Search

With models getting stronger, evaluations have grown more complex, testing multiple skills in one benchmark and even in the same instance at once. However, skill-wise performance is obscured when inspecting aggregate accuracy, under-utilizing the rich signal modern benchmarks contain. We propose an automatic approach to recover the underlying skills relevant for any evaluation instance, by way of inspecting model-generated rationales. After validating the relevance of rationale-parsed skills and inferring skills for $46$k instances over $12$ benchmarks, we observe many skills to be common across benchmarks, resulting in the curation of hundreds of skill-slices (i.e. sets of instances testing a common skill). Inspecting accuracy over these slices yields novel insights on model trade-offs: e.g., compared to GPT-4o and Claude 3.5 Sonnet, on average, Gemini 1.5 Pro is $18\%$ more accurate in "computing molar mass", but $19\%$ less accurate in "applying constitutional law", despite the overall accuracies of the three models differing by a mere $0.4\%$. Furthermore, we demonstrate the practical utility of our approach by showing that insights derived from skill slice analysis can generalize to held-out instances: when routing each instance to the model strongest on the relevant skills, we see a $3\%$ accuracy improvement over our $12$ dataset corpus. Our skill-slices and framework open a new avenue in model evaluation, leveraging skill-specific analyses to unlock a more granular and actionable understanding of model capabilities., Comment: Code at: github.com/microsoft/skill-slice-insights

Medical Vision-Language Pre-training (MedVLP) has made significant progress in enabling zero-shot tasks for medical image understanding. However, training MedVLP models typically requires large-scale datasets with paired, high-quality image-text data, which are scarce in the medical domain. Recent advancements in Large Language Models (LLMs) and diffusion models have made it possible to generate large-scale synthetic image-text pairs. This raises the question: "Can MedVLP succeed using purely synthetic data?" To address this, we use off-the-shelf generative models to create synthetic radiology reports and paired Chest X-ray (CXR) images, and propose an automated pipeline to build a diverse, high-quality synthetic dataset, enabling a rigorous study that isolates model and training settings, focusing entirely from the data perspective. Our results show that MedVLP models trained exclusively on synthetic data outperform those trained on real data by 3.8% in averaged AUC on zero-shot classification. Moreover, using a combination of synthetic and real data leads to a further improvement of 9.07%. Additionally, MedVLP models trained on synthetic or mixed data consistently outperform those trained on real data in zero-shot grounding, as well as in fine-tuned classification and segmentation tasks. Our analysis suggests MedVLP trained on well-designed synthetic data can outperform models trained on real datasets, which may be limited by low-quality samples and long-tailed distributions., Comment: Under Review

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models and use them to steer models accordingly. These vectors are computed as the difference in activations between inputs with and without instructions, enabling a modular approach to activation steering. We demonstrate how this method can enhance model adherence to constraints such as output format, length, and word inclusion, providing inference-time control over instruction following. Our experiments across four models demonstrate how we can use the activation vectors to guide models to follow constraints even without explicit instructions and to enhance performance when instructions are present. Additionally, we explore the compositionality of activation steering, successfully applying multiple instructions simultaneously. Finally, we demonstrate that steering vectors computed on instruction-tuned models can transfer to improve base models. Our findings demonstrate that activation steering offers a practical and scalable approach for fine-grained control in language generation.

Time series forecasting remains a challenging task, particularly in the context of complex multiscale temporal patterns. This study presents LLM-Mixer, a framework that improves forecasting accuracy through the combination of multiscale time-series decomposition with pre-trained LLMs (Large Language Models). LLM-Mixer captures both short-term fluctuations and long-term trends by decomposing the data into multiple temporal resolutions and processing them with a frozen LLM, guided by a textual prompt specifically designed for time-series data. Extensive experiments conducted on multivariate and univariate datasets demonstrate that LLM-Mixer achieves competitive performance, outperforming recent state-of-the-art models across various forecasting horizons. This work highlights the potential of combining multiscale analysis and LLMs for effective and scalable time-series forecasting., Comment: Time series forecasting using LLMs

We propose RoCoFT, a parameter-efficient fine-tuning method for large-scale language models (LMs) based on updating only a few rows and columns of the weight matrices in transformers. Through extensive experiments with medium-size LMs like BERT and RoBERTa, and larger LMs like Bloom-7B, Llama2-7B, and Llama2-13B, we show that our method gives comparable or better accuracies than state-of-art PEFT methods while also being more memory and computation-efficient. We also study the reason behind the effectiveness of our method with tools from neural tangent kernel theory. We empirically demonstrate that our kernel, constructed using a restricted set of row and column parameters, are numerically close to the full-parameter kernel and gives comparable classification performance. Ablation studies are conducted to investigate the impact of different algorithmic choices, including the selection strategy for rows and columns as well as the optimal rank for effective implementation of our method., Comment: RoCoFT is a parameter-efficient method

This study examines the alignment of \emph{Conference on Computer Vision and Pattern Recognition} (CVPR) research with the principles of the "bitter lesson" proposed by Rich Sutton. We analyze two decades of CVPR abstracts and titles using large language models (LLMs) to assess the field's embracement of these principles. Our methodology leverages state-of-the-art natural language processing techniques to systematically evaluate the evolution of research approaches in computer vision. The results reveal significant trends in the adoption of general-purpose learning algorithms and the utilization of increased computational resources. We discuss the implications of these findings for the future direction of computer vision research and its potential impact on broader artificial intelligence development. This work contributes to the ongoing dialogue about the most effective strategies for advancing machine learning and computer vision, offering insights that may guide future research priorities and methodologies in the field., Comment: NLP4Sceince Workshop, EMNLP 2024

Large Language Models (LLMs) are gaining significant popularity in recent years for specialized tasks using prompts due to their low computational cost. Standard methods like prefix tuning utilize special, modifiable tokens that lack semantic meaning and require extensive training for best performance, often falling short. In this context, we propose a novel method called Semantic Knowledge Tuning (SK-Tuning) for prompt and prefix tuning that employs meaningful words instead of random tokens. This method involves using a fixed LLM to understand and process the semantic content of the prompt through zero-shot capabilities. Following this, it integrates the processed prompt with the input text to improve the model's performance on particular tasks. Our experimental results show that SK-Tuning exhibits faster training times, fewer parameters, and superior performance on tasks such as text classification and understanding compared to other tuning methods. This approach offers a promising method for optimizing the efficiency and effectiveness of LLMs in processing language tasks., Comment: Accepted in Nature Scientific Reports

Plastic pollution presents an escalating global issue, impacting health and environmental systems, with micro- and nanoplastics found across mediums from potable water to air. Traditional methods for studying these contaminants are labor-intensive and time-consuming, necessitating a shift towards more efficient technologies. In response, this paper introduces micro- and nanoplastics (MiNa), a novel and open-source dataset engineered for the automatic detection and classification of micro and nanoplastics using object detection algorithms. The dataset, comprising scanning electron microscopy images simulated under realistic aquatic conditions, categorizes plastics by polymer type across a broad size spectrum. We demonstrate the application of state-of-the-art detection algorithms on MiNa, assessing their effectiveness and identifying the unique challenges and potential of each method. The dataset not only fills a critical gap in available resources for microplastic research but also provides a robust foundation for future advancements in the field.

Rigorous and reproducible evaluation is critical for assessing the state of the art and for guiding scientific advances in Artificial Intelligence. Evaluation is challenging in practice due to several reasons, including benchmark saturation, lack of transparency in methods used for measurement, development challenges in extracting measurements for generative tasks, and, more generally, the extensive number of capabilities required for a well-rounded comparison across models. We make three contributions to alleviate the above challenges. First, we present Eureka, an open-source framework for standardizing evaluations of large foundation models beyond single-score reporting and rankings. Second, we introduce Eureka-Bench as an extensible collection of benchmarks testing capabilities that (i) are still challenging for state-of-the-art models and (ii) represent fundamental but overlooked language and multimodal capabilities. The inherent space for improvement in non-saturated benchmarks enables us to discover meaningful differences between models at a capability level. Third, using Eureka, we conduct an analysis of 12 state-of-the-art models, providing in-depth insights into failure understanding and model comparison, which can be leveraged to plan targeted improvements. In contrast to recent trends in reports and leaderboards showing absolute rankings and claims for one model or another to be the best, our analysis shows that there is no such best model. Different models have different strengths, but there are models that appear more often than others as best performers for some capabilities. Despite the recent improvements, current models still struggle with several fundamental capabilities including detailed image understanding, benefiting from multimodal input when available rather than fully relying on language, factuality and grounding for information retrieval, and over refusals.

Neural audio codec tokens serve as the fundamental building blocks for speech language model (SLM)-based speech generation. However, there is no systematic understanding on how the codec system affects the speech generation performance of the SLM. In this work, we examine codec tokens within SLM framework for speech generation to provide insights for effective codec design. We retrain existing high-performing neural codec models on the same data set and loss functions to compare their performance in a uniform setting. We integrate codec tokens into two SLM systems: masked-based parallel speech generation system and an auto-regressive (AR) plus non-auto-regressive (NAR) model-based system. Our findings indicate that better speech reconstruction in codec systems does not guarantee improved speech generation in SLM. A high-quality codec decoder is crucial for natural speech production in SLM, while speech intelligibility depends more on quantization mechanism., Comment: Accepted by SLT-2024

Utilization of intracranial electroencephalography (iEEG) is rapidly increasing for clinical and brain-computer interface applications. iEEG facilitates the recording of neural activity with high spatial and temporal resolution, making it a desirable neuroimaging modality for studying neural dynamics. Despite its benefits, iEEG faces challenges such as inter-subject variability in electrode implantation, which makes the development of unified neural decoder models across different patients difficult. In this research, we introduce a novel decoder model that is robust to inter-subject electrode implantation variability. We call this model RISE-iEEG, which stands for Robust Inter-Subject Electrode Implantation Variability iEEG Classifier. RISE-iEEG employs a deep neural network structure preceded by a patient-specific projection network. The projection network maps the neural data of individual patients onto a common low-dimensional space, compensating for the implantation variability. In other words, we developed an iEEG decoder model that can be applied across multiple patients' data without requiring the coordinates of electrode for each patient. The performance of RISE-iEEG across multiple datasets, including the Audio-Visual dataset, Music Reconstruction dataset, and Upper-Limb Movement dataset, surpasses that of state-of-the-art iEEG decoder models such as HTNet and EEGNet. Our analysis shows that the performance of RISE-iEEG is 10\% higher than that of HTNet and EEGNet in terms of F1 score, with an average F1 score of 83\%, which is the highest result among the evaluation methods defined. Furthermore, the analysis of projection network weights in the Music Reconstruction dataset across patients suggests that the Superior Temporal lobe serves as the primary encoding neural node. This finding aligns with the auditory processing physiology.

With the advancement of technologies like Industry 4.0, communication networks must meet stringent requirements of applications demanding deterministic and bounded latencies. The problem is further compounded by the need to periodically synchronize network devices to a common time reference to address clock drifts. Existing solutions often simplify the problem by assuming either perfect synchronization or a worst-case error. Additionally, these approaches delay the scheduling process in network devices until the scheduled frame is guaranteed to have arrived in the device queue, inducing additional delays to the stream. A novel approach that completely avoids queuing delays is proposed, enabling it to meet even the strictest deadline requirement. Furthermore, both approaches can be enhanced by incorporating network-derived time-synchronization information. This is not only convenient for meeting deadline requirements but also improves bandwidth efficiency.

There is a rising interest and trend in research towards directly translating speech from one language to another, known as end-to-end speech-to-speech translation. However, most end-to-end models struggle to outperform cascade models, i.e., a pipeline framework by concatenating speech recognition, machine translation and text-to-speech models. The primary challenges stem from the inherent complexities involved in direct translation tasks and the scarcity of data. In this study, we introduce a novel model framework TransVIP that leverages diverse datasets in a cascade fashion yet facilitates end-to-end inference through joint probability. Furthermore, we propose two separated encoders to preserve the speaker's voice characteristics and isochrony from the source speech during the translation process, making it highly suitable for scenarios such as video dubbing. Our experiments on the French-English language pair demonstrate that our model outperforms the current state-of-the-art speech-to-speech translation model., Comment: Neural Information Processing Systems, poster

In this paper, we experimentally report the saturated absorption spectroscopy (SAS) and frequency locking (FL) of a narrow-band DBR laser with 0.5MHz linewidth on the LD2-transition of Rb atoms., Comment: submitted to International Conference on Quantum Technologies & Industrial Applications at Shahid-Beheshti University, Tehran, Iran May 28-May 29, 2024

Non-parametric models, such as Gaussian Processes (GP), show promising results in the analysis of complex data. Their applications in neuroscience data have recently gained traction. In this research, we introduce a novel neural decoder model built upon GP models. The core idea is that two GPs generate neural data and their associated labels using a set of low-dimensional latent variables. Under this modeling assumption, the latent variables represent the underlying manifold or essential features present in the neural data. When GPs are trained, the latent variable can be inferred from neural data to decode the labels with a high accuracy. We demonstrate an application of this decoder model in a verbal memory experiment dataset and show that the decoder accuracy in predicting stimulus significantly surpasses the state-of-the-art decoder models. The preceding performance of this model highlights the importance of utilizing non-parametric models in the analysis of neuroscience data.

Ground Penetrating Radar (GPR) has been widely studied as a tool for extracting soil parameters relevant to agriculture and horticulture. When combined with Machine-Learning-based (ML) methods, high-resolution Stepped Frequency Countinuous Wave Radar (SFCW) measurements hold the promise to give cost effective access to depth resolved soil parameters, including at root-level depth. In a first step in this direction, we perform an extensive field survey with a tractor mounted SFCW GPR instrument. Using ML data processing we test the GPR instrument's capabilities to predict the apparent electrical conductivity (ECaR) as measured by a simultaneously recording Electromagnetic Induction (EMI) instrument. The large-scale field measurement campaign with 3472 co-registered and geo-located GPR and EMI data samples distributed over ~6600 square meters was performed on a golf course. The selected terrain benefits from a high surface homogeneity, but also features the challenge of only small, and hence hard to discern, variations in the measured soil parameter. Based on the quantitative results we suggest the use of nugget-to-sill ratio as a performance metric for the evaluation of end-to-end ML performance in the agricultural setting and discuss the limiting factors in the multi-sensor regression setting. The code is released as open source and available at https://opensource.silicon-austria.com/xuc/soil-analysis-machine-learning-stepped-frequency-gpr.

With the advent of smart grid (SG) systems, electricity networks have been able to ensure greater efficiency and utility by interconnecting their grids through cloud-based technology. As SGs become increasingly complex, a wide range of security challenges arise, threatening the grid's reliability, safety, efficiency, and stability. The security challenges include the potential exposure of personal data due to hackers intercepting the communications between the SG infrastructure and the smart meters. Security awareness plays a vital role in addressing some of these challenges. However, the traditional training programs are no longer efficient for instilling information security culture in organisations or from an individual user perspective. Gamification is a new concept in the field of information security awareness training (SAT) campaigns that can be introduced to fill in this gap by providing employees with a means of practising and learning about many security flaws and risks that exist within the organisation. Thus, this paper examines the effectiveness of gamification in promoting security awareness among smart meter components for smart grid users/operators. A gaming application is developed as part of the study with the aim of training and evaluating the results through three difficulty levels of questionnaires. Furthermore, the results are evaluated for the three difficulty levels as well as the overall flag captured. It can be demonstrated that the scores of participants in the three levels have improved by 40%, 35% and 29%, respectively. This reflects the awareness of learning within our system., Comment: 18 pages, 15 figures and 2 tables

Thyroid cancer is an increasing global health concern that requires advanced diagnostic methods. The application of AI and radiomics to thyroid cancer diagnosis is examined in this review. A review of multiple databases was conducted in compliance with PRISMA guidelines until October 2023. A combination of keywords led to the discovery of an English academic publication on thyroid cancer and related subjects. 267 papers were returned from the original search after 109 duplicates were removed. Relevant studies were selected according to predetermined criteria after 124 articles were eliminated based on an examination of their abstract and title. After the comprehensive analysis, an additional six studies were excluded. Among the 28 included studies, radiomics analysis, which incorporates ultrasound (US) images, demonstrated its effectiveness in diagnosing thyroid cancer. Various results were noted, some of the studies presenting new strategies that outperformed the status quo. The literature has emphasized various challenges faced by AI models, including interpretability issues, dataset constraints, and operator dependence. The synthesized findings of the 28 included studies mentioned the need for standardization efforts and prospective multicenter studies to address these concerns. Furthermore, approaches to overcome these obstacles were identified, such as advances in explainable AI technology and personalized medicine techniques. The review focuses on how AI and radiomics could transform the diagnosis and treatment of thyroid cancer. Despite challenges, future research on multidisciplinary cooperation, clinical applicability validation, and algorithm improvement holds the potential to improve patient outcomes and diagnostic precision in the treatment of thyroid cancer., Comment: 50 pages, 8 figures, 1 table, 119 references

Recent advancements in zero-shot text-to-speech (TTS) modeling have led to significant strides in generating high-fidelity and diverse speech. However, dialogue generation, along with achieving human-like naturalness in speech, continues to be a challenge. In this paper, we introduce CoVoMix: Conversational Voice Mixture Generation, a novel model for zero-shot, human-like, multi-speaker, multi-round dialogue speech generation. CoVoMix first converts dialogue text into multiple streams of discrete tokens, with each token stream representing semantic information for individual talkers. These token streams are then fed into a flow-matching based acoustic model to generate mixed mel-spectrograms. Finally, the speech waveforms are produced using a HiFi-GAN model. Furthermore, we devise a comprehensive set of metrics for measuring the effectiveness of dialogue modeling and generation. Our experimental results show that CoVoMix can generate dialogues that are not only human-like in their naturalness and coherence but also involve multiple talkers engaging in multiple rounds of conversation. This is exemplified by instances generated in a single channel where one speaker's utterance is seamlessly mixed with another's interjections or laughter, indicating the latter's role as an attentive listener. Audio samples are available at https://aka.ms/covomix.

The isometric mapping method employs the shortest path algorithm to estimate the Euclidean distance between points on High dimensional (HD) manifolds. This may not be sufficient for weakly uniformed HD data as it could lead to overestimating distances between far neighboring points, resulting in inconsistencies between the intrinsic (local) and extrinsic (global) distances during the projection. To address this issue, we modify the shortest path algorithm by adding a novel constraint inspired by the Parzen-Rosenblatt (PR) window, which helps to maintain the uniformity of the constructed shortest-path graph in Isomap. Multiple imaging datasets overall of 72,236 cases, 70,000 MINST data, 1596 from multiple Chest-XRay pneumonia datasets, and three NSCLC CT/PET datasets with a total of 640 lung cancer patients, were used to benchmark and validate PR-Isomap. 431 imaging biomarkers were extracted from each modality. Our results indicate that PR-Isomap projects HD attributes into a lower-dimensional (LD) space while preserving information, visualized by the MNIST dataset indicating the maintaining local and global distances. PR-Isomap achieved the highest comparative accuracies of 80.9% (STD:5.8) for pneumonia and 78.5% (STD:4.4), 88.4% (STD:1.4), and 61.4% (STD:11.4) for three NSCLC datasets, with a confidence interval of 95% for outcome prediction. Similarly, the multivariate Cox model showed higher overall survival, measured with c-statistics and log-likelihood test, of PR-Isomap compared to other dimensionality reduction methods. Kaplan Meier survival curve also signifies the notable ability of PR-Isomap to distinguish between high-risk and low-risk patients using multimodal imaging biomarkers preserving HD imaging characteristics for precision medicine., Comment: This is the author's version

Evaluating the theory of mind (ToM) capabilities of language models (LMs) has recently received a great deal of attention. However, many existing benchmarks rely on synthetic data, which risks misaligning the resulting experiments with human behavior. We introduce the first ToM dataset based on naturally occurring spoken dialogs, Common-ToM, and show that LMs struggle to demonstrate ToM. We then show that integrating a simple, explicit representation of beliefs improves LM performance on Common-ToM.

This study aims to investigate the comprehensive characterization of information content in multimedia (videos), particularly on YouTube. The research presents a multi-method framework for characterizing multimedia content by clustering signals from various modalities, such as audio, video, and text. With a focus on South China Sea videos as a case study, this approach aims to enhance our understanding of online content, especially on YouTube. The dataset includes 160 videos, and our findings offer insights into content themes and patterns within different modalities of a video based on clusters. Text modality analysis revealed topical themes related to geopolitical countries, strategies, and global security, while video and audio modality analysis identified distinct patterns of signals related to diverse sets of videos, including news analysis/reporting, educational content, and interviews. Furthermore, our findings uncover instances of content repurposing within video clusters, which were identified using the barcode technique and audio similarity assessments. These findings indicate potential content amplification techniques. In conclusion, this study uniquely enhances our current understanding of multimedia content information based on modality clustering techniques., Comment: 14 pages, In the 4th International Conference on SMART MULTIMEDIA, 2024

Lung cancer is the primary cause of cancer-related mortality, claiming approximately 1.79 million lives globally in 2020, with an estimated 2.21 million new cases diagnosed within the same period. Among these, Non-Small Cell Lung Cancer (NSCLC) is the predominant subtype, characterized by a notably bleak prognosis and low overall survival rate of approximately 25% over five years across all disease stages. However, survival outcomes vary considerably based on the stage at diagnosis and the therapeutic interventions administered. Recent advancements in artificial intelligence (AI) have revolutionized the landscape of lung cancer prognosis. AI-driven methodologies, including machine learning and deep learning algorithms, have shown promise in enhancing survival prediction accuracy by efficiently analyzing complex multi-omics data and integrating diverse clinical variables. By leveraging AI techniques, clinicians can harness comprehensive prognostic insights to tailor personalized treatment strategies, ultimately improving patient outcomes in NSCLC. Overviewing AI-driven data processing can significantly help bolster the understanding and provide better directions for using such systems., Comment: This is the author's version of a book chapter entitled: "Cancer Research: An Interdisciplinary Approach", Springer

Extracting meaningful information from high-dimensional data poses a formidable modeling challenge, particularly when the data is obscured by noise or represented through different modalities. This research proposes a novel non-parametric modeling approach, leveraging the Gaussian process (GP), to characterize high-dimensional data by mapping it to a latent low-dimensional manifold. This model, named the latent discriminative generative decoder (LDGD), employs both the data and associated labels in the manifold discovery process. We derive a Bayesian solution to infer the latent variables, allowing LDGD to effectively capture inherent stochasticity in the data. We demonstrate applications of LDGD on both synthetic and benchmark datasets. Not only does LDGD infer the manifold accurately, but its accuracy in predicting data points' labels surpasses state-of-the-art approaches. In the development of LDGD, we have incorporated inducing points to reduce the computational complexity of Gaussian processes for large datasets, enabling batch training for enhanced efficient processing and scalability. Additionally, we show that LDGD can robustly infer manifold and precisely predict labels for scenarios in that data size is limited, demonstrating its capability to efficiently characterize high-dimensional data with limited samples. These collective attributes highlight the importance of developing non-parametric modeling approaches to analyze high-dimensional data., Comment: 40 pages, 6 figures