automated speech recognition (ASR) on phone calls eavesdropped remotely using off-the-shelf frequency modulated continuous wave (FMCW) millimeter-wave radars. Operating in the 77-81 GHz range, mmWave-Whisper captures earpiece vibrations from smartphones, converts them into audio, and processes the audio to produce speech transcriptions automatically. Unlike previous work that focused on loudspeakers or limited vocabulary, this is the first work to perform such a speech recognition by handling large vocabulary and full sentences on earpiece vibrations from smartphones. This approach expands the potential of radar-audio eavesdropping. mmWave-Whisper addresses challenges such as the lack of large scale training datasets, low SNR, and limited frequency information in radar data through a systematic pipeline designed to leverage synthetic training data, domain adaptation, and inference by incorporating OpenAI's Whisper automatic speech recognition model. The system achieves a word accuracy rate of 44.74% and a character accuracy rate of 62.52% over a range of 25 cm to 125 cm. The paper highlights emerging misuse modalities of AI as the technology evolves rapidly., Comment: 5 pages, 4 figures, 1 table

Due to the growing volume of user generated content, hashtags are employed as topic indicators to manage content efficiently on social media platforms. However, finding these vital topics is challenging in microvideos since they contain substantial information in a short duration. Existing methods that recommend hashtags for microvideos primarily focus on content and personalization while disregarding relatedness among users. Moreover, the cold start user issue prevails in hashtag recommendation systems. Considering the above, we propose a hybrid filtering based MIcro-video haSHtag recommendatiON MISHON technique to recommend hashtags for micro-videos. Besides content based filtering, we employ user-based collaborative filtering to enhance recommendations. Since hashtags reflect users topical interests, we find similar users based on historical tagging behavior to model user relatedness. We employ a graph-based deep neural network to model user to user, modality to modality, and user to modality interactions. We then use refined modality specific and user representations to recommend pertinent hashtags for microvideos. The empirical results on three real world datasets demonstrate that MISHON attains a comparative enhancement of 3.6, 2.8, and 6.5 reported in percentage concerning the F1 score, respectively. Since cold start users exist whose historical tagging information is unavailable, we also propose a content and social influence based technique to model the relatedness of cold start users with influential users. The proposed solution shows a relative improvement of 15.8 percent in the F1 score over its content only counterpart. These results show that the proposed framework mitigates the cold start user problem.

Zero-shot action recognition requires a strong ability to generalize from pre-training and seen classes to novel unseen classes. Similarly, continual learning aims to develop models that can generalize effectively and learn new tasks without forgetting the ones previously learned. The generalization goals of zero-shot and continual learning are closely aligned, however techniques from continual learning have not been applied to zero-shot action recognition. In this paper, we propose a novel method based on continual learning to address zero-shot action recognition. This model, which we call {\em Generative Iterative Learning} (GIL) uses a memory of synthesized features of past classes, and combines these synthetic features with real ones from novel classes. The memory is used to train a classification model, ensuring a balanced exposure to both old and new classes. Experiments demonstrate that {\em GIL} improves generalization in unseen classes, achieving a new state-of-the-art in zero-shot recognition across multiple benchmarks. Importantly, {\em GIL} also boosts performance in the more challenging generalized zero-shot setting, where models need to retain knowledge about classes seen before fine-tuning., Comment: Accepted in ACCV 2024

We introduce homological measurement, a framework for measuring the logical Pauli operators encoded in CSS stabilizer codes. The framework is based on the algebraic description of such codes as chain complexes. Protocols such as lattice surgery some of its recent generalizations are shown to be special cases of homological measurement. Using this framework, we develop a specific protocol called edge expanded homological measurement for fault-tolerant measurement of arbitrary logical Pauli operators of general qLDPC codes, requiring a number of ancillary qubits growing only linearly with the weight of the logical operator measured, and guaranteed that the distance of the code is preserved. We further benchmark our protocol numerically in a photonic architecture based on GKP qubits, showing that the logical error rate of various codes are on par with other methods requiring more ancilla qubits., Comment: 20 pages, 5 figures, 5 tables. Version 2 fixes a mistake in section 3.4 and briefly addresses related recent work

Brain-body-computer interfaces aim to provide a fluid and natural way for humans to interact with technology. Among noninvasive interfaces, surface electromyogram (sEMG) signals have shown particular utility. However, much remains unknown about how sEMG is affected by various physiological and anatomical factors and how these confounds might affect gesture decoding across individuals or groups. In this article, we show that sEMG signals evince non-Euclidean graph data structure that is defined by a set of orthogonal axes and explain the signal distribution shift across individuals. We provide a dataset of upper limb sEMG signals and physiological measures of 91 adults as they perform 10 different hand gestures. Participants were selected to be representative of various age groups (18to 92 years) and BMI (healthy, overweight, and obese). Additional anatomical or physiological measures that might impact sEMG signals were also collected, such as skin hydration and elasticity. The article describes the inherent structure of sEMG data and provides methods to construct differentiable signal features that can be used with machine learning algorithms that use backpropagation. We then analyze how those parameters correlate with various physiological measures to probe if they can induce bias against (or towards) certain population groups. We find that higher frequencies in sEMG, although comprising less power than lower ones, provide better gesture decoding and show less bias with regard to demographic, circumstantial, and physiological confounds (such as age, skin hydration, and skin elasticity)., Comment: 24 pages

The deep learning language of choice these days is Python; measured by factors such as available libraries and technical support, it is hard to beat. At the same time, software written in lower-level programming languages like C++ retain advantages in speed. We describe a Python interface to Marian NMT, a C++-based training and inference toolkit for sequence-to-sequence models, focusing on machine translation. This interface enables models trained with Marian to be connected to the rich, wide range of tools available in Python. A highlight of the interface is the ability to compute state-of-the-art COMET metrics from Python but using Marian's inference engine, with a speedup factor of up to 7.8$\times$ the existing implementations. We also briefly spotlight a number of other integrations, including Jupyter notebooks, connection with prebuilt models, and a web app interface provided with the package. PyMarian is available in PyPI via $\texttt{pip install pymarian}$.

Utilizing large pre-trained models for specific tasks has yielded impressive results. However, fully fine-tuning these increasingly large models is becoming prohibitively resource-intensive. This has led to a focus on more parameter-efficient transfer learning, primarily within the same modality. But this approach has limitations, particularly in video understanding where suitable pre-trained models are less common. Addressing this, our study introduces a novel cross-modality transfer learning approach from images to videos, which we call parameter-efficient image-to-video transfer learning. We present the Facial-Emotion Adapter (FE-Adapter), designed for efficient fine-tuning in video tasks. This adapter allows pre-trained image models, which traditionally lack temporal processing capabilities, to analyze dynamic video content efficiently. Notably, it uses about 15 times fewer parameters than previous methods, while improving accuracy. Our experiments in video emotion recognition demonstrate that the FE-Adapter can match or even surpass existing fine-tuning and video emotion models in both performance and efficiency. This breakthrough highlights the potential for cross-modality approaches in enhancing the capabilities of AI models, particularly in fields like video emotion analysis where the demand for efficiency and accuracy is constantly rising.

The Segment Anything Model (SAM) has achieved remarkable successes in the realm of natural image segmentation, but its deployment in the medical imaging sphere has encountered challenges. Specifically, the model struggles with medical images that feature low contrast, faint boundaries, intricate morphologies, and small-sized objects. To address these challenges and enhance SAM's performance in the medical domain, we introduce a comprehensive modification. Firstly, we incorporate a frozen Convolutional Neural Network (CNN) branch as an image encoder, which synergizes with SAM's original Vision Transformer (ViT) encoder through a novel variational attention fusion module. This integration bolsters the model's capability to capture local spatial information, which is often paramount in medical imagery. Moreover, to further optimize SAM for medical imaging, we introduce feature and position adapters within the ViT branch, refining the encoder's representations. We see that compared to current prompting strategies to fine-tune SAM for ultrasound medical segmentation, the use of text descriptions that serve as text prompts for SAM helps significantly improve the performance. Leveraging ChatGPT's natural language understanding capabilities, we generate prompts that offer contextual information and guidance to SAM, enabling it to better understand the nuances of ultrasound medical images and improve its segmentation accuracy. Our method, in its entirety, represents a significant stride towards making universal image segmentation models more adaptable and efficient in the medical domain., Comment: Accepted to ECCV 2024

This is the preliminary ranking of WMT24 General MT systems based on automatic metrics. The official ranking will be a human evaluation, which is superior to the automatic ranking and supersedes it. The purpose of this report is not to interpret any findings but only provide preliminary results to the participants of the General MT task that may be useful during the writing of the system submission.

Following the rapid progress in natural language processing (NLP) models, language models are applied to increasingly more complex interactive tasks such as negotiations and conversation moderations. Having human evaluators directly interact with these NLP models is essential for adequately evaluating the performance on such interactive tasks. We develop BotEval, an easily customizable, open-source, evaluation toolkit that focuses on enabling human-bot interactions as part of the evaluation process, as opposed to human evaluators making judgements for a static input. BotEval balances flexibility for customization and user-friendliness by providing templates for common use cases that span various degrees of complexity and built-in compatibility with popular crowdsourcing platforms. We showcase the numerous useful features of BotEval through a study that evaluates the performance of various chatbots on their effectiveness for conversational moderation and discuss how BotEval differs from other annotation tools., Comment: ACL 2024 SDT, 10 pages

Contemporary medical contrastive learning faces challenges from inconsistent semantics and sample pair morphology, leading to dispersed and converging semantic shifts. The variability in text reports, due to multiple authors, complicates semantic consistency. To tackle these issues, we propose a two-step approach. Initially, text reports are converted into a standardized triplet format, laying the groundwork for our novel concept of ``observations'' and ``verdicts''. This approach refines the {Entity, Position, Exist} triplet into binary questions, guiding towards a clear ``verdict''. We also innovate in visual pre-training with a Meijering-based masking, focusing on features representative of medical images' local context. By integrating this with our text conversion method, our model advances cross-modal representation in a multimodal contrastive learning framework, setting new benchmarks in medical image analysis., Comment: Accepted in MICCAI-24

This paper focuses on the educational journey of a computer engineering undergraduate student venturing into the domain of computer vision and robotics. It explores how optical flow and its applications can be used to detect moving objects when a camera undergoes translational motion, highlighting the challenges encountered and the strategies used to overcome them. Furthermore, the paper discusses not only the technical skills acquired by the student but also interpersonal skills as related to teamwork and diversity. In this paper, we detail the learning process, including the acquisition of technical and problem-solving skills, as well as out-of-the-box thinking., Comment: 20 Pages

A vast majority of electrical devices have integrated magnetic units, which generate constant magnetic fields with noticeable vibrations. The majority of existing nanogenerators acquire energy through friction/mechanical forces and most of these instances overlook acoustic vibrations and magnetic fields. Magnetic two-dimensional (2D) tellurides present a wide range of possibilities for devising a potential flexible energy harvester. We have synthesized two-dimensional chromium telluride (2D CrTe3) which exhibits ferromagnetic (FM) nature with a Tc of 224 K. The structure exhibits stable high remnant magnetization, making 2D CrTe3 flakes a potential material for harvesting of magneto-acoustic waves at room temperature. A magneto-acoustic nanogenerator (MANG) was fabricated composing of 2D CrTe3 dispersed in a polymer matrix. Basic mechanical stability and sensitivity of the device with change in load conditions were tested. A high surface charge density of 2.919 mC m-2 was obtained for the device. The thermal strain created in the lattice structure was examined using in-situ Raman spectroscopic measurements. The magnetic anisotropy energy (MAE) responsible for long-range FM ordering was calculated with the help of theoretical modelling. The theoretical calculations also showed opening of electronic bandgap which enhances the flexoelectric effects. The MANG can be a potential energy harvester to synergistically tap into the magneto-acoustic vibrations generated from the frequency changes of a vibrating device such as loudspeakers.

Two-dimensional (2D) chromium telluride Cr2Te3 exhibits strong ferromagnetic ordering with high coercivity at low temperatures and paramagnetic behaviour when approaching room temperature. The spin states of monolayer Cr2Te3 show ferromagnetic ordering in the ground state, and in-situ Raman analysis shows reversible structure transformation and hence a ferromagnetic to paramagnetic transition during low-temperature heating cycles (0 - 25 {\deg}C). The magnetic phase transition near room temperature in the 2D Cr2Te3 prompted the exploration of these layered materials for energy application. We demonstrate that the low-temperature ferromagnetic behavior can be used to magnetically deice material surfaces using an external magnetic source, avoiding the use of harsh chemicals and high temperatures. The hydrophobic nature and dipole interactions of H2O molecules with the surface of the 2D Cr2Te3 coating aid in the condensation of ice droplets formed on the surface. First-principles calculations also confirm the observed crystal structure, surface interaction, and magnetic properties of 2D Cr2Te3.

Audio classification models, particularly the Audio Spectrogram Transformer (AST), play a crucial role in efficient audio analysis. However, optimizing their efficiency without compromising accuracy remains a challenge. In this paper, we introduce FastAST, a framework that integrates Token Merging (ToMe) into the AST framework. FastAST enhances inference speed without requiring extensive retraining by merging similar tokens in audio spectrograms. Furthermore, during training, FastAST brings about significant speed improvements. The experiments indicate that FastAST can increase audio classification throughput with minimal impact on accuracy. To mitigate the accuracy impact, we integrate Cross-Model Knowledge Distillation (CMKD) into the FastAST framework. Integrating ToMe and CMKD into AST results in improved accuracy compared to AST while maintaining faster inference speeds. FastAST represents a step towards real-time, resource-efficient audio analysis., Comment: Accepted to Interspeech 2024

We give an efficient algorithm for Centroid-Linkage Hierarchical Agglomerative Clustering (HAC), which computes a $c$-approximate clustering in roughly $n^{1+O(1/c^2)}$ time. We obtain our result by combining a new Centroid-Linkage HAC algorithm with a novel fully dynamic data structure for nearest neighbor search which works under adaptive updates. We also evaluate our algorithm empirically. By leveraging a state-of-the-art nearest-neighbor search library, we obtain a fast and accurate Centroid-Linkage HAC algorithm. Compared to an existing state-of-the-art exact baseline, our implementation maintains the clustering quality while delivering up to a $36\times$ speedup due to performing fewer distance comparisons.

Zero-Shot Learning (ZSL) aims to enable classifiers to identify unseen classes by enhancing data efficiency at the class level. This is achieved by generating image features from pre-defined semantics of unseen classes. However, most current approaches heavily depend on the number of samples from seen classes, i.e. they do not consider instance-level effectiveness. In this paper, we demonstrate that limited seen examples generally result in deteriorated performance of generative models. To overcome these challenges, we propose ZeroDiff, a Diffusion-based Generative ZSL model. This unified framework incorporates diffusion models to improve data efficiency at both the class and instance levels. Specifically, for instance-level effectiveness, ZeroDiff utilizes a forward diffusion chain to transform limited data into an expanded set of noised data. For class-level effectiveness, we design a two-branch generation structure that consists of a Diffusion-based Feature Generator (DFG) and a Diffusion-based Representation Generator (DRG). DFG focuses on learning and sampling the distribution of cross-entropy-based features, whilst DRG learns the supervised contrastive-based representation to boost the zero-shot capabilities of DFG. Additionally, we employ three discriminators to evaluate generated features from various aspects and introduce a Wasserstein-distance-based mutual learning loss to transfer knowledge among discriminators, thereby enhancing guidance for generation. Demonstrated through extensive experiments on three popular ZSL benchmarks, our ZeroDiff not only achieves significant improvements over existing ZSL methods but also maintains robust performance even with scarce training data. Code will be released upon acceptance.