Search

Jaccard Similarity is a very common proximity measurement used to compute the similarity between two asymmetric binary vectors. Jaccard Similarity is the ratio between the 1s (Intersection of two vectors) to 1s (Union of two vectors). This paper introduces a quantum algorithm for finding the Jaccard Similarity 1s, in the Intersection and Union of two binary vectors. There are two sub-algorithms one for each. Measuring the register for respective algorithm gives count of number of 1 s in binary format. Implementation on IBM composer is also included.

Medical foundation models are gaining prominence in the medical community for their ability to derive general representations from extensive collections of medical image-text pairs. Recent research indicates that these models are susceptible to backdoor attacks, which allow them to classify clean images accurately but fail when specific triggers are introduced. However, traditional backdoor attacks necessitate a considerable amount of additional data to maliciously pre-train a model. This requirement is often impractical in medical imaging applications due to the usual scarcity of data. Inspired by the latest developments in learnable prompts, this work introduces a method to embed a backdoor into the medical foundation model during the prompt learning phase. By incorporating learnable prompts within the text encoder and introducing imperceptible learnable noise trigger to the input images, we exploit the full capabilities of the medical foundation models (Med-FM). Our method, BAPLe, requires only a minimal subset of data to adjust the noise trigger and the text prompts for downstream tasks, enabling the creation of an effective backdoor attack. Through extensive experiments with four medical foundation models, each pre-trained on different modalities and evaluated across six downstream datasets, we demonstrate the efficacy of our approach. BAPLe achieves a high backdoor success rate across all models and datasets, outperforming the baseline backdoor attack methods. Our work highlights the vulnerability of Med-FMs towards backdoor attacks and strives to promote the safe adoption of Med-FMs before their deployment in real-world applications. Code is available at https://asif-hanif.github.io/baple/., Comment: MICCAI 2024

Retrieval Augmented Generation or RAG is the most popular pattern for modern Large Language Model or LLM applications. RAG involves taking a user query and finding relevant paragraphs of context in a large corpus typically captured in a vector database. Once the first level of search happens over a vector database, the top n chunks of relevant text are included directly in the context and sent as prompt to the LLM. Problem with this approach is that quality of text chunks depends on effectiveness of search. There is no strong post processing after search to determine if the chunk does hold enough information to include in prompt. Also many times there may be chunks that have conflicting information on the same subject and the model has no prior experience which chunk to prioritize to make a decision. Often times, this leads to the model providing a statement that there are conflicting statements, and it cannot produce an answer. In this research we propose a Bayesian approach to verify the quality of text chunks from the search results. Bayes theorem tries to relate conditional probabilities of the hypothesis with evidence and prior probabilities. We propose that, finding likelihood of text chunks to give a quality answer and using prior probability of quality of text chunks can help us improve overall quality of the responses from RAG systems. We can use the LLM itself to get a likelihood of relevance of a context paragraph. For prior probability of the text chunk, we use the page number in the documents parsed. Assumption is that that paragraphs in earlier pages have a better probability of being findings and more relevant to generalizing an answer.

An ever-widening workforce gap exists in the global cybersecurity industry but diverse talent is underutilized. The global cybersecurity workforce is only 25% female. Much research exists on the effect of gender bias on the hiring of women into the technical workforce, but little on how the gender of the recruiter (gender difference) affects recruitment decisions. This research reveals differences between the non-technical skills sought by female vs non-female cybersecurity recruiters. The former look for recruits with people-focused skills while the latter look for task-focused skills, highlighting the need for gender diversity in recruitment panels. Recruiters are increasingly seeking non-technical (soft) skills in technical graduate recruits. This requires STEM curriculum in Universities to adapt to match. Designing an industry-ready cybersecurity curriculum requires knowledge of these non-technical skills. An online survey of cybersecurity professionals was used to determine the most sought after non-technical skills in the field. Analysis of the data reveals distinct gender differences in the non-technical skills most valued in a recruit, based on the gender of the recruiter (not the recruited). The gender differences discovered do not correspond to the higher proportion of women employed in non-technical cybersecurity roles., Comment: 22 pages, 4 figures

Recently, machine learning techniques, particularly deep learning, have demonstrated superior performance over traditional time series forecasting methods across various applications, including both single-variable and multi-variable predictions. This study aims to investigate the capability of i) Next Generation Reservoir Computing (NG-RC) ii) Reservoir Computing (RC) iii) Long short-term Memory (LSTM) for predicting chaotic system behavior, and to compare their performance in terms of accuracy, efficiency, and robustness. These methods are applied to predict time series obtained from four representative chaotic systems including Lorenz, R\"ossler, Chen, Qi systems. In conclusion, we found that NG-RC is more computationally efficient and offers greater potential for predicting chaotic system behavior., Comment: 8 pages, 15 figures

Zero-shot image recognition (ZSIR) aims at empowering models to recognize and reason in unseen domains via learning generalized knowledge from limited data in the seen domain. The gist for ZSIR is to execute element-wise representation and reasoning from the input visual space to the target semantic space, which is a bottom-up modeling paradigm inspired by the process by which humans observe the world, i.e., capturing new concepts by learning and combining the basic components or shared characteristics. In recent years, element-wise learning techniques have seen significant progress in ZSIR as well as widespread application. However, to the best of our knowledge, there remains a lack of a systematic overview of this topic. To enrich the literature and provide a sound basis for its future development, this paper presents a broad review of recent advances in element-wise ZSIR. Concretely, we first attempt to integrate the three basic ZSIR tasks of object recognition, compositional recognition, and foundation model-based open-world recognition into a unified element-wise perspective and provide a detailed taxonomy and analysis of the main research approaches. Then, we collect and summarize some key information and benchmarks, such as detailed technical implementations and common datasets. Finally, we sketch out the wide range of its related applications, discuss vital challenges, and suggest potential future directions., Comment: 23 pages, 7 figures, and 3 tables

Extraction and interpretation of intricate information from unstructured text data arising in financial applications, such as earnings call transcripts, present substantial challenges to large language models (LLMs) even using the current best practices to use Retrieval Augmented Generation (RAG) (referred to as VectorRAG techniques which utilize vector databases for information retrieval) due to challenges such as domain specific terminology and complex formats of the documents. We introduce a novel approach based on a combination, called HybridRAG, of the Knowledge Graphs (KGs) based RAG techniques (called GraphRAG) and VectorRAG techniques to enhance question-answer (Q&A) systems for information extraction from financial documents that is shown to be capable of generating accurate and contextually relevant answers. Using experiments on a set of financial earning call transcripts documents which come in the form of Q&A format, and hence provide a natural set of pairs of ground-truth Q&As, we show that HybridRAG which retrieves context from both vector database and KG outperforms both traditional VectorRAG and GraphRAG individually when evaluated at both the retrieval and generation stages in terms of retrieval accuracy and answer generation. The proposed technique has applications beyond the financial domain, Comment: 9 pages, 2 figures, 5 tables

Multilingual speaker verification introduces the challenge of verifying a speaker in multiple languages. Existing systems were built using i-vector/x-vector approaches along with Bi-LSTMs, which were trained to discriminate speakers, irrespective of the language. Instead of exploring the design space manually, we propose a neural architecture search for multilingual speaker verification suitable for mobile devices, called \textbf{NeuralMultiling}. First, our algorithm searches for an optimal operational combination of neural cells with different architectures for normal cells and reduction cells and then derives a CNN model by stacking neural cells. Using the derived architecture, we performed two different studies:1) language agnostic condition and 2) interoperability between languages and devices on the publicly available Multilingual Audio-Visual Smartphone (MAVS) dataset. The experimental results suggest that the derived architecture significantly outperforms the existing Autospeech method by a 5-6\% reduction in the Equal Error Rate (EER) with fewer model parameters.

An optimal guidance method is developed that reduces sensitivity to parameters in the dynamic model. The method combines a previously developed method for guidance and control using adaptive Legendre-Gauss-Radau (LGR) collocation and a previously developed approach for desensitized optimal control. Guidance updates are performed such that the desensitized optimal control problem is re-solved on the remaining horizon at the start of each guidance cycle. The effectiveness of the method is demonstrated on a simple example using Monte Carlo simulation. It is found that the method reduces variations in the terminal state as compared to either desensitized optimal control without guidance updates or a previously developed method for optimal guidance and control., Comment: 12 pages, 4 figures

Touchscreen-based interaction on display devices are ubiquitous nowadays. However, capacitive touch screens, the core technology that enables its widespread use, are prohibitively expensive to be used in large displays because the cost increases proportionally with the screen area. In this paper, we propose a millimeter wave (mmWave) radar-based solution to achieve subresolution error performance using a network of four mmWave radar sensors. Unfortunately, achieving this is non-trivial due to inherent range resolution limitations of mmWave radars, since the target (human hand, finger etc.) is 'distributed' in space. We overcome this using a deep learning-based approach, wherein we train a deep convolutional neural network (CNN) on range-FFT (range vs power profile)-based features against ground truth (GT) positions obtained using a capacitive touch screen. To emulate the clutter characteristics encountered in radar-based positioning of human fingers, we use a metallic finger mounted on a metallic robot arm as the target. Using this setup, we demonstrate subresolution position error performance. Compared to conventional signal processing (CSP)-based approaches, we achieve a 2-3x reduction in positioning error using the CNN. Furthermore, we observe that the inference time performance and CNN model size support real-time integration of our approach on general purpose processor-based computing platforms., Comment: 7 pages, 9 figures and 2 tables. To appear in the 100th Vehicular Technology Conference (VTC-Fall 2024)

Transformers have revolutionized deep learning and generative modeling to enable unprecedented advancements in natural language processing tasks and beyond. However, designing hardware accelerators for executing transformer models is challenging due to the wide variety of computing kernels involved in the transformer architecture. Existing accelerators are either inadequate to accelerate end-to-end transformer models or suffer notable thermal limitations. In this paper, we propose the design of a three-dimensional heterogeneous architecture referred to as HeTraX specifically optimized to accelerate end-to-end transformer models. HeTraX employs hardware resources aligned with the computational kernels of transformers and optimizes both performance and energy. Experimental results show that HeTraX outperforms existing state-of-the-art by up to 5.6x in speedup and improves EDP by 14.5x while ensuring thermally feasibility., Comment: Presented at ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED-24)

In this article, we describe an algorithm for solving Quadratic Unconstrained Binary Optimization problems on the Intel Loihi 2 neuromorphic processor. The solver is based on a hardware-aware fine-grained parallel simulated annealing algorithm developed for Intel's neuromorphic research chip Loihi 2. Preliminary results show that our approach can generate feasible solutions in as little as 1 ms and up to 37x more energy efficient compared to two baseline solvers running on a CPU. These advantages could be especially relevant for size-, weight-, and power-constrained edge computing applications., Comment: 12 pages, 3 figures. Shared first authorship: Alessandro Pierro, Philipp Stratmann, and Gabriel Andres Fonseca Guerra

We derive the transport equations from the Vlasov-Fokker-Planck equation when the velocity space is spherically symmetric. The Shkarofsky's form of Fokker-Planck-Rosenbluth collision operator is employed in the Vlasov-Fokker-Planck equation. A closed-form relaxation model for homogeneous plasmas could be presented in terms of Gauss hypergeometric2F1 functions. This has been accomplished based on the Maxwellian mixture model. Furthermore, we demonstrate that classic models such as two-temperature thermal equilibrium model and thermodynamic equilibrium model are special cases of our relaxation model and the zeroth-order Braginskii heat transfer model can also be derived. The present relaxation model is a nonequilibrium model based on the hypothesis that the plasmas system possesses finitely distinguishable independent features, without relying on the conventional near-equilibrium assumption., Comment: 15 pages, 1 figure

Multimodal language models (MLLMs) are increasingly being implemented in real-world environments, necessitating their ability to interpret 3D spaces and comprehend temporal dynamics. Despite their potential, current top models within our community still fall short in adequately understanding spatial and temporal dimensions. We introduce Coarse Correspondence, a simple, training-free, effective, and general-purpose visual prompting method to elicit 3D and temporal understanding in multimodal LLMs. Our method uses a lightweight tracking model to find object correspondences between frames in a video or between sets of image viewpoints. It selects the most frequent object instances and visualizes them with markers with unique IDs in the image. With this simple approach, we achieve state-of-the-art results on 3D understanding benchmarks including ScanQA (+20.5\%) and a subset of OpenEQA (+9.7\%), and on long-form video benchmarks such as EgoSchema (+6.0\%). We also curate a small diagnostic dataset to evaluate whether MLLMs can reason about space from a described viewpoint other than the camera viewpoint. Again, Coarse Correspondence improves spatial perspective-taking abilities but we highlight that MLLMs struggle with this task. Together, we demonstrate that our simple prompting method can significantly aid downstream tasks that require 3D or temporal reasoning., Comment: project page: https://coarse-correspondence.github.io

In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters. In this new version, we apply several known technical modifications to the Transformer architecture, such as interleaving local-global attentions (Beltagy et al., 2020a) and group-query attention (Ainslie et al., 2023). We also train the 2B and 9B models with knowledge distillation (Hinton et al., 2015) instead of next token prediction. The resulting models deliver the best performance for their size, and even offer competitive alternatives to models that are 2-3 times bigger. We release all our models to the community.

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

Elastic collisions of solitons generally have a finite phase shift. When the phase shift has a finitely large value, the two vertices of the (2+1)-dimensional 2-soliton are significantly separated due to the phase shift, accompanied by the formation of a local structure connecting the two V-shaped solitons. We define this local structure as the stem structure. This study systematically investigates the localized stem structures between two solitons in the (2+1)-dimensional asymmetric Nizhnik-Novikov-Veselov system. These stem structures, arising from quasi-resonant collisions between the solitons, exhibit distinct features of spatial locality and temporal invariance. We explore two scenarios: one characterized by weakly quasi-resonant collisions (i.e. $a_{12}\approx 0$), and the other by strongly quasi-resonant collisions (i.e. $a_{12}\approx +\infty$). Through mathematical analysis, we extract comprehensive insights into the trajectories, amplitudes, and velocities of the soliton arms. Furthermore, we discuss the characteristics of the stem structures, including their length and extreme points. Our findings shed new light on the interaction between solitons in the (2+1)-dimensional asymmetric Nizhnik-Novikov-Veselov system., Comment: 14 pages, 6 figures;Accepted by journal of mathematical physics(July, 2024)

CultureVo, Inc. has developed the Integrated Culture Learning Suite (ICLS) to deliver foundational knowledge of world cultures through a combination of interactive lessons and gamified experiences. This paper explores how Generative AI powered by open source Large Langauge Models are utilized within the ICLS to enhance cultural intelligence. The suite employs Generative AI techniques to automate the assessment of learner knowledge, analyze behavioral patterns, and manage interactions with non-player characters using real time learner assessment. Additionally, ICLS provides contextual hint and recommend course content by assessing learner proficiency, while Generative AI facilitates the automated creation and validation of educational content., Comment: Fourth International Conference on AI-ML Systems, 8-11 October, 2024, Louisiana, USA

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute. These models are designed to perform a wide range of tasks efficiently, accurately, and responsibly. This report describes the model architecture, the data used to train the model, the training process, how the models are optimized for inference, and the evaluation results. We highlight our focus on Responsible AI and how the principles are applied throughout the model development.

We study approval-based committee voting in which a target number of candidates are selected based on voters' approval preferences over candidates. In contrast to most of the work, we consider the setting where voters express uncertain approval preferences and explore four different types of uncertain approval preference models. For each model, we study the problems such as computing a committee with the highest probability of satisfying axioms such as justified representation.

In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of their key-value (KV) caches. Conventional cache management strategies for LLMs focus on cache eviction, which often fails to address the specific needs of multimodal instruction-following models. Recognizing this gap, in this paper, we introduce Elastic Cache, a novel approach that benefits from applying distinct acceleration methods for instruction encoding and output generation stages. We investigate the metrics of importance in different stages and propose an importance-driven cache merging strategy to prune redundancy caches. Instead of discarding less important caches, our strategy identifies important key/value vectors as anchor points. Surrounding less important caches are then merged with these anchors, enhancing the preservation of contextual information in the KV caches while yielding an arbitrary acceleration ratio. For instruction encoding, we utilize the frequency to evaluate the importance of caches. Regarding output generation, we prioritize tokens based on their distance with an offset, by which both the initial and most recent tokens are retained. Results on a range of LVLMs demonstrate that Elastic Cache not only boosts efficiency but also notably outperforms existing pruning methods in language generation across various tasks. Code is available at https://github.com/liuzuyan/ElasticCache, Comment: Accepted to ECCV 2024

With the advancement of artificial intelligence technology, the automation of network management, also known as Autonomous Driving Networks (ADN), is gaining widespread attention. The network management has shifted from traditional homogeneity and centralization to heterogeneity and decentralization. Multi-agent deep reinforcement learning (MADRL) allows agents to make decisions based on local observations independently. This approach is in line with the needs of automation and has garnered significant attention from academia and industry. In a distributed environment, information interaction between agents can effectively address the non-stationarity problem of multiple agents and promote cooperation. Therefore, in this survey, we first examined the application of MADRL in network management, including specific application fields such as traffic engineering, wireless network access, power control, and network security. Then, we conducted a detailed analysis of communication behavior between agents, including communication schemes, communication content construction, communication object selection, message processing, and communication constraints. Finally, we discussed the open issues and future research directions of agent communication in MADRL for future network management and ADN applications.

We define the modulo-$m$ Toeplitz fixed point generated by Toeplitz substitution and study the lattice subsequence of such fixed point. Moreover, we provide a method to check whether one modulo-$m$ Toeplitz fixed point is a lattice subsequence of another.

Concept Bottleneck Models (CBMs) have recently been proposed to address the 'black-box' problem of deep neural networks, by first mapping images to a human-understandable concept space and then linearly combining concepts for classification. Such models typically require first coming up with a set of concepts relevant to the task and then aligning the representations of a feature extractor to map to these concepts. However, even with powerful foundational feature extractors like CLIP, there are no guarantees that the specified concepts are detectable. In this work, we leverage recent advances in mechanistic interpretability and propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm: instead of pre-selecting concepts based on the downstream classification task, we use sparse autoencoders to first discover concepts learnt by the model, and then name them and train linear probes for classification. Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model. We perform a comprehensive evaluation across multiple datasets and CLIP architectures and show that our method yields semantically meaningful concepts, assigns appropriate names to them that make them easy to interpret, and yields performant and interpretable CBMs. Code available at https://github.com/neuroexplicit-saar/discover-then-name., Comment: 40 pages, 21 figures, 6 tables, European Conference on Computer Vision (ECCV) 2024

Recent innovations in language model training have demonstrated that it is possible to create highly performant models that are small enough to run on a smartphone. As these models are deployed in an increasing number of domains, it is critical to ensure that they are aligned with human preferences and safety considerations. In this report, we present our methodology for safety aligning the Phi-3 series of language models. We utilized a "break-fix" cycle, performing multiple rounds of dataset curation, safety post-training, benchmarking, red teaming, and vulnerability identification to cover a variety of harm areas in both single and multi-turn scenarios. Our results indicate that this approach iteratively improved the performance of the Phi-3 models across a wide range of responsible AI benchmarks. Finally, we include additional red teaming strategies and evaluations that were used to test the safety behavior of Phi-3.5-mini and Phi-3.5-MoE, which were optimized for multilingual capabilities.

Accurate modeling of system dynamics is crucial for achieving high-performance planning and control of robotic systems. Although existing data-driven approaches represent a promising approach for modeling dynamics, their accuracy is limited to a short prediction horizon, overlooking the impact of compounding prediction errors over longer prediction horizons. Strategies to mitigate these cumulative errors remain underexplored. To bridge this gap, in this paper, we study the key design choices for efficiently learning long-horizon prediction dynamics for quadrotors. Specifically, we analyze the impact of multiple architectures, historical data, and multi-step loss formulation. We show that sequential modeling techniques showcase their advantage in minimizing compounding errors compared to other types of solutions. Furthermore, we propose a novel decoupled dynamics learning approach, which further simplifies the learning process while also enhancing the approach modularity. Extensive experiments and ablation studies on real-world quadrotor data demonstrate the versatility and precision of the proposed approach. Our outcomes offer several insights and methodologies for enhancing long-term predictive accuracy of learned quadrotor dynamics for planning and control., Comment: 8 pages, 5 figures, 3 tables. Paper accepted by IROS 2024

Achieving photorealistic 3D view synthesis and relighting of human portraits is pivotal for advancing AR/VR applications. Existing methodologies in portrait relighting demonstrate substantial limitations in terms of generalization and 3D consistency, coupled with inaccuracies in physically realistic lighting and identity preservation. Furthermore, personalization from a single view is difficult to achieve and often requires multiview images during the testing phase or involves slow optimization processes. This paper introduces Lite2Relight, a novel technique that can predict 3D consistent head poses of portraits while performing physically plausible light editing at interactive speed. Our method uniquely extends the generative capabilities and efficient volumetric representation of EG3D, leveraging a lightstage dataset to implicitly disentangle face reflectance and perform relighting under target HDRI environment maps. By utilizing a pre-trained geometry-aware encoder and a feature alignment module, we map input images into a relightable 3D space, enhancing them with a strong face geometry and reflectance prior. Through extensive quantitative and qualitative evaluations, we show that our method outperforms the state-of-the-art methods in terms of efficacy, photorealism, and practical application. This includes producing 3D-consistent results of the full head, including hair, eyes, and expressions. Lite2Relight paves the way for large-scale adoption of photorealistic portrait editing in various domains, offering a robust, interactive solution to a previously constrained problem. Project page: https://vcai.mpi-inf.mpg.de/projects/Lite2Relight/, Comment: Accepted at SIGGRAPH '24: ACM SIGGRAPH 2024 Conference Papers

Two simple yet powerful optimization algorithms, named the Best-Mean-Random (BMR) and Best-Worst-Random (BWR) algorithms, are developed and presented in this paper to handle both constrained and unconstrained optimization problems. These algorithms are free of metaphors and algorithm-specific parameters. The BMR algorithm is based on the best, mean, and random solutions of the population generated for solving a given problem, and the BWR algorithm is based on the best, worst, and random solutions. The performances of the proposed two algorithms are investigated by implementing them on 26 real-life nonconvex constrained optimization problems given in the Congress on Evolutionary Computation (CEC) 2020 competition, and comparisons are made with those of the other prominent optimization algorithms. The performances on 12 constrained engineering problems are also investigated, and the results are compared with those of very recent algorithms (in some cases, compared with more than 30 algorithms). Furthermore, computational experiments are conducted on 30 unconstrained standard benchmark optimization problems, including 5 recently developed benchmark problems with distinct characteristics. The results demonstrated the superior competitiveness and superiority of the proposed simple algorithms. The optimization research community may gain an advantage by adapting these algorithms to solve various constrained and unconstrained real-life optimization problems across various scientific and engineering disciplines. The codes of the BMR and BWR algorithms are available at https://sites.google.com/view/bmr-bwr-optimization-algorithm/home?authuser=0., Comment: 37 pages, 6 figures, improved version of the own original paper

We present multiwavelength polarization measurements of the luminous blazar Mrk~501 over a 14-month period. The 2--8 keV X-ray polarization was measured with the Imaging X-ray Polarimetry Explorer (IXPE) with six 100-ks observations spanning from 2022 March to 2023 April. Each IXPE observation was accompanied by simultaneous X-ray data from NuSTAR, Swift/XRT, and/or XMM-Newton. Complementary optical-infrared polarization measurements were also available in the B, V, R, I, and J bands, as were radio polarization measurements from 4.85 GHz to 225.5 GHz. Among the first five IXPE observations, we did not find significant variability in the X-ray polarization degree and angle with IXPE. However, the most recent sixth observation found an elevated polarization degree at $>3\sigma$ above the average of the other five observations. The optical and radio measurements show no apparent correlations with the X-ray polarization properties. Throughout the six IXPE observations, the X-ray polarization degree remained higher than, or similar to, the R-band optical polarization degree, which remained higher than the radio value. This is consistent with the energy-stratified shock scenario proposed to explain the first two IXPE observations, in which the polarized X-ray, optical, and radio emission arises from different regions., Comment: Accepted for publication in ApJ

Kotlarski (1978) proved a result on identification of the distributions of independent random variables $X,Y$ and $Z$ from the joint distribution of the bivariate random vector $(U,V)$ where $(U,V)= (\max(X,Z),\max(Y,Z)).$ We extend this result to the case $(U,V)=(\max(X,aZ_1,bZ_2),\max(Y,cZ_1,dZ_2))$ where $X,Y,Z_1,Z_2$ are independent or max-independent random variables, $Z_1$ and $Z_2$ are identically distributed and $a,b,c,d$ are known positive constants.

We consider the problem of active learning for global sensitivity analysis of expensive black-box functions. Our aim is to efficiently learn the importance of different input variables, e.g., in vehicle safety experimentation, we study the impact of the thickness of various components on safety objectives. Since function evaluations are expensive, we use active learning to prioritize experimental resources where they yield the most value. We propose novel active learning acquisition functions that directly target key quantities of derivative-based global sensitivity measures (DGSMs) under Gaussian process surrogate models. We showcase the first application of active learning directly to DGSMs, and develop tractable uncertainty reduction and information gain acquisition functions for these measures. Through comprehensive evaluation on synthetic and real-world problems, our study demonstrates how these active learning acquisition strategies substantially enhance the sample efficiency of DGSM estimation, particularly with limited evaluation budgets. Our work paves the way for more efficient and accurate sensitivity analysis in various scientific and engineering applications.

Machine learning models have been exponentially growing in terms of their parameter size over the past few years. We are now seeing the rise of trillion-parameter models. The large models cannot fit into a single GPU and thus require partitioned deployment across GPUs and even hosts. A high-performance collective communication library (CCL) such as NCCL is essential to fully utilize expensive GPU resources. However, CCL is not a great fit for inference. Unlike training for which a fixed amount of GPU resources is used for fixed workloads (e.g., input datasets), the inference workloads can change dynamically over time. Failures at the serving time can also impact individual user's experiences directly. In contrast, workers in a CCL process group share a single fault domain and the process group cannot grow as the workloads increase. The gap between the unique characteristics of model serving and CCL's nature makes it hard to serve large models elastically. To bridge the gap, we propose MultiWorld that enables fault tolerance and online scaling at the granularity of workers for model serving. Our evaluation showcases that enabling these new functionalities incurs small overheads (1.4-4.3% throughput loss) for most of the scenarios we tested.

This paper tackles the multi-vehicle Coverage Path Planning (CPP) problem, crucial for applications like search and rescue or environmental monitoring. Due to its NP-hard nature, finding optimal solutions becomes infeasible with larger problem sizes. This motivates the development of heuristic approaches that enhance efficiency even marginally. We propose a novel approach for exploring paths in a 2D grid, specifically designed for easy integration with the Quantum Alternating Operator Ansatz (QAOA), a powerful quantum heuristic. Our contribution includes: 1) An objective function tailored to solve the multi-vehicle CPP using QAOA. 2) Theoretical proofs guaranteeing the validity of the proposed approach. 3) Efficient construction of QAOA operators for practical implementation. 4) Resource estimation to assess the feasibility of QAOA execution. 5) Performance comparison against established algorithms like the Depth First Search. This work paves the way for leveraging quantum computing in optimizing multi-vehicle path planning, potentially leading to real-world advancements in various applications.

In this paper, we propose an innovative Graphical User Interface (GUI) aimed at improving preoperative planning and intra-operative guidance for precise spinal screw placement through vertebrae segmentation. The methodology encompasses both front-end and back-end computations. The front end comprises a GUI that allows surgeons to precisely adjust the placement of screws on X-Ray images, thereby improving the simulation of surgical screw insertion in the patient's spine. On the other hand, the back-end processing involves several steps, including acquiring spinal X-ray images, performing pre-processing techniques to reduce noise, and training a neural network model to achieve real-time segmentation of the vertebrae. The integration of vertebral segmentation in the GUI ensures precise screw placement, reducing complications like nerve injury and ultimately improving surgical outcomes. The Spine-Vision provides a comprehensive solution with innovative features like synchronous AP-LP planning, accurate screw positioning via vertebrae segmentation, effective screw visualization, and dynamic position adjustments. This X-ray image-based GUI workflow emerges as a valuable tool, enhancing precision and safety in spinal screw placement and planning procedures.

We present the analysis of optical photometric and spectroscopic observations of two non-magnetic cataclysmic variables, namely CRTS J080846.2+313106 and V416 Dra. CRTS J080846.2+313106 has been found to vary with a period of 4.9116$\pm$0.0003 h, which was not found in earlier studies and is provisionally suggested as the orbital period of the system. In both long-period systems, the observed dominant signal at second harmonic of the orbital frequency and the orbital modulation during quiescence are suggestive of ellipsoidal variation from changing aspects of the secondary, with an additional contribution from the accretion stream or hotspot. However, during the outburst, the hotspot itself is overwhelmed by the increased brightness, which is possibly associated with the accretion disc. The mid-eclipse phase for V416 Dra occurs earlier and the width of the eclipse is greater during outbursts compared to quiescence, suggesting an increased accretion disc radius during outbursts. Furthermore, the investigation of accretion disc eclipse in V416 Dra implies that a total disc eclipse is possible during quiescence, whereas the disc seems to be partially obscured during outbursts, which further signifies that the disc may grow in size as the outburst progresses. Optical spectra of CRTS J080846.2+313106 and V416 Dra are typical of dwarf novae during quiescence, and they both show a significant contribution from the M2-4V secondary. The light curve patterns, orbital periods, and spectra observed in both systems look remarkably similar, and seem to resemble the characteristics of U Gem-type dwarf novae., Comment: 14 pages, 11 Figures, and 3 Tables, Accepted for publication in A&A

Foundation ASR models often support many languages, e.g. 100 languages in Whisper. However, there has been limited work on integrating an additional, typically low-resource, language, while maintaining performance on the original language set. Fine-tuning, while simple, may degrade the accuracy of the original set. We compare three approaches that exploit adaptation parameters: soft language code tuning, train only the language code; soft prompt tuning, train prepended tokens; and LoRA where a small set of additional parameters are optimised. Elastic Weight Consolidation (EWC) offers an alternative compromise with the potential to maintain performance in specific target languages. Results show that direct fine-tuning yields the best performance for the new language but degrades existing language capabilities. EWC can address this issue for specific languages. If only adaptation parameters are used, the language capabilities are maintained but at the cost of performance in the new language., Comment: Proceedings of Interspeech

Recurrent large language models that compete with Transformers in language modeling perplexity are emerging at a rapid rate (e.g., Mamba, RWKV). Excitingly, these architectures use a constant amount of memory during inference. However, due to the limited memory, recurrent LMs cannot recall and use all the information in long contexts leading to brittle in-context learning (ICL) quality. A key challenge for efficient LMs is selecting what information to store versus discard. In this work, we observe the order in which information is shown to the LM impacts the selection difficulty. To formalize this, we show that the hardness of information recall reduces to the hardness of a problem called set disjointness (SD), a quintessential problem in communication complexity that requires a streaming algorithm (e.g., recurrent model) to decide whether inputted sets are disjoint. We empirically and theoretically show that the recurrent memory required to solve SD changes with set order, i.e., whether the smaller set appears first in-context. Our analysis suggests, to mitigate the reliance on data order, we can put information in the right order in-context or process prompts non-causally. Towards that end, we propose: (1) JRT-Prompt, where context gets repeated multiple times in the prompt, effectively showing the model all data orders. This gives $11.0 \pm 1.3$ points of improvement, averaged across $16$ recurrent LMs and the $6$ ICL tasks, with $11.9\times$ higher throughput than FlashAttention-2 for generation prefill (length $32$k, batch size $16$, NVidia H100). We then propose (2) JRT-RNN, which uses non-causal prefix-linear-attention to process prompts and provides $99\%$ of Transformer quality at $360$M params., $30$B tokens and $96\%$ at $1.3$B params., $50$B tokens on average across the tasks, with $19.2\times$ higher throughput for prefill than FA2.

XB 1254-690 is a neutron star low-mass X-ray binary with an orbital period of 3.88 hrs, and it exhibits energy-dependent intensity dips, thermonuclear bursts, and flares. We present the results of an analysis of a long observation of this source using the AstroSat satellite. The X-ray light curve gradually changed from a high-intensity flaring state to a low-intensity one with a few dips. The hardness intensity diagram showed that the source is in a high-intensity banana state with a gradually changing flux. Based on this, we divide the observation into four flux levels for a flux-resolved spectral study. The X-ray spectra can be explained by a model consisting of absorption, thermal emission from the disc and non-thermal emission from the corona. From our studies, we detect a correlation between the temperature of the thermal component and the flux and we examine the implications of our results for the accretion disc geometry of this source., Comment: Accepted for publication in MNRAS; 11 pages, 12 figures

We develop a novel algorithm to construct a congestion-approximator with polylogarithmic quality on a capacitated, undirected graph in nearly-linear time. Our approach is the first *bottom-up* hierarchical construction, in contrast to previous *top-down* approaches including that of Racke, Shah, and Taubig (SODA 2014), the only other construction achieving polylogarithmic quality that is implementable in nearly-linear time (Peng, SODA 2016). Similar to Racke, Shah, and Taubig, our construction at each hierarchical level requires calls to an approximate max-flow/min-cut subroutine. However, the main advantage to our bottom-up approach is that these max-flow calls can be implemented directly *without recursion*. More precisely, the previously computed levels of the hierarchy can be converted into a *pseudo-congestion-approximator*, which then translates to a max-flow algorithm that is sufficient for the particular max-flow calls used in the construction of the next hierarchical level. As a result, we obtain the first non-recursive algorithms for congestion-approximator and approximate max-flow that run in nearly-linear time, a conceptual improvement to the aforementioned algorithms that recursively alternate between the two problems., Comment: SODA 2025, 46 pages

Massive Open Online Courses (MOOCs) have significantly enhanced educational accessibility by offering a wide variety of courses and breaking down traditional barriers related to geography, finance, and time. However, students often face difficulties navigating the vast selection of courses, especially when exploring new fields of study. Driven by this challenge, researchers have been exploring course recommender systems to offer tailored guidance that aligns with individual learning preferences and career aspirations. These systems face particular challenges in effectively addressing the ``cold start'' problem for new users. Recent advancements in recommender systems suggest integrating large language models (LLMs) into the recommendation process to enhance personalized recommendations and address the ``cold start'' problem. Motivated by these advancements, our study introduces RAMO (Retrieval-Augmented Generation for MOOCs), a system specifically designed to overcome the ``cold start'' challenges of traditional course recommender systems. The RAMO system leverages the capabilities of LLMs, along with Retrieval-Augmented Generation (RAG)-facilitated contextual understanding, to provide course recommendations through a conversational interface, aiming to enhance the e-learning experience., Comment: 7 pages, this paper underwent a rigorous review process and was officially accepted on May 31, 2024, for presentation at the Educational Data Mining 2024 Workshop: Leveraging Large Language Models for Next Generation Educational Technologies

Transformer-based architectures have become the de-facto standard models for diverse vision tasks owing to their superior performance. As the size of the models continues to scale up, model distillation becomes extremely important in various real applications, particularly on devices limited by computational resources. However, prevailing knowledge distillation methods exhibit diminished efficacy when confronted with a large capacity gap between the teacher and the student, e.g, 10x compression rate. In this paper, we present a novel approach named Automatic Multi-step Distillation (AMD) for large-scale vision model compression. In particular, our distillation process unfolds across multiple steps. Initially, the teacher undergoes distillation to form an intermediate teacher-assistant model, which is subsequently distilled further to the student. An efficient and effective optimization framework is introduced to automatically identify the optimal teacher-assistant that leads to the maximal student performance. We conduct extensive experiments on multiple image classification datasets, including CIFAR-10, CIFAR-100, and ImageNet. The findings consistently reveal that our approach outperforms several established baselines, paving a path for future knowledge distillation methods on large-scale vision models., Comment: 19 pages, 5 figures

Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint speech-text foundational models. In this work, we present a comprehensive analysis on building ASR systems with discrete codes. We investigate different methods for codec training such as quantization schemes and time-domain vs spectral feature encodings. We further explore ASR training techniques aimed at enhancing performance, training efficiency, and noise robustness. Drawing upon our findings, we introduce a codec ASR pipeline that outperforms Encodec at similar bit-rate. Remarkably, it also surpasses the state-of-the-art results achieved by strong self-supervised models on the 143 languages ML-SUPERB benchmark despite being smaller in size and pretrained on significantly less data., Comment: Accepted at Interspeech 2024

The use of generative AI in video game development is on the rise, and as the conversational and other capabilities of large language models continue to improve, we expect LLM-driven non-player characters (NPCs) to become widely deployed. In this paper, we seek to understand how human players collaborate with LLM-driven NPCs to accomplish in-game goals. We design a minigame within Minecraft where a player works with two GPT4-driven NPCs to complete a quest. We perform a user study in which 28 Minecraft players play this minigame and share their feedback. On analyzing the game logs and recordings, we find that several patterns of collaborative behavior emerge from the NPCs and the human players. We also report on the current limitations of language-only models that do not have rich game-state or visual understanding. We believe that this preliminary study and analysis will inform future game developers on how to better exploit these rapidly improving generative AI models for collaborative roles in games., Comment: Accepted at Wordplay workshop at ACL 2024

The advent of the sixth-generation (6G) networks presents another round of revolution for the mobile communication landscape, promising an immersive experience, robust reliability, minimal latency, extreme connectivity, ubiquitous coverage, and capabilities beyond communication, including intelligence and sensing. To achieve these ambitious goals, it is apparent that 6G networks need to incorporate the state-of-the-art technologies. One of the technologies that has garnered rising interest is fluid antenna system (FAS) which represents any software-controllable fluidic, conductive, or dielectric structure capable of dynamically changing its shape and position to reconfigure essential radio-frequency (RF) characteristics. Compared to traditional antenna systems (TASs) with fixed-position radiating elements, the core idea of FAS revolves around the unique flexibility of reconfiguring the radiating elements within a given space. One recent driver of FAS is the recognition of its position-flexibility as a new degree of freedom (dof) to harness diversity and multiplexing gains. In this paper, we provide a comprehensive tutorial, covering channel modeling, signal processing and estimation methods, information-theoretic insights, new multiple access techniques, and hardware designs. Moreover, we delineate the challenges of FAS and explore the potential of using FAS to improve the performance of other contemporary technologies. By providing insights and guidance, this tutorial paper serves to inspire researchers to explore new horizons and fully unleash the potential of FAS., Comment: 50 pages, 45 figures, 5 tables. Submitted for potential publication

We prove the conjecture that the deformation limit of Moishezon manifolds under a smooth deformation over a unit disk in $\mathbb{C}$ is Moishezon., Comment: All comments are welcome

Abstractive Speech Summarization (SSum) aims to generate human-like text summaries from spoken content. It encounters difficulties in handling long speech input and capturing the intricate cross-modal mapping between long speech inputs and short text summaries. Research on large language models (LLMs) and multimodal information fusion has provided new insights for addressing these challenges. In this paper, we propose an end-to-end SSum model that utilizes Q-Former as a connector for the audio-text modality and employs LLMs to generate text summaries directly from speech features. We adopt a multi-stage training approach that includes LLM based ASR and Text Summarization (TSum) tasks as auxiliary tasks. ASR tasks are used to align feature spaces and enhance the LLM's ability to handle longer speech. Then, we utilize a curriculum learning strategy to facilitate the model's transition from TSum to SSum. Finally, our model achieves competitive performance on the How-2 dataset., Comment: InterSpeech 2024

Increasing the quantum information processing power with limited number of hosts is vital for achieving quantum advantage. Here we propose a novel scheme that achieves a scalable n-ion-2n-qubit quantum processor utilizing four internal levels of each ion, and experimentally implement a 1-ion-2-qubit universal processor using the valence electron spin and nuclear spin of a single 171Yb+ ion. Fidelities of single-qubit and two-qubit gates are around 0.98 obtained by quantum process tomography. Additionally, the Grover's algorithm is implemented with a successful rate exceeding 0.99. We provide explicit scaling-up protocols based on standard laser-less and laser-based frameworks, and further demonstrate that the electron/nuclear-spin scheme allows less demanding two-qubit entangling gates between different ions. The replacement of some inter-atomic gates by intra-atomic gates could increase the fidelity of some quantum circuits. Our work paves the way towards achieving 2n-times increase in the size of quantum computational Hilbert space with n ions.

There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech foundation model with strong performance on speech recognition and English translation, is used as the example model. Using speech-to-speech retrieval to analyse the audio representations generated by the encoder, we show that utterances from different languages are mapped to a shared semantic space. This shared embedding space can then be leveraged for zero-shot cross-lingual transfer in speech translation. By fine-tuning the Whisper decoder with only English-to-Chinese speech translation data, improved performance for translation to Chinese can be obtained for multiple languages, in addition to English. Furthermore, for languages related to those seen in training it is possible to perform speech translation, despite the model never seeing the language in training, or being able to perform transcription.

We prove a lower bound on the communication complexity of computing the $n$-fold xor of an arbitrary function $f$, in terms of the communication complexity and rank of $f$. We prove that $D(f^{\oplus n}) \geq n \cdot \Big(\frac{\Omega(D(f))}{\log \mathsf{rk}(f)} -\log \mathsf{rk}(f)\Big )$, where here $D(f), D(f^{\oplus n})$ represent the deterministic communication complexity, and $\mathsf{rk}(f)$ is the rank of $f$. Our methods involve a new way to use information theory to reason about deterministic communication complexity.