Search

Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spoken language model that comprehends a wide range of natural language instructions is critical for bridging communication gaps and facilitating more intuitive interactions. However, the absence of a comprehensive evaluation benchmark poses a significant challenge. We present Dynamic-SUPERB Phase-2, an open and evolving benchmark for the comprehensive evaluation of instruction-based universal speech models. Building upon the first generation, this second version incorporates 125 new tasks contributed collaboratively by the global research community, expanding the benchmark to a total of 180 tasks, making it the largest benchmark for speech and audio evaluation. While the first generation of Dynamic-SUPERB was limited to classification tasks, Dynamic-SUPERB Phase-2 broadens its evaluation capabilities by introducing a wide array of novel and diverse tasks, including regression and sequence generation, across speech, music, and environmental audio. Evaluation results indicate that none of the models performed well universally. SALMONN-13B excelled in English ASR, while WavLLM demonstrated high accuracy in emotion recognition, but current models still require further innovations to handle a broader range of tasks. We will soon open-source all task data and the evaluation pipeline.

World models integrate raw data from various modalities, such as images and language to simulate comprehensive interactions in the world, thereby displaying crucial roles in fields like mixed reality and robotics. Yet, applying the world model for accurate video prediction is quite challenging due to the complex and dynamic intentions of the various scenes in practice. In this paper, inspired by the human rethinking process, we decompose the complex video prediction into four meta-tasks that enable the world model to handle this issue in a more fine-grained manner. Alongside these tasks, we introduce a new benchmark named Embodied Video Anticipation Benchmark (EVA-Bench) to provide a well-rounded evaluation. EVA-Bench focused on evaluating the video prediction ability of human and robot actions, presenting significant challenges for both the language model and the generation model. Targeting embodied video prediction, we propose the Embodied Video Anticipator (EVA), a unified framework aiming at video understanding and generation. EVA integrates a video generation model with a visual language model, effectively combining reasoning capabilities with high-quality generation. Moreover, to enhance the generalization of our framework, we tailor-designed a multi-stage pretraining paradigm that adaptatively ensembles LoRA to produce high-fidelity results. Extensive experiments on EVA-Bench highlight the potential of EVA to significantly improve performance in embodied scenes, paving the way for large-scale pre-trained models in real-world prediction tasks.

For superconducting quantum processors, stable high-fidelity two-qubit operations depend on precise flux control of the tunable coupler. However, the pulse distortion poses a significant challenge to the control precision. Current calibration methods, which often rely on microwave crosstalk or additional readout resonators for coupler excitation and readout, tend to be cumbersome and inefficient, especially when couplers only have flux control. Here, we introduce and experimentally validate a novel pulse calibration scheme that exploits the strong coupling between qubits and couplers, eliminating the need for extra coupler readout and excitation. Our method directly measures the short-time and long-time step responses of the coupler flux pulse transient, enabling us to apply predistortion to subsequent signals using fast Fourier transformation and deconvolution. This approach not only simplifies the calibration process but also significantly improves the precision and stability of the flux control. We demonstrate the efficacy of our method through the implementation of diabatic CZ and iSWAP gates with fidelities of $99.61\pm0.04\%$ and $99.82\pm0.02\%$, respectively, as well as a series of diabatic CPhase gates with high fidelities characterized by cross-entropy benchmarking. The consistency and robustness of our technique are further validated by the reduction in pulse distortion and phase error observed across multilayer CZ gates. These results underscore the potential of our calibration and predistortion method to enhance the performance of two-qubit gates in superconducting quantum processors., Comment: 16 pages, 11 figures, 7 tables

$N{:}M$ sparsity is an emerging model compression method supported by more and more accelerators to speed up sparse matrix multiplication in deep neural networks. Most existing $N{:}M$ sparsity methods compress neural networks with a uniform setting for all layers in a network or heuristically determine the layer-wise configuration by considering the number of parameters in each layer. However, very few methods have been designed for obtaining a layer-wise customized $N{:}M$ sparse configuration for vision transformers (ViTs), which usually consist of transformer blocks involving the same number of parameters. In this work, to address the challenge of selecting suitable sparse configuration for ViTs on $N{:}M$ sparsity-supporting accelerators, we propose ELSA, Exploiting Layer-wise $N{:}M$ Sparsity for ViTs. Considering not only all $N{:}M$ sparsity levels supported by a given accelerator but also the expected throughput improvement, our methodology can reap the benefits of accelerators supporting mixed sparsity by trading off negligible accuracy loss with both memory usage and inference time reduction for ViT models. For instance, our approach achieves a noteworthy 2.9$\times$ reduction in FLOPs for both Swin-B and DeiT-B with only a marginal degradation of accuracy on ImageNet. Our code will be released upon paper acceptance.

Hyperspectral image (HSI) classification involves assigning unique labels to each pixel to identify various land cover categories. While deep classifiers have achieved high predictive accuracy in this field, they lack the ability to rigorously quantify confidence in their predictions. Quantifying the certainty of model predictions is crucial for the safe usage of predictive models, and this limitation restricts their application in critical contexts where the cost of prediction errors is significant. To support the safe deployment of HSI classifiers, we first provide a theoretical proof establishing the validity of the emerging uncertainty quantification technique, conformal prediction, in the context of HSI classification. We then propose a conformal procedure that equips any trained HSI classifier with trustworthy prediction sets, ensuring that these sets include the true labels with a user-specified probability (e.g., 95\%). Building on this foundation, we introduce Spatial-Aware Conformal Prediction (\texttt{SACP}), a conformal prediction framework specifically designed for HSI data. This method integrates essential spatial information inherent in HSIs by aggregating the non-conformity scores of pixels with high spatial correlation, which effectively enhances the efficiency of prediction sets. Both theoretical and empirical results validate the effectiveness of our proposed approach. The source code is available at \url{https://github.com/J4ckLiu/SACP}.

Sensing human motions through Inertial Measurement Units (IMUs) embedded in personal devices has enabled significant applications in health and wellness. While labeled IMU data is scarce, we can collect unlabeled or weakly labeled IMU data to model human motions. For video or text modalities, the "pretrain and adapt" approach utilizes large volumes of unlabeled or weakly labeled data for pretraining, building a strong feature extractor, followed by adaptation to specific tasks using limited labeled data. This approach has not been widely adopted in the IMU domain for two reasons: (1) pretraining methods are poorly understood in the context of IMU, and (2) open-source pretrained models that generalize across datasets are rarely publicly available. In this paper, we aim to address the first issue by proposing PRIMUS, a method for PRetraining IMU encoderS. We conduct a systematic and unified evaluation of various self-supervised and multimodal learning pretraining objectives. Our findings indicate that using PRIMUS, which combines self-supervision, multimodal supervision, and nearest-neighbor supervision, can significantly enhance downstream performance. With fewer than 500 labeled samples per class, PRIMUS effectively enhances downstream performance by up to 15% in held-out test data, compared to the state-of-the-art multimodal training method. To benefit the broader community, our code and pre-trained IMU encoders will be made publicly available at github.com/nokia-bell-labs upon publication., Comment: Also presented under the title "PRIMUS: Pretraining IMU Encoders with Multimodal and Self-Supervised Learning" at NeurIPS 2024 TSALM Workshop (Time Series in the Age of Large Models)

RISC-V's limited security features hinder its use in confidential computing and heterogeneous platforms. This paper introduces RISecure-PUF, a security extension utilizing existing Physical Unclonable Functions for key generation and secure protocol purposes. A one-way hash function is integrated to ensure provable security against modeling attacks, while a lookaside buffer accelerates batch sampling and minimizes reliance on error correction codes. Implemented on the Genesys 2 FPGA, RISecure-PUF improves at least $2.72\times$ in batch scenarios with negligible hardware overhead and a maximum performance reduction of $10.7\%$, enabled by reusing the hash function module in integrated environments such as cryptographic engines.

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in the number of visual tokens input into LLMs, resulting in significant computational costs. Current work develop visual token compression methods to achieve efficiency improvements, often at the expense of performance. We argue that removing visual redundancy can simultaneously improve both efficiency and performance. We build a coarse-to-fine visual token compression method, with a vision-guided sampler for compressing redundant regions with low information density, and a text-guided sampler for selecting visual tokens that are strongly correlated with the user instructions.With these two modules, the proposed FocusLLaVA achieves improvements in both efficiency and performance. We validate the effectiveness of our approach on a wide range of evaluation datasets.

The evolution of the lunar magnetic field can reveal the Moon's interior structure, thermal history, and surface environment. The mid-to-late stage evolution of the lunar magnetic field is poorly constrained, and thus the existence of a long-lived lunar dynamo remains controversial. The Chang'e-5 mission returned the heretofore youngest mare basalts from Oceanus Procellarum uniquely positioned at mid-latitude. We recovered weak paleointensities of 2-4 uT from the Chang'e-5 basalt clasts at 2 billion years ago, attestting to the longevity of a lunar dynamo until at least the Moon's midlife. This paleomagnetic result implies the existence of thermal convection in the lunar deep interior at the lunar mid-stage which may have supplied mantle heat flux for the young volcanism.

We model a spin-phase transition in a two-dimensional square array, or a lateral superlattice, of quantum rings in an external perpendicular homogeneous magnetic field. The electron system is placed in a circular cylindrical far-infrared photon cavity with a single circularly symmetric photon mode. Our numerical results reveal that the spin ordering of the two-dimensional electron gas in each quantum ring can be influenced or controlled by the electron-photon coupling strength and the energy of the photons. The Coulomb interaction between the electrons is described by a spin-density functional approach, but the para- and the diamagnetic electron-photon interactions are modeled via a configuration interaction formalism in a truncated many-body Fock-space, which is updated in each iteration step of the density functional approach. In the absence of external electromagnetic pulses this spin-phase transition is replicated in the orbital magnetization of the rings. The spin-phase transition can be suppressed by a strong electron-photon interaction. In addition, fluctuations in the spin configuration are found in dynamical calculations, where the system is excited by a time-dependent scheme specially fit for emphasizing the diamagnetic electron-photon interaction., Comment: RevTeX - pdfLaTeX, 11 pages with 9 included pdf figures

Given the rising proliferation and diversity of AI writing assistance tools, especially those powered by large language models (LLMs), both writers and readers may have concerns about the impact of these tools on the authenticity of writing work. We examine whether and how writers want to preserve their authentic voice when co-writing with AI tools and whether personalization of AI writing support could help achieve this goal. We conducted semi-structured interviews with 19 professional writers, during which they co-wrote with both personalized and non-personalized AI writing-support tools. We supplemented writers' perspectives with opinions from 30 avid readers about the written work co-produced with AI collected through an online survey. Our findings illuminate conceptions of authenticity in human-AI co-creation, which focus more on the process and experience of constructing creators' authentic selves. While writers reacted positively to personalized AI writing tools, they believed the form of personalization needs to target writers' growth and go beyond the phase of text production. Overall, readers' responses showed less concern about human-AI co-writing. Readers could not distinguish AI-assisted work, personalized or not, from writers' solo-written work and showed positive attitudes toward writers experimenting with new technology for creative writing.

Oracle character recognition-an analysis of ancient Chinese inscriptions found on oracle bones-has become a pivotal field intersecting archaeology, paleography, and historical cultural studies. Traditional methods of oracle character recognition have relied heavily on manual interpretation by experts, which is not only labor-intensive but also limits broader accessibility to the general public. With recent breakthroughs in pattern recognition and deep learning, there is a growing movement towards the automation of oracle character recognition (OrCR), showing considerable promise in tackling the challenges inherent to these ancient scripts. However, a comprehensive understanding of OrCR still remains elusive. Therefore, this paper presents a systematic and structured survey of the current landscape of OrCR research. We commence by identifying and analyzing the key challenges of OrCR. Then, we provide an overview of the primary benchmark datasets and digital resources available for OrCR. A review of contemporary research methodologies follows, in which their respective efficacies, limitations, and applicability to the complex nature of oracle characters are critically highlighted and examined. Additionally, our review extends to ancillary tasks associated with OrCR across diverse disciplines, providing a broad-spectrum analysis of its applications. We conclude with a forward-looking perspective, proposing potential avenues for future investigations that could yield significant advancements in the field.

Synchronizing production and test code, known as PT co-evolution, is critical for software quality in the software development lifecycle. Existing methods for automatic PT co-evolution either utilize predefined heuristic rules or rely on simple application of machine learning techniques. Due to the limitations of underlying techniques, existing methods either only partially automate PT co-evolution (e.g., only automate obsolete test code identification) or result in low accuracy. In this paper, we propose REACCEPT, a novel approach that leverages large language models and dynamic validation to fully automate PT co-evolution (i.e., capable of both identifying and updating obsolete test cases). REACCEPT relies on experience-based prompt template generation, dynamic validation, and retrieval-augmented generation techniques to accomplish automated PT co-evolution. To evaluate REACCEPT's effectiveness, we extensive experiments with a dataset of 537 Java projects and compared REACCEPT's performance with several state-of-the-art methods. Results show that REACCEPT achieved an update accuracy of 60.16% on correctly identified obsolete test code, surpassing the state-of-the-art technique CEPROT by 90%. This confirms that REACCEPT can effectively assist developers in maintaining test code, improving overall software quality and reducing maintenance effort., Comment: 21 pages, 8 figures

Data contamination presents a critical barrier preventing widespread industrial adoption of advanced software engineering techniques that leverage code language models (CLMs). This phenomenon occurs when evaluation data inadvertently overlaps with the public code repositories used to train CLMs, severely undermining the credibility of performance evaluations. For software companies considering the integration of CLM-based techniques into their development pipeline, this uncertainty about true performance metrics poses an unacceptable business risk. Code refactoring, which comprises code restructuring and variable renaming, has emerged as a promising measure to mitigate data contamination. It provides a practical alternative to the resource-intensive process of building contamination-free evaluation datasets, which would require companies to collect, clean, and label code created after the CLMs' training cutoff dates. However, the lack of automated code refactoring tools and scientifically validated refactoring techniques has hampered widespread industrial implementation. To bridge the gap, this paper presents the first systematic study to examine the efficacy of code refactoring operators at multiple scales (method-level, class-level, and cross-class level) and in different programming languages. In particular, we develop an open-sourced toolkit, CODECLEANER, which includes 11 operators for Python, with nine method-level, one class-level, and one cross-class-level operator. A drop of 65% overlap ratio is found when applying all operators in CODECLEANER, demonstrating their effectiveness in addressing data contamination. Additionally, we migrate four operators to Java, showing their generalizability to another language. We make CODECLEANER online available to facilitate further studies on mitigating CLM data contamination.

We present a unified controllable video generation approach AnimateAnything that facilitates precise and consistent video manipulation across various conditions, including camera trajectories, text prompts, and user motion annotations. Specifically, we carefully design a multi-scale control feature fusion network to construct a common motion representation for different conditions. It explicitly converts all control information into frame-by-frame optical flows. Then we incorporate the optical flows as motion priors to guide final video generation. In addition, to reduce the flickering issues caused by large-scale motion, we propose a frequency-based stabilization module. It can enhance temporal coherence by ensuring the video's frequency domain consistency. Experiments demonstrate that our method outperforms the state-of-the-art approaches. For more details and videos, please refer to the webpage: https://yu-shaonian.github.io/Animate_Anything/.

Chest X-rays (CXRs) often display various diseases with disparate class frequencies, leading to a long-tailed, multi-label data distribution. In response to this challenge, we explore the Pruned MIMIC-CXR-LT dataset, a curated collection derived from the MIMIC-CXR dataset, specifically designed to represent a long-tailed and multi-label data scenario. We introduce LTCXNet, a novel framework that integrates the ConvNeXt model, ML-Decoder, and strategic data augmentation, further enhanced by an ensemble approach. We demonstrate that LTCXNet improves the performance of CXR interpretation across all classes, especially enhancing detection in rarer classes like `Pneumoperitoneum' and `Pneumomediastinum' by 79\% and 48\%, respectively. Beyond performance metrics, our research extends into evaluating fairness, highlighting that some methods, while improving model accuracy, could inadvertently affect fairness across different demographic groups negatively. This work contributes to advancing the understanding and management of long-tailed, multi-label data distributions in medical imaging, paving the way for more equitable and effective diagnostic tools., Comment: 8 pages, 5 figures

We introduce a dataset of natural-language questions in the decision theory of so-called Newcomb-like problems. Newcomb-like problems include, for instance, decision problems in which an agent interacts with a similar other agent, and thus has to reason about the fact that the other agent will likely reason in similar ways. Evaluating LLM reasoning about Newcomb-like problems is important because interactions between foundation-model-based agents will often be Newcomb-like. Some ways of reasoning about Newcomb-like problems may allow for greater cooperation between models. Our dataset contains both capabilities questions (i.e., questions with a unique, uncontroversially correct answer) and attitude questions (i.e., questions about which decision theorists would disagree). We use our dataset for an investigation of decision-theoretical capabilities and expressed attitudes and their interplay in existing models (different models by OpenAI, Anthropic, Meta, GDM, Reka, etc.), as well as models under simple prompt-based interventions. We find, among other things, that attitudes vary significantly between existing models; that high capabilities are associated with attitudes more favorable toward so-called evidential decision theory; and that attitudes are consistent across different types of questions., Comment: 48 pages, 15 figures; code and data at https://github.com/casparoe/newcomblike_questions_dataset

We introduce Llama Guard 3 Vision, a multimodal LLM-based safeguard for human-AI conversations that involves image understanding: it can be used to safeguard content for both multimodal LLM inputs (prompt classification) and outputs (response classification). Unlike the previous text-only Llama Guard versions (Inan et al., 2023; Llama Team, 2024b,a), it is specifically designed to support image reasoning use cases and is optimized to detect harmful multimodal (text and image) prompts and text responses to these prompts. Llama Guard 3 Vision is fine-tuned on Llama 3.2-Vision and demonstrates strong performance on the internal benchmarks using the MLCommons taxonomy. We also test its robustness against adversarial attacks. We believe that Llama Guard 3 Vision serves as a good starting point to build more capable and robust content moderation tools for human-AI conversation with multimodal capabilities.

In recent years, machine learning (ML) based reconstruction has been widely investigated and employed in cardiac magnetic resonance (CMR) imaging. ML-based reconstructions can deliver clinically acceptable image quality under substantially accelerated scans. ML-based reconstruction, however, also requires substantial data and computational time to train the neural network, which is often optimized for a fixed acceleration rate or image contrast. In practice, imaging parameters are often tuned to best suit the diagnosis, which may differ from the training data. This can result in degraded image quality, and multiple trained networks are needed to fulfill the clinical demands. In this study, we propose a foundation model that uses adaptive unrolling, channel-shifting, and Pattern and Contrast-Prompt-UNet (PCP-UNet) to tackle the problem. In particular, the undersampled data goes through a different number of unrolled iterations according to its acceleration rate. Channel-shifting improves reconstructed data quality. The PCP-UNet is equipped with an image contrast and sampling pattern prompt. In vivo CMR experiments were performed using mixed combinations of image contrasts, acceleration rates, and (under)sampling patterns. The proposed foundation model has significantly improved image quality for a wide range of CMR protocols and outperforms the conventional ML-based method., Comment: For MICCAI CMRxRecon Challenge 2024 team CardiAxs

In large-scale content recommendation systems, retrieval serves as the initial stage in the pipeline, responsible for selecting thousands of candidate items from billions of options to pass on to ranking modules. Traditionally, the dominant retrieval method has been Embedding-Based Retrieval (EBR) using a Deep Neural Network (DNN) dual-tower structure. However, applying transformer in retrieval tasks has been the focus of recent research, though real-world industrial deployment still presents significant challenges. In this paper, we introduce KuaiFormer, a novel transformer-based retrieval framework deployed in a large-scale content recommendation system. KuaiFormer fundamentally redefines the retrieval process by shifting from conventional score estimation tasks (such as click-through rate estimate) to a transformer-driven Next Action Prediction paradigm. This shift enables more effective real-time interest acquisition and multi-interest extraction, significantly enhancing retrieval performance. KuaiFormer has been successfully integrated into Kuaishou App's short-video recommendation system since May 2024, serving over 400 million daily active users and resulting in a marked increase in average daily usage time of Kuaishou users. We provide insights into both the technical and business aspects of deploying transformer in large-scale recommendation systems, addressing practical challenges encountered during industrial implementation. Our findings offer valuable guidance for engineers and researchers aiming to leverage transformer models to optimize large-scale content recommendation systems.

Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-image models has become increasingly important. Current metrics focus on directly matching the input text with the generated image, but due to cross-modal information asymmetry, this leads to unreliable or incomplete assessment results. Motivated by this, we introduce the Image Regeneration task in this study to assess text-to-image models by tasking the T2I model with generating an image according to the reference image. We use GPT4V to bridge the gap between the reference image and the text input for the T2I model, allowing T2I models to understand image content. This evaluation process is simplified as comparisons between the generated image and the reference image are straightforward. Two regeneration datasets spanning content-diverse and style-diverse evaluation dataset are introduced to evaluate the leading diffusion models currently available. Additionally, we present ImageRepainter framework to enhance the quality of generated images by improving content comprehension via MLLM guided iterative generation and revision. Our comprehensive experiments have showcased the effectiveness of this framework in assessing the generative capabilities of models. By leveraging MLLM, we have demonstrated that a robust T2M can produce images more closely resembling the reference image.

Quantum machine learning (QML) is a rapidly growing field that combines quantum computing principles with traditional machine learning. It seeks to revolutionize machine learning by harnessing the unique capabilities of quantum mechanics and employs machine learning techniques to advance quantum computing research. This paper introduces quantum computing for the machine learning paradigm, where variational quantum circuits (VQC) are used to develop QML architectures on noisy intermediate-scale quantum (NISQ) devices. We discuss machine learning for the quantum computing paradigm, showcasing our recent theoretical and empirical findings. In particular, we delve into future directions for studying QML, exploring the potential industrial impacts of QML research., Comment: In submission

This article propose a whole-body impedance coordinative control framework for a wheel-legged humanoid robot to achieve adaptability on complex terrains while maintaining robot upper body stability. The framework contains a bi-level control strategy. The outer level is a variable damping impedance controller, which optimizes the damping parameters to ensure the stability of the upper body while holding an object. The inner level employs Whole-Body Control (WBC) optimization that integrates real-time terrain estimation based on wheel-foot position and force data. It generates motor torques while accounting for dynamic constraints, joint limits,friction cones, real-time terrain updates, and a model-free friction compensation strategy. The proposed whole-body coordinative control method has been tested on a recently developed quadruped humanoid robot. The results demonstrate that the proposed algorithm effectively controls the robot, maintaining upper body stability to successfully complete a water-carrying task while adapting to varying terrains.

While existing one-shot talking head generation models have achieved progress in coarse-grained emotion editing, there is still a lack of fine-grained emotion editing models with high interpretability. We argue that for an approach to be considered fine-grained, it needs to provide clear definitions and sufficiently detailed differentiation. We present LES-Talker, a novel one-shot talking head generation model with high interpretability, to achieve fine-grained emotion editing across emotion types, emotion levels, and facial units. We propose a Linear Emotion Space (LES) definition based on Facial Action Units to characterize emotion transformations as vector transformations. We design the Cross-Dimension Attention Net (CDAN) to deeply mine the correlation between LES representation and 3D model representation. Through mining multiple relationships across different feature and structure dimensions, we enable LES representation to guide the controllable deformation of 3D model. In order to adapt the multimodal data with deviations to the LES and enhance visual quality, we utilize specialized network design and training strategies. Experiments show that our method provides high visual quality along with multilevel and interpretable fine-grained emotion editing, outperforming mainstream methods.

We demonstrate atom-resolved detection of itinerant bosonic $^{23}$Na and fermionic $^6$Li quantum gases, enabling the direct in situ measurement of interparticle correlations. In contrast to prior work on lattice-trapped gases, here we realize microscopy of quantum gases in the continuum. We reveal Bose-Einstein condensation with single-atom resolution, measure the enhancement of two-particle $g^{(2)}$ correlations of thermal bosons, and observe the suppression of $g^{(2)}$ for fermions; the Fermi or exchange hole. For strongly interacting Fermi gases confined to two dimensions, we directly observe non-local fermion pairs in the BEC-BCS crossover. We obtain the pairing gap, the pair size, and the short-range contact directly from the pair correlations. In situ thermometry is enabled via the fluctuation-dissipation theorem. Our technique opens the door to the atom-resolved study of strongly correlated quantum gases of bosons, fermions, and their mixtures., Comment: 7 pages, 6 figures

Quantum Machine Learning (QML) offers tremendous potential but is currently limited by the availability of qubits. We introduce an innovative approach that utilizes pre-trained neural networks to enhance Variational Quantum Circuits (VQC). This technique effectively separates approximation error from qubit count and removes the need for restrictive conditions, making QML more viable for real-world applications. Our method significantly improves parameter optimization for VQC while delivering notable gains in representation and generalization capabilities, as evidenced by rigorous theoretical analysis and extensive empirical testing on quantum dot classification tasks. Moreover, our results extend to applications such as human genome analysis, demonstrating the broad applicability of our approach. By addressing the constraints of current quantum hardware, our work paves the way for a new era of advanced QML applications, unlocking the full potential of quantum computing in fields such as machine learning, materials science, medicine, mimetics, and various interdisciplinary areas., Comment: In submission

Interpretable Machine Learning faces a recurring challenge of explaining the predictions made by opaque classifiers such as ensemble models, kernel methods, or neural networks in terms that are understandable to humans. When the model is viewed as a black box, the objective is to identify a small set of features that jointly determine the black box response with minimal error. However, finding such model-agnostic explanations is computationally demanding, as the problem is intractable even for binary classifiers. In this paper, the task is framed as a Constraint Optimization Problem, where the constraint solver seeks an explanation of minimum error and bounded size for an input data instance and a set of samples generated by the black box. From a theoretical perspective, this constraint programming approach offers PAC-style guarantees for the output explanation. We evaluate the approach empirically on various datasets and show that it statistically outperforms the state-of-the-art heuristic Anchors method.

Accurate segmentation of retinal images plays a crucial role in aiding ophthalmologists in diagnosing retinopathy of prematurity (ROP) and assessing its severity. However, due to their underdeveloped, thinner vessels, manual annotation in infant fundus images is very complex, and this presents challenges for fully supervised learning. To address the scarcity of annotations, we propose a semi supervised segmentation framework designed to advance ROP studies without the need for extensive manual vessel annotation. Unlike previous methods that rely solely on limited labeled data, our approach leverages teacher student learning by integrating two powerful components: an uncertainty weighted vessel unveiling module and domain adversarial learning. The vessel unveiling module helps the model effectively reveal obscured and hard to detect vessel structures, while adversarial training aligns feature representations across different domains, ensuring robust and generalizable vessel segmentations. We validate our approach on public datasets (CHASEDB, STARE) and an in-house ROP dataset, demonstrating its superior performance across multiple evaluation metrics. Additionally, we extend the model's utility to a downstream task of ROP multi-stage classification, where vessel masks extracted by our segmentation model improve diagnostic accuracy. The promising results in classification underscore the model's potential for clinical application, particularly in early-stage ROP diagnosis and intervention. Overall, our work offers a scalable solution for leveraging unlabeled data in pediatric ophthalmology, opening new avenues for biomarker discovery and clinical research., Comment: 10 pages, 5 figures

Thanks to the explosive growth of data and the development of computational resources, it is possible to build pre-trained models that can achieve outstanding performance on various tasks, such as neural language processing, computer vision, and more. Despite their powerful capabilities, pre-trained models have also sparked attention to the emerging security challenges associated with their real-world applications. Security and privacy issues, such as leaking privacy information and generating harmful responses, have seriously undermined users' confidence in these powerful models. Concerns are growing as model performance improves dramatically. Researchers are eager to explore the unique security and privacy issues that have emerged, their distinguishing factors, and how to defend against them. However, the current literature lacks a clear taxonomy of emerging attacks and defenses for pre-trained models, which hinders a high-level and comprehensive understanding of these questions. To fill the gap, we conduct a systematical survey on the security risks of pre-trained models, proposing a taxonomy of attack and defense methods based on the accessibility of pre-trained models' input and weights in various security test scenarios. This taxonomy categorizes attacks and defenses into No-Change, Input-Change, and Model-Change approaches. With the taxonomy analysis, we capture the unique security and privacy issues of pre-trained models, categorizing and summarizing existing security issues based on their characteristics. In addition, we offer a timely and comprehensive review of each category's strengths and limitations. Our survey concludes by highlighting potential new research opportunities in the security and privacy of pre-trained models.

Hand-face interactions play a key role in many everyday tasks, providing insights into user habits, behaviors, intentions, and expressions. However, existing wearable sensing systems often struggle to track these interactions in daily settings due to their reliance on multiple sensors or privacy-sensitive, vision-based approaches. To address these challenges, we propose WristSonic, a wrist-worn active acoustic sensing system that uses speakers and microphones to capture ultrasonic reflections from hand, arm, and face movements, enabling fine-grained detection of hand-face interactions with minimal intrusion. By transmitting and analyzing ultrasonic waves, WristSonic distinguishes a wide range of gestures, such as tapping the temple, brushing teeth, and nodding, using a Transformer-based neural network architecture. This approach achieves robust recognition of 21 distinct actions with a single, low-power, privacy-conscious wearable. Through two user studies with 15 participants in controlled and semi-in-the-wild settings, WristSonic demonstrates high efficacy, achieving macro F1-scores of 93.08% and 82.65%, respectively., Comment: 21 Pages, 10 Figures, Under Review

In the many years since the inception of wearable sensor-based Human Activity Recognition (HAR), a wide variety of methods have been introduced and evaluated for their ability to recognize activities. Substantial gains have been made since the days of hand-crafting heuristics as features, yet, progress has seemingly stalled on many popular benchmarks, with performance falling short of what may be considered 'sufficient'-- despite the increase in computational power and scale of sensor data, as well as rising complexity in techniques being employed. The HAR community approaches a new paradigm shift, this time incorporating world knowledge from foundational models. In this paper, we take stock of sensor-based HAR -- surveying it from its beginnings to the current state of the field, and charting its future. This is accompanied by a hands-on tutorial, through which we guide practitioners in developing HAR systems for real-world application scenarios. We provide a compendium for novices and experts alike, of methods that aim at finally solving the activity recognition problem.

Mossinghoff, Trudgian, and the first author~\cite{MMT23} recently introduced a family of arithmetic functions called ``fake $\mu$'s'', which are multiplicative functions for which there is a $\{-1,0,1\}$-valued sequence $(\varepsilon_j)_{j=1}^{\infty}$ such that $f(p^j) = \varepsilon_j$ for all primes $p$. They investigated comparative number-theoretic results for fake $\mu$'s and in particular proved oscillation results at scale $\sqrt{x}$ for the summatory functions of fake $\mu$'s with $\varepsilon_1=-1$ and $\varepsilon_2=1$. In this paper, we establish new oscillation results for the summatory functions of all nontrivial fake $\mu$'s at scales $x^{1/2\ell}$ where $\ell$ is a positive integer (the ``critical index'') depending on $f$; for $\ell=1$ this recovers the oscillation results in~\cite{MMT23}. Our work also recovers results on the indicator functions of powerfree and powerfull numbers; we generalize techniques applied to each of these examples to extend to all fake $\mu$'s., Comment: 39 pages

Query-focused summarization (QFS) is the task of generating a summary in response to a user-written query. Despite its user-oriented nature, there has been limited work in QFS in explicitly considering a user's understanding of a generated summary, potentially causing QFS systems to underperform at inference time. In this paper, we adapt the Rational Speech Act (RSA) framework, a model of human communication, to explicitly model a reader's understanding of a query-focused summary and integrate it within the generation method of existing QFS systems. In particular, we introduce the answer reconstruction objective which approximates a reader's understanding of a summary by their ability to use it to reconstruct the answer to their initial query. Using this objective, we are able to re-rank candidate summaries generated by existing QFS systems and select summaries that better align with their corresponding query and reference summary. More generally, our study suggests that a simple and effective way of improving a language generation system designed for a user-centered task may be to explicitly incorporate its user requirements into the system's generation procedure.

The Psycho Frame, a sophisticated system primarily used in Universal Century (U.C.) series mobile suits for NEWTYPE pilots, has evolved as an integral component in harnessing the latent potential of mental energy. Its ability to amplify and resonate with the pilot's psyche enables real-time mental control, creating unique applications such as psychomagnetic fields and sensory-based weaponry. This paper presents the development of a novel robotic control system inspired by the Psycho Frame, combining electroencephalography (EEG) and deep learning for real-time control of robotic systems. By capturing and interpreting brainwave data through EEG, the system extends human cognitive commands to robotic actions, reflecting the seamless synchronization of thought and machine, much like the Psyco Frame's integration with a Newtype pilot's mental faculties. This research demonstrates how modern AI techniques can expand the limits of human-machine interaction, potentially transcending traditional input methods and enabling a deeper, more intuitive control of complex robotic systems.

We investigate the return-forecasting and volatility-forecasting power of intraday on-chain flow data for BTC, ETH, and USDT, and the associated option strategies. First, we find that USDT net inflow into cryptocurrency exchanges positively forecasts future returns of both BTC and ETH, with the strongest effect at the 1-hour frequency. Second, we find that ETH net inflow into cryptocurrency exchanges negatively forecasts future returns of ETH. Third, we find that BTC net inflow into cryptocurrency exchanges does not significantly forecast future returns of BTC. Finally, we confirm that selling 0DTE ETH call options is a profitable trading strategy when the net inflow into cryptocurrency exchanges is high. Our study lends new insights into the emerging literature that studies the on-chain activities and their asset-pricing impact in the cryptocurrency market.

We assess the difficulty of gender resolution in literary-style dialogue settings and the influence of gender stereotypes. Instances of the test suite contain spoken dialogue interleaved with external meta-context about the characters and the manner of speaking. We find that character and manner stereotypes outside of the dialogue significantly impact the gender agreement of referents within the dialogue.

Artificial intelligence generated content (AIGC) technologies, with a predominance of large language models (LLMs), have demonstrated remarkable performance improvements in various applications, which have attracted great interests from both academia and industry. Although some noteworthy advancements have been made in this area, a comprehensive exploration of the intricate relationship between AIGC and communication networks remains relatively limited. To address this issue, this paper conducts an exhaustive survey from dual standpoints: firstly, it scrutinizes the integration of LLMs and AIGC technologies within the domain of communication networks; secondly, it investigates how the communication networks can further bolster the capabilities of LLMs and AIGC. Additionally, this research explores the promising applications along with the challenges encountered during the incorporation of these AI technologies into communication networks. Through these detailed analyses, our work aims to deepen the understanding of how LLMs and AIGC can synergize with and enhance the development of advanced intelligent communication networks, contributing to a more profound comprehension of next-generation intelligent communication networks., Comment: Accepted by IEEE Internet of Things Journal

In the field of non-invasive medical imaging, radiomic features are utilized to measure tumor characteristics. However, these features can be affected by the techniques used to discretize the images, ultimately impacting the accuracy of diagnosis. To investigate the influence of various image discretization methods on diagnosis, it is common practice to evaluate multiple discretization strategies individually. This approach often leads to redundant and time-consuming tasks such as training predictive models and fine-tuning hyperparameters separately. This study examines the feasibility of employing multi-task Bayesian optimization to accelerate the hyperparameters search for classifying benign and malignant pulmonary nodules using RBF SVM. Our findings suggest that multi-task Bayesian optimization significantly accelerates the search for hyperparameters in comparison to a single-task approach. To the best of our knowledge, this is the first investigation to utilize multi-task Bayesian optimization in a critical medical context., Comment: 12 pages, 4 figures, 37 references

Game solving is the process of finding the theoretical outcome for a game, assuming that all player choices are optimal. This paper focuses on a technique that can reduce the heuristic search space significantly for 7x7 Killall-Go. In Go and Killall-Go, live patterns are stones that are protected from opponent capture. Mutual life, also referred to as seki, is when both players' stones achieve life by sharing liberties with their opponent. Whichever player attempts to capture the opponent first will leave their own stones vulnerable. Therefore, it is critical to recognize seki patterns to avoid putting oneself in jeopardy. Recognizing seki can reduce the search depth significantly. In this paper, we enumerate all seki patterns up to a predetermined area size, then store these patterns into a seki table. This allows us to recognize seki during search, which significantly improves solving efficiency for the game of Killall-Go. Experiments show that a day-long, unsolvable position can be solved in 482 seconds with the addition of a seki table. For general positions, a 10% to 20% improvement in wall clock time and node count is observed., Comment: Accepted by the Computers and Games conference (CG 2024)

In the United States, skin cancer ranks as the most commonly diagnosed cancer, presenting a significant public health issue due to its high rates of occurrence and the risk of serious complications if not caught early. Recent advancements in dataset curation and deep learning have shown promise in quick and accurate detection of skin cancer. However, current open-source datasets have significant class imbalances which impedes the effectiveness of these deep learning models. In healthcare, generative artificial intelligence (AI) models have been employed to create synthetic data, addressing data imbalance in datasets by augmenting underrepresented classes and enhancing the overall quality and performance of machine learning models. In this paper, we build on top of previous work by leveraging new advancements in generative AI, notably Stable Diffusion and DreamBooth. We introduce Cancer-Net SCa-Synth, an open access synthetically generated 2D skin lesion dataset for skin cancer classification. Further analysis on the data effectiveness by comparing the ISIC 2020 test set performance for training with and without these synthetic images for a simple model highlights the benefits of leveraging synthetic data to improve performance. Cancer-Net SCa-Synth is publicly available at https://github.com/catai9/Cancer-Net-SCa-Synth as part of a global open-source initiative for accelerating machine learning for cancer care.

Secure multiparty computation enables collaborative computations across multiple users while preserving individual privacy, which has a wide range of applications in finance, machine learning and healthcare. Secure multiparty computation can be realized using oblivious transfer as a primitive function. In this paper, we present an experimental implementation of a quantum-secure quantum oblivious transfer (QOT) protocol using an adapted quantum key distribution system combined with a bit commitment scheme, surpassing previous approaches only secure in the noisy storage model. We demonstrate the first practical application of the QOT protocol by solving the private set intersection, a prime example of secure multiparty computation, where two parties aim to find common elements in their datasets without revealing any other information. In our experiments, two banks can identify common suspicious accounts without disclosing any other data. This not only proves the experimental functionality of QOT, but also showcases its real-world commercial applications.

Promises made by politicians, corporate leaders, and public figures have a significant impact on public perception, trust, and institutional reputation. However, the complexity and volume of such commitments, coupled with difficulties in verifying their fulfillment, necessitate innovative methods for assessing their credibility. This paper introduces the concept of Promise Verification, a systematic approach involving steps such as promise identification, evidence assessment, and the evaluation of timing for verification. We propose the first multilingual dataset, ML-Promise, which includes English, French, Chinese, Japanese, and Korean, aimed at facilitating in-depth verification of promises, particularly in the context of Environmental, Social, and Governance (ESG) reports. Given the growing emphasis on corporate environmental contributions, this dataset addresses the challenge of evaluating corporate promises, especially in light of practices like greenwashing. Our findings also explore textual and image-based baselines, with promising results from retrieval-augmented generation (RAG) approaches. This work aims to foster further discourse on the accountability of public commitments across multiple languages and domains., Comment: 6 pages

In the United States, prostate cancer is the second leading cause of deaths in males with a predicted 35,250 deaths in 2024. However, most diagnoses are non-lethal and deemed clinically insignificant which means that the patient will likely not be impacted by the cancer over their lifetime. As a result, numerous research studies have explored the accuracy of predicting clinical significance of prostate cancer based on magnetic resonance imaging (MRI) modalities and deep neural networks. Despite their high performance, these models are not trusted by most clinical scientists as they are trained solely on a single modality whereas clinical scientists often use multiple magnetic resonance imaging modalities during their diagnosis. In this paper, we investigate combining multiple MRI modalities to train a deep learning model to enhance trust in the models for clinically significant prostate cancer prediction. The promising performance and proposed training pipeline showcase the benefits of incorporating multiple MRI modalities for enhanced trust and accuracy., Comment: Findings paper presented at Machine Learning for Health (ML4H) symposium 2024, December 15-16, 2024, Vancouver, Canada, 6 pages

The FCC-ee offers the potential to measure the electron Yukawa coupling via direct s-channel Higgs production, e+ e- -> H, at a centre-of-mass (CM) energy of 125 GeV. This measurement is significantly facilitated if the CM energy spread of e+ e- collisions can be reduced to a level comparable to the natural width of the Higgs boson, {\Gamma}_H = 4.1 MeV, without substantial loss in luminosity. Achieving this reduction in collision-energy spread is possible through the "monochromatization" concept. The basic idea is to create opposite correlations between spatial position and energy deviation within the colliding beams, which can be accomplished in beam optics by introducing a nonzero dispersion function with opposite signs for the two beams at the interaction point. Since the first proposal in 2016, the implementation of monochromatization at the FCC-ee has been continuously improved, starting from preliminary parametric studies. In this paper, we present a detailed study of the interaction region optics design for this newly proposed collision mode, exploring different potential configurations and their implementation in the FCC-ee global lattice, along with beam dynamics simulations and performance evaluations including the impact of "beamstrahlung."

The rapid development of Multimodal Large Language Models (MLLMs) has expanded their capabilities from image comprehension to video understanding. However, most of these MLLMs focus primarily on offline video comprehension, necessitating extensive processing of all video frames before any queries can be made. This presents a significant gap compared to the human ability to watch, listen, think, and respond to streaming inputs in real time, highlighting the limitations of current MLLMs. In this paper, we introduce StreamingBench, the first comprehensive benchmark designed to evaluate the streaming video understanding capabilities of MLLMs. StreamingBench assesses three core aspects of streaming video understanding: (1) real-time visual understanding, (2) omni-source understanding, and (3) contextual understanding. The benchmark consists of 18 tasks, featuring 900 videos and 4,500 human-curated QA pairs. Each video features five questions presented at different time points to simulate a continuous streaming scenario. We conduct experiments on StreamingBench with 13 open-source and proprietary MLLMs and find that even the most advanced proprietary MLLMs like Gemini 1.5 Pro and GPT-4o perform significantly below human-level streaming video understanding capabilities. We hope our work can facilitate further advancements for MLLMs, empowering them to approach human-level video comprehension and interaction in more realistic scenarios.

We study the problem of estimating the body movements of a camera wearer from egocentric videos. Current methods for ego-body pose estimation rely on temporally dense sensor data, such as IMU measurements from spatially sparse body parts like the head and hands. However, we propose that even temporally sparse observations, such as hand poses captured intermittently from egocentric videos during natural or periodic hand movements, can effectively constrain overall body motion. Naively applying diffusion models to generate full-body pose from head pose and sparse hand pose leads to suboptimal results. To overcome this, we develop a two-stage approach that decomposes the problem into temporal completion and spatial completion. First, our method employs masked autoencoders to impute hand trajectories by leveraging the spatiotemporal correlations between the head pose sequence and intermittent hand poses, providing uncertainty estimates. Subsequently, we employ conditional diffusion models to generate plausible full-body motions based on these temporally dense trajectories of the head and hands, guided by the uncertainty estimates from the imputation. The effectiveness of our method was rigorously tested and validated through comprehensive experiments conducted on various HMD setup with AMASS and Ego-Exo4D datasets., Comment: Accepted at NeurIPS 2024

Detecting mitigating and correcting errors in quantum control is among the most pertinent contemporary problems in quantum technologies. We consider three of the most common bosonic error correction codes -- the CLY, binomial and dual rail and compare their performance under typical errors in bosonic systems. We find that the dual rail code shows the best performance. We also develop a new technique for error mitigation in quantum control. We consider a quantum system with large Hilbert space dimension, e.g., a qudit or a multi-qubit system and construct two $2- $ dimensional subspaces -- a code space, $\mathcal C = \text{span}\{|\bar{0}\rangle, |\bar{1}\rangle\}$ where the logical qubit is encoded and a ``proxy'' space $\mathcal P = \text{span}\{|\bar{0}'\rangle, |\bar{1}'\rangle\}$. While the qubit (i.e., $\mathcal C$) can be a part of a quantum circuit, the proxy (i.e., $\mathcal P$) remains idle. In the absence of errors, the quantum state of the proxy qubit does not evolve in time. If $\mathcal E$ is an error channel acting on the full system, we consider its projections on $\mathcal C$ and $\mathcal P$ represented as pauli transfer matrices $T_{\mathcal E}$ and $T'_{\mathcal E}$ respectively. Under reasonable assumptions regarding the origin of the errors, $T_{\mathcal E}$ can be inferred from $T'_{\mathcal E}$ acting on the proxy qubit and the latter can be measured without affecting the qubit. The latter can be measured while the qubit is a part of a quantum circuit because, one can perform simultaneous measurements on the logical and the proxy qubits. We use numerical data to learn an \textit{affine map} $\phi$ such that $T_{\mathcal E} \approx \phi(T'_{\mathcal E})$. We also show that the inversion of a suitable proxy space's logical pauli transfer matrix can effectively mitigate the noise on the two modes bosonic system or two qudits system., Comment: 7+4 pages, 4+2 figures

Precision therapy for liver cancer necessitates accurately delineating liver sub-regions to protect healthy tissue while targeting tumors, which is essential for reducing recurrence and improving survival rates. However, the segmentation of hepatic segments, known as Couinaud segmentation, is challenging due to indistinct sub-region boundaries and the need for extensive annotated datasets. This study introduces LiverFormer, a novel Couinaud segmentation model that effectively integrates global context with low-level local features based on a 3D hybrid CNN-Transformer architecture. Additionally, a registration-based data augmentation strategy is equipped to enhance the segmentation performance with limited labeled data. Evaluated on CT images from 123 patients, LiverFormer demonstrated high accuracy and strong concordance with expert annotations across various metrics, allowing for enhanced treatment planning for surgery and radiation therapy. It has great potential to reduces complications and minimizes potential damages to surrounding tissue, leading to improved outcomes for patients undergoing complex liver cancer treatments.

Implementing and tuning chirality is fundamental in physics, chemistry, and material science. Chiral charge density waves (CDWs), where chirality arises from correlated charge orders, are attracting intense interest due to their exotic transport and optical properties. However, a general framework for predicting chiral CDW materials is lacking, primarily because the underlying mechanisms remain elusive. Here, we address this challenge by developing the first comprehensive predictive framework, systematically identifying chiral CDW materials via first-principles calculations. The key lies in the previously overlooked phase difference of the CDW Q-vectors between layers, which is linked to opposite collective atomic displacements across different layers. This phase difference induces a spiral arrangement of the Q-vectors, ultimately giving rise to a chiral structure in real space. We validate our framework by applying it to the kagome lattice AV$_{3}$Sb$_{5}$ (A = K, Rb, Cs), successfully predicting emergent structural chirality. To demonstrate the generality of our approach, we extend it to predict chiral CDWs in the triangular-lattice NbSe$_{2}$. Beyond material predictions, our theory uncovers a universal and unprecedented Hall effect in chiral CDW materials, occurring without external magnetic fields or intrinsic magnetization. Our experiments on CsV$_{3}$Sb$_{5}$ confirm this prediction, observing a unique signature where the Hall conductivity's sign reverses when the input current is reversed, a phenomenon distinct from known Hall effects. Our findings elucidate the mechanisms behind chiral CDWs and open new avenues for discovering materials with unconventional quantum properties, with potential applications in next-generation electronic and spintronic devices.

A central challenge in quantum simulation is to prepare low-energy states of strongly interacting many-body systems. In this work, we study the problem of preparing a quantum state that optimizes a random all-to-all, sparse or dense, spin or fermionic $k$-local Hamiltonian. We prove that a simplified quantum Gibbs sampling algorithm achieves a $\Omega(\frac{1}{k})$-fraction approximation of the optimum, giving an exponential improvement on the $k$-dependence over the prior best (both classical and quantum) algorithmic guarantees. Combined with the circuit lower bound for such states, our results suggest that finding low-energy states for sparsified (quasi)local spin and fermionic models is quantumly easy but classically nontrivial. This further indicates that quantum Gibbs sampling may be a suitable metaheuristic for optimization problems., Comment: 51 pages