Tootfinder

The Role of Code Proficiency in the Era of Generative AI
Gregorio Robles, Christoph Treude, Jesus M. Gonzalez-Barahona, Raula Gaikovina Kula
https://arxiv.org/abs/2405.01565

The Role of Code Proficiency in the Era of Generative AI
At the current pace of technological advancements, Generative AI models, including both Large Language Models and Large Multi-modal Models, are becoming integral to the developer workspace. However, challenges emerge due to the 'black box' nature of many of these models, where the processes behind their outputs are not transparent. This position paper advocates for a 'white box' approach to these generative models, emphasizing the necessity of transparency and understanding in AI-generated code…

How positive male role models are detoxifying the social media ‘manosphere’ | Social media | The Guardian https://www.theguardian.com/media/2024/mar/02/positive-male-role-models-detoxifying-social-media-manosphere

Analyzing the Role of Semantic Representations in the Era of Large Language Models
Zhijing Jin, Yuen Chen, Fernando Gonzalez, Jiarui Liu, Jiayi Zhang, Julian Michael, Bernhard Sch\"olkopf, Mona Diab
https://arxiv.org/abs/2405.01502

Analyzing the Role of Semantic Representations in the Era of Large Language Models
Traditionally, natural language processing (NLP) models often use a rich set of features created by linguistic expertise, such as semantic representations. However, in the era of large language models (LLMs), more and more tasks are turned into generic, end-to-end sequence generation problems. In this paper, we investigate the question: what is the role of semantic representations in the era of LLMs? Specifically, we investigate the effect of Abstract Meaning Representation (AMR) across five di…

A comparative study of conformal prediction methods for valid uncertainty quantification in machine learning
Nicolas Dewolf
https://arxiv.org/abs/2405.02082

A comparative study of conformal prediction methods for valid uncertainty quantification in machine learning
In the past decades, most work in the area of data analysis and machine learning was focused on optimizing predictive models and getting better results than what was possible with existing models. To what extent the metrics with which such improvements were measured were accurately capturing the intended goal, whether the numerical differences in the resulting values were significant, or whether uncertainty played a role in this study and if it should have been taken into account, was of second…

Simplicity in Complexity
Kevin Shen, Surabhi S Nath, Aenne Brielmann, Peter Dayan
https://arxiv.org/abs/2403.03134 https://arxiv.org/…

Simplicity in Complexity
The complexity of visual stimuli plays an important role in many cognitive phenomena, including attention, engagement, memorability, time perception and aesthetic evaluation. Despite its importance, complexity is poorly understood and ironically, previous models of image complexity have been quite \textit{complex}. There have been many attempts to find handcrafted features that explain complexity, but these features are usually dataset specific, and hence fail to generalise. On the other hand, …

Prioritizing Software Requirements Using Large Language Models
Malik Abdul Sami, Zeeshan Rasheed, Muhammad Waseem, Zheying Zhang, Tomas Herda, Pekka Abrahamsson
https://arxiv.org/abs/2405.01564

Prioritizing Software Requirements Using Large Language Models
Large Language Models (LLMs) are revolutionizing Software Engineering (SE) by introducing innovative methods for tasks such as collecting requirements, designing software, generating code, and creating test cases, among others. This article focuses on requirements engineering, typically seen as the initial phase of software development that involves multiple system stakeholders. Despite its key role, the challenge of identifying requirements and satisfying all stakeholders within time and budge…

This https://arxiv.org/abs/2403.11916 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Sound Horizon Independent Constraints on Early Dark Energy: The Role of Supernova Data
We assess the consistency of cosmological models that alter the size of the sound horizon at last scattering to resolve the Hubble tension with data from ACT + Planck CMB lensing, Big Bang Nucleosynthesis, and supernova data from Pantheon or Pantheon+. We use early dark energy (EDE) as an example model but conclude that the results apply to other similar models. We constrain $Λ$CDM and EDE with these data finding that while they can constrain $Λ$CDM very tightly, EDE opens up the parameter sp…

This https://arxiv.org/abs/2306.11980 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

LLM-based Smart Reply (LSR): Enhancing Collaborative Performance with ChatGPT-mediated Smart Reply System
Interactive user interfaces have increasingly explored AI's role in enhancing communication efficiency and productivity in collaborative tasks. The emergence of Large Language Models (LLMs) such as ChatGPT has revolutionized conversational agents, employing advanced deep learning techniques to generate context-aware, coherent, and personalized responses. Consequently, LLM-based AI assistants provide a more natural and efficient user experience across various scenarios. In this paper, we study h…

A pH Sensor Scaffold for Mapping Spatiotemporal Gradients in Three Dimensional In Vitro Tumour Models
Riccardo Rizzo, Valentina Onesto, Stefania Forciniti, Anil Chandra, Saumya Prasad, Helena Iuele, Francesco Colella, Giuseppe Gigli, Loretta L. del Mercato
https://arxiv.org/abs/2403.02838

A pH Sensor Scaffold for Mapping Spatiotemporal Gradients in Three Dimensional In Vitro Tumour Models
The detection of extracellular pH at single cell resolution is challenging and requires advanced sensibility. Sensing pH at a high spatial and temporal resolution might provide crucial information in understanding the role of pH and its fluctuations in a wide range of physio-pathological cellular processes, including cancer. Here, a method to embed silica-based fluorescent pH sensors into alginate-based three-dimensional (3D) microgels tumour models, coupled with a computational method for fine…

This https://arxiv.org/abs/2402.19276 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Modular Blind Video Quality Assessment
Blind video quality assessment (BVQA) plays a pivotal role in evaluating and improving the viewing experience of end-users across a wide range of video-based platforms and services. Contemporary deep learning-based models primarily analyze the video content in its aggressively downsampled format, while being blind to the impact of actual spatial resolution and frame rate on video quality. In this paper, we propose a modular BVQA model, and a method of training it to improve its modularity. Spec…

Discovering intrinsic multi-compartment pharmacometric models using Physics Informed Neural Networks
Imran Nasim, Adam Nasim
https://arxiv.org/abs/2405.00166

Discovering intrinsic multi-compartment pharmacometric models using Physics Informed Neural Networks
Pharmacometric models are pivotal across drug discovery and development, playing a decisive role in determining the progression of candidate molecules. However, the derivation of mathematical equations governing the system is a labor-intensive trial-and-error process, often constrained by tight timelines. In this study, we introduce PKINNs, a novel purely data-driven pharmacokinetic-informed neural network model. PKINNs efficiently discovers and models intrinsic multi-compartment-based pharmaco…

This https://arxiv.org/abs/2404.00826 has been replaced.
link: https://scholar.google.com/scholar?q=a

Extracting Social Determinants of Health from Pediatric Patient Notes Using Large Language Models: Novel Corpus and Methods
Social determinants of health (SDoH) play a critical role in shaping health outcomes, particularly in pediatric populations where interventions can have long-term implications. SDoH are frequently studied in the Electronic Health Record (EHR), which provides a rich repository for diverse patient data. In this work, we present a novel annotated corpus, the Pediatric Social History Annotation Corpus (PedSHAC), and evaluate the automatic extraction of detailed SDoH representations using fine-tuned…

Joint sentiment analysis of lyrics and audio in music
Lea Schaab, Anna Kruspe
https://arxiv.org/abs/2405.01988 https://arxiv.org/pdf/…

Joint sentiment analysis of lyrics and audio in music
Sentiment or mood can express themselves on various levels in music. In automatic analysis, the actual audio data is usually analyzed, but the lyrics can also play a crucial role in the perception of moods. We first evaluate various models for sentiment analysis based on lyrics and audio separately. The corresponding approaches already show satisfactory results, but they also exhibit weaknesses, the causes of which we examine in more detail. Furthermore, different approaches to combining the au…

This https://arxiv.org/abs/2403.11916 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Sound Horizon Independent Constraints on Early Dark Energy: The Role of Supernova Data
We assess the consistency of cosmological models that alter the size of the sound horizon at last scattering to resolve the Hubble tension with data from ACT + Planck CMB lensing, Big Bang Nucleosynthesis, and supernova data from Pantheon or Pantheon+. We use early dark energy (EDE) as an example model but conclude that the results apply to other similar models. We constrain $Λ$CDM and EDE with these data finding that while they can constrain $Λ$CDM very tightly, EDE opens up the parameter sp…

“Kind of a stupid game, isn’t it?”
War by #CalvinAndHobbes

Discovering intrinsic multi-compartment pharmacometric models using Physics Informed Neural Networks
Imran Nasim, Adam Nasim
https://arxiv.org/abs/2405.00166

Discovering intrinsic multi-compartment pharmacometric models using Physics Informed Neural Networks
Pharmacometric models are pivotal across drug discovery and development, playing a decisive role in determining the progression of candidate molecules. However, the derivation of mathematical equations governing the system is a labor-intensive trial-and-error process, often constrained by tight timelines. In this study, we introduce PKINNs, a novel purely data-driven pharmacokinetic-informed neural network model. PKINNs efficiently discovers and models intrinsic multi-compartment-based pharmaco…

This https://arxiv.org/abs/2402.01663 has been replaced.
link: https://scholar.google.com/scholar?q=a

Killer Apps: Low-Speed, Large-Scale AI Weapons
The accelerating advancements in Artificial Intelligence (AI) and Machine Learning (ML), highlighted by the development of cutting-edge Generative Pre-trained Transformer (GPT) models by organizations such as OpenAI, Meta, and Anthropic, present new challenges and opportunities in warfare and security. Much of the current focus is on AI's integration within weapons systems and its role in rapid decision-making in kinetic conflict. However, an equally important but often overlooked aspect is the…

Modulational instability in a quasi-one-dimensional Bose-Einstein condensates
Sherzod R. Otajonov, Bakhram A. Umarov, Fatkhulla Kh. Abdullaev
https://arxiv.org/abs/2405.02282

Modulational instability in a quasi-one-dimensional Bose-Einstein condensates
In this work, we investigate the modulational instability of plane wave solutions within a modified Gross-Pitaevskii equation framework. The equation features cubic and quartic nonlinearity. It models the behaviour of quasi-one-dimensional Bose-Einstein condensates in symmetric Bose-Bose mixtures of ultra-dilute cold atoms. Our study demonstrates the pivotal role of the competition between mean-field attractions and quantum fluctuation-induced repulsions. This competition significantly affects …

Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models
Xianzhen Luo, Qingfu Zhu, Zhiming Zhang, Xu Wang, Qing Yang, Dongliang Xu, Wanxiang Che
https://arxiv.org/abs/2403.00338

Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models
Instruction tuning plays a pivotal role in Code Large Language Models (Code LLMs) for the task of program synthesis. Presently, two dominant paradigms for collecting tuning data are natural-instruct (human-written) and self-instruct (automatically generated). Natural-instruct includes diverse and correct codes but lacks instruction-code pairs, and exists improper code formats like nested single-line codes. In contrast, self-instruct automatically generates proper paired data. However, it suffer…

Efficient Data-driven Scene Simulation using Robotic Surgery Videos via Physics-embedded 3D Gaussians
Zhenya Yang, Kai Chen, Yonghao Long, Qi Dou
https://arxiv.org/abs/2405.00956 …

Efficient Data-driven Scene Simulation using Robotic Surgery Videos via Physics-embedded 3D Gaussians
Surgical scene simulation plays a crucial role in surgical education and simulator-based robot learning. Traditional approaches for creating these environments with surgical scene involve a labor-intensive process where designers hand-craft tissues models with textures and geometries for soft body simulations. This manual approach is not only time-consuming but also limited in the scalability and realism. In contrast, data-driven simulation offers a compelling alternative. It has the potential …

This https://arxiv.org/abs/2112.14876 has been replaced.
link: https://scholar.google.com/scholar?q=a

Stochastic COVID-19 Model Influenced by Non-Gaussian Noise
Natural fluctuations have played a crucial role in affecting the dynamics of pervasive diseases such as the coronavirus. Examining the effects of irregular unsettling disturbances on epidemic models is important for understanding these dynamics. In this study, we introduce a mathematical model for the SIR (Susceptible-Infectious-Recovered) dynamics of the coronavirus, incorporating perturbations in the contact rate through Levy noise. The utilization of the Levy process is essential for the pro…

Pre-trained Model-based Actionable Warning Identification: A Feasibility Study
Xiuting Ge, Chunrong Fang, Quanjun Zhang, Daoyuan Wu, Bowen Yu, Qirui Zheng, An Guo, Shangwei Lin, Zhihong Zhao, Yang Liu, Zhenyu Chen
https://arxiv.org/abs/2403.02716

Pre-trained Model-based Actionable Warning Identification: A Feasibility Study
Actionable Warning Identification (AWI) plays a pivotal role in improving the usability of static code analyzers. Currently, Machine Learning (ML)-based AWI approaches, which mainly learn an AWI classifier from labeled warnings, are notably common. However, these approaches still face the problem of restricted performance due to the direct reliance on a limited number of labeled warnings to develop a classifier. Very recently, Pre-Trained Models (PTMs), which have been trained through billions …

This https://arxiv.org/abs/2402.13717 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent
Large Language Models (LLMs) have revolutionized open-domain dialogue agents but encounter challenges in multi-character role-playing (MCRP) scenarios. To address the issue, we present Neeko, an innovative framework designed for efficient multiple characters imitation. Unlike existing methods, Neeko employs a dynamic low-rank adapter (LoRA) strategy, enabling it to adapt seamlessly to diverse characters. Our framework breaks down the role-playing process into agent pre-training, multiple charac…

This https://arxiv.org/abs/2207.02460 has been replaced.
link: https://scholar.google.com/scholar?q=a

Combinatorics of the Berezin-Karpelevich Integral
The Berezin-Karpelevich integral is a double integral over unitary matrices which plays the role of the Itzykson-Zuber integral in rectangular matrix models. We obtain a topological expansion of the Berezin-Karpelevich integral in terms of monotone Hurwitz numbers, and obtain from this certain combinatorial identities.

This https://arxiv.org/abs/2403.05241 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hept…

Black Holes and Marchenko-Pastur distribution
The universal eigenvalue distribution characterizing the Gram matrix of semiclassical ensembles of black hole microstates is recognized as the Marchenko-Pastur distribution, which plays a prominent role as the universal limit distribution in a large class of random matrix and vector models. It is proposed that this distribution also universally determines the energy spectral density of black holes, which allows to construct a Krylov space for the time evolution of typical black hole states and …

Hy-DAT: A Tool to Address Hydropower Modelling Gaps Using Interdependency, Efficiency Curves, and Unit Dispatch Models
Dewei Wang, Bhaskar Mitra, Sameer Nekkalapu, Sohom Datta, Bibi Matthew, Rounak Meyur, Heng Wang, Slaven Kincic
https://arxiv.org/abs/2402.18017

Hy-DAT: A Tool to Address Hydropower Modelling Gaps Using Interdependency, Efficiency Curves, and Unit Dispatch Models
As the power system continues to be flooded with intermittent resources, it becomes more important to accurately assess the role of hydro and its impact on the power grid. While hydropower generation has been studied for decades, dependency of power generation on water availability and constraints in hydro operation are not well represented in power system models used in the planning and operation of large-scale interconnection studies. There are still multiple modeling gaps that need to be add…

PANGeA: Procedural Artificial Narrative using Generative AI for Turn-Based Video Games
Steph Buongiorno, Lawrence Jake Klinkert, Tanishq Chawla, Zixin Zhuang, Corey Clark
https://arxiv.org/abs/2404.19721

PANGeA: Procedural Artificial Narrative using Generative AI for Turn-Based Video Games
This research introduces Procedural Artificial Narrative using Generative AI (PANGeA), a structured approach for leveraging large language models (LLMs), guided by a game designer's high-level criteria, to generate narrative content for turn-based role-playing video games (RPGs). Distinct from prior applications of LLMs used for video game design, PANGeA innovates by not only generating game level data (which includes, but is not limited to, setting, key items, and non-playable characters (NPCs…

#AI & the #Web: Understanding and managing the impact of #MachineLearning models on the Web

Causal blind spots when using prediction models for treatment decisions
Nan van Geloven, Ruth H Keogh, Wouter van Amsterdam, Giovanni Cin\`a, Jesse H. Krijthe, Niels Peek, Kim Luijken, Sara Magliacane, Pawe{\l} Morzywo{\l}ek, Thijs van Ommen, Hein Putter, Matthew Sperrin, Junfeng Wang, Daniala L. Weir, Vanessa Didelez
https://ar…

Causal blind spots when using prediction models for treatment decisions
Prediction models are increasingly proposed for guiding treatment decisions, but most fail to address the special role of treatments, leading to inappropriate use. This paper highlights the limitations of using standard prediction models for treatment decision support. We identify 'causal blind spots' in three common approaches to handling treatments in prediction modelling and illustrate potential harmful consequences in several medical applications. We advocate for an extension of guidelines …

Proving correctness for SQL implementations of OCL constraints
Hoang Nguyen Phuoc Bao, Manuel Clavel
https://arxiv.org/abs/2403.18599 https://

Proving correctness for SQL implementations of OCL constraints
In the context of the model-driven development of data-centric applications, OCL constraints play a major role in adding precision to the source models (e.g., data models and security models). Several code-generators have been proposed to bridge the gap between source models with OCL constraints and their corresponding database implementations. However, the database queries produced by these code-generators are significantly less efficient -- from the point of view of execution-time performance…

This https://arxiv.org/abs/2402.13717 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent
Large Language Models (LLMs) have revolutionized open-domain dialogue agents but encounter challenges in multi-character role-playing (MCRP) scenarios. To address the issue, we present Neeko, an innovative framework designed for efficient multiple characters imitation. Unlike existing methods, Neeko employs a dynamic low-rank adapter (LoRA) strategy, enabling it to adapt seamlessly to diverse characters. Our framework breaks down the role-playing process into agent pre-training, multiple charac…

Sentiment Analysis of Citations in Scientific Articles Using ChatGPT: Identifying Potential Biases and Conflicts of Interest
Walid Hariri
https://arxiv.org/abs/2404.01800

Sentiment Analysis of Citations in Scientific Articles Using ChatGPT: Identifying Potential Biases and Conflicts of Interest
Scientific articles play a crucial role in advancing knowledge and informing research directions. One key aspect of evaluating scientific articles is the analysis of citations, which provides insights into the impact and reception of the cited works. This article introduces the innovative use of large language models, particularly ChatGPT, for comprehensive sentiment analysis of citations within scientific articles. By leveraging advanced natural language processing (NLP) techniques, ChatGPT ca…

The Limited Role of the Streaming Instability During Moon and Exomoon Formation
Miki Nakajima, Jeremy Atkins, Jacob B. Simon, Alice C. Quillen
https://arxiv.org/abs/2404.18145

The Limited Role of the Streaming Instability During Moon and Exomoon Formation
It is generally accepted that the Moon accreted from the disk formed by an impact between the proto-Earth and impactor, but its details are highly debated. Some models suggest that a Mars-sized impactor formed a silicate melt-rich (vapor-poor) disk around Earth, whereas other models suggest that a highly energetic impact produced a silicate vapor-rich disk. Such a vapor-rich disk, however, may not be suitable for the Moon formation, because moonlets, building blocks of the Moon, of 100 m-100 km…

The Future of Primordial Black Holes: Open Questions and Roadmap
Antonio Riotto, Joe Silk
https://arxiv.org/abs/2403.02907 https://ar…

The Future of Primordial Black Holes: Open Questions and Roadmap
We discuss some of the the open questions and the roadmap in the physics of primordial black holes. Black holes are the only dark matter candidate that is known to actually exit. Their conjectured primordial role is admittedly based on hypothesis rather than fact, most straightforwardly as a simple extension to the standard models of inflation, or even, in homage to quantum physics, more controversially via a slowing-down of Hawking evaporation. Regardless of one's stance on the theoretical bas…

This https://arxiv.org/abs/2310.15831 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

A Comparative Study of Variational Autoencoders, Normalizing Flows, and Score-based Diffusion Models for Electrical Impedance Tomography
Electrical Impedance Tomography (EIT) is a widely employed imaging technique in industrial inspection, geophysical prospecting, and medical imaging. However, the inherent nonlinearity and ill-posedness of EIT image reconstruction present challenges for classical regularization techniques, such as the critical selection of regularization terms and the lack of prior knowledge. Deep generative models (DGMs) have been shown to play a crucial role in learning implicit regularizers and prior knowledg…

Irreversibility of mesoscopic processes with hydrodynamic interactions
Biswajit Das, Sreekanth K Manikandan, Shuvojit Paul, Avijit Kundu, Supriya Krishnamurthy, Ayan Banerjee
https://arxiv.org/abs/2405.00800

Irreversibility of mesoscopic processes with hydrodynamic interactions
Microscopic colloidal particles are often used as probes to study the non-equilibrium activity of living matter or other complex systems. In many of these contexts hydrodynamic interactions between the probe particle and the system of interest play an important role. However little is known about what effect such interactions could have on the overall non-equilibrium characteristics of the system of interest. In this paper, we study two simple models experimentally and theoretically, which demo…

Disentangling representations of retinal images with generative models
Sarah M\"uller, Lisa M. Koch, Hendrik P. A. Lensch, Philipp Berens
https://arxiv.org/abs/2402.19186

Disentangling representations of retinal images with generative models
Retinal fundus images play a crucial role in the early detection of eye diseases and, using deep learning approaches, recent studies have even demonstrated their potential for detecting cardiovascular risk factors and neurological disorders. However, the impact of technical factors on these images can pose challenges for reliable AI applications in ophthalmology. For example, large fundus cohorts are often confounded by factors like camera type, image quality or illumination level, bearing the …

Exergetic Port-Hamiltonian Systems for Multibody Dynamics
Markus Lohmayer, Giuseppe Capobianco, Sigrid Leyendecker
https://arxiv.org/abs/2402.18095 https:/…

Exergetic Port-Hamiltonian Systems for Multibody Dynamics
Multibody dynamics simulation plays an important role in various fields, including mechanical engineering, robotics, and biomechanics. Setting up computational models however becomes increasingly challenging as systems grow in size and complexity. Especially the consistent combination of models across different physical domains usually demands a lot of attention. This motivates us to study formal languages for compositional modeling of multiphysical systems. This article shows how multibody sys…

Applying the starquake model to study the formation of elastic mountains on spinning neutron stars
Yashaswi Gangwar, David Ian Jones
https://arxiv.org/abs/2405.00553

Applying the starquake model to study the formation of elastic mountains on spinning neutron stars
When a neutron star is spun-up or spun-down, the changing strains in its solid elastic crust can give rise to sudden fractures known as starquakes. Early interest in starquakes focused on their possible connection to pulsar glitches. While modern glitch models rely on pinned superfluid vorticity rather than crustal fracture, starquakes may nevertheless play a role in the glitch mechanism. Recently, there has been interest in the issue of starquakes resulting in non-axisymmetric shape changes, p…

Signatures of magnetic braking in Class 0 protostars ? Exploring the gas kinematics in magnetized models of low-mass star formation
N. A\~nez-Lopez, U. Lebreuilly, A. Maury, P. Hennebelle
https://arxiv.org/abs/2403.18009

Signatures of magnetic braking in Class 0 protostars ? Exploring the gas kinematics in magnetized models of low-mass star formation
Only indirect evidence of the role of magnetic braking in regulating gravitational collapse and the formation of circumstellar disks was found from observational work, such as compact disk sizes and the launching of high-velocity collimated protostellar jets. More direct tests of the magnetic braking shaping the angular momentum (AM) of the gas in Class 0 protostars are crucially needed. In the present work we have used non-ideal MHD models of protostellar collapse and synthetic observations of…

"Training Data for the Price of a Sandwich – Common Crawl’s Impact on Generative AI "
https://foundation.mozilla.org/de/research/library/generative-ai-training-data/common-crawl/

Training Data for the Price of a Sandwich: Common Crawl’s Impact on Generative AI
Mozilla research finds that Common Crawl's outsized role in the generative AI boom has improved transparency and competition, but is also contributing to biased and opaque generative AI models.

Parity doublet model for baryon octets: ground states saturated by good diquarks and the role of bad diquarks for excited states
Bikai Gao, Toru Kojo, Masayasu Harada
https://arxiv.org/abs/2403.18214

Parity doublet model for baryon octets: ground states saturated by good diquarks and the role of bad diquarks for excited states
Parity doublet model is an effective chiral model that includes the chiral variant and invariant masses of baryons. The chiral invariant mass has large impacts on the density dependence of models which can be constrained by neutron star observations. In the previous work, models of two-flavors have been considered up to a few times nuclear saturation density, but in such dense region it is also necessary to consider hyperons. With the chiral invariant masses baryons can stay massive in extreme …

MambaStock: Selective state space model for stock prediction
Zhuangwei Shi
https://arxiv.org/abs/2402.18959 https://arxiv.org/pdf/240…

MambaStock: Selective state space model for stock prediction
The stock market plays a pivotal role in economic development, yet its intricate volatility poses challenges for investors. Consequently, research and accurate predictions of stock price movements are crucial for mitigating risks. Traditional time series models fall short in capturing nonlinearity, leading to unsatisfactory stock predictions. This limitation has spurred the widespread adoption of neural networks for stock prediction, owing to their robust nonlinear generalization capabilities. …

Grant O'Brien and Alley Beardslay were role models for me growing up — I think they should know that :blobcatmeltlove:

An in-depth look at Common Crawl, the 9.5PB web crawl archive dating back to 2008 run by a small nonprofit, its role in generative AI, its dataset, and more (Mozilla Foundation)
https://foundation.mozilla.org/en/research/library/generat…

Training Data for the Price of a Sandwich: Common Crawl’s Impact on Generative AI
Mozilla research finds that Common Crawl's outsized role in the generative AI boom has improved transparency and competition, but is also contributing to biased and opaque generative AI models.

Spyx: A Library for Just-In-Time Compiled Optimization of Spiking Neural Networks
Kade M. Heckel, Thomas Nowotny
https://arxiv.org/abs/2402.18994 https://<…

Spyx: A Library for Just-In-Time Compiled Optimization of Spiking Neural Networks
As the role of artificial intelligence becomes increasingly pivotal in modern society, the efficient training and deployment of deep neural networks have emerged as critical areas of focus. Recent advancements in attention-based large neural architectures have spurred the development of AI accelerators, facilitating the training of extensive, multi-billion parameter models. Despite their effectiveness, these powerful networks often incur high execution costs in production environments. Neuromor…

This https://arxiv.org/abs/2401.08052 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Multi-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarization
Audio-visual learning has demonstrated promising results in many classical speech tasks (e.g., speech separation, automatic speech recognition, wake-word spotting). We believe that introducing visual modality will also benefit speaker diarization. To date, Target-Speaker Voice Activity Detection (TS-VAD) plays an important role in highly accurate speaker diarization. However, previous TS-VAD models take audio features and utilize the speaker's acoustic footprint to distinguish his or her person…

Retrieval-Oriented Knowledge for Click-Through Rate Prediction
Huanshuo Liu, Bo Chen, Menghui Zhu, Jianghao Lin, Jiarui Qin, Yang Yang, Hao Zhang, Ruiming Tang
https://arxiv.org/abs/2404.18304

Retrieval-Oriented Knowledge for Click-Through Rate Prediction
Click-through rate (CTR) prediction plays an important role in personalized recommendations. Recently, sample-level retrieval-based models (e.g., RIM) have achieved remarkable performance by retrieving and aggregating relevant samples. However, their inefficiency at the inference stage makes them impractical for industrial applications. To overcome this issue, this paper proposes a universal plug-and-play Retrieval-Oriented Knowledge (ROK) framework. Specifically, a knowledge base, consisting o…

This https://arxiv.org/abs/2307.10811 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

"It Felt Like Having a Second Mind": Investigating Human-AI Co-creativity in Prewriting with Large Language Models
Prewriting is the process of discovering and developing ideas before a first draft, which requires divergent thinking and often implies unstructured strategies such as diagramming, outlining, free-writing, etc. Although large language models (LLMs) have been demonstrated to be useful for a variety of tasks including creative writing, little is known about how users would collaborate with LLMs to support prewriting. The preferred collaborative role and initiative of LLMs during such a creativity…

This https://arxiv.org/abs/2402.00097 has been replaced.
link: https://scholar.google.com/scholar?q=a

Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM
Testing plays a pivotal role in ensuring software quality, yet conventional Search Based Software Testing (SBST) methods often struggle with complex software units, achieving suboptimal test coverage. Recent works using large language models (LLMs) for test generation have focused on improving generation quality through optimizing the test generation context and correcting errors in model outputs, but use fixed prompting strategies that prompt the model to generate tests without additional guid…

Inline AI: Open-source Deep Learning Inference for Cardiac MR
Hui Xue, Rhodri H Davies, James Howard, Hunain Shiwani, Azaan Rehman, Iain Pierce, Henry Procter, Marianna Fontana, James C Moon, Eylem Levelt, Peter Kellman
https://arxiv.org/abs/2404.02384

Inline AI: Open-source Deep Learning Inference for Cardiac MR
Cardiac Magnetic Resonance (CMR) is established as a non-invasive imaging technique for evaluation of heart function, anatomy, and myocardial tissue characterization. Quantitative biomarkers are central for diagnosis and management of heart disease. Deep learning (DL) is playing an ever more important role in extracting these quantitative measures from CMR images. While many researchers have reported promising results in training and evaluating models, model deployment into the imaging workflow…

Assessment of physical schemes for WRF model in convection-permitting mode over southern Iberian Peninsula
Feliciano Solano-Far\'ias, Matilde Garc\'ia-Valdecasas Ojeda, David Donaire-Monta\~no, Juan Jos\'e Rosa-C\'anovas, Yolanda Castro-Diez, Maria Jes\'us Esteban-Parra, Sonia Raquel G\'amiz-Fortis
https://

Assessment of physical schemes for WRF model in convection-permitting mode over southern Iberian Peninsula
Convection-permitting models (CPMs) enable the representation of meteorological variables at horizontal high resolution spatial scales (higher than 4 km), where convection plays a significant role. Physical schemes need to be evaluated considering factors in the studied region such as orography and climate variability. This study investigates the sensitivity of the WRF model as CPM to the use of different physics schemes on Andalusia, a complex orography region in southern Iberian Peninsula (IP…

Text Role Classification in Scientific Charts Using Multimodal Transformers
Hye Jin Kim, Nicolas Lell, Ansgar Scherp
https://arxiv.org/abs/2402.14579 https…

Text Role Classification in Scientific Charts Using Multimodal Transformers
Text role classification involves classifying the semantic role of textual elements within scientific charts. For this task, we propose to finetune two pretrained multimodal document layout analysis models, LayoutLMv3 and UDOP, on chart datasets. The transformers utilize the three modalities of text, image, and layout as input. We further investigate whether data augmentation and balancing methods help the performance of the models. The models are evaluated on various chart datasets, and result…

Big news: Evidence for #Menopause as a Sex-Specific Risk Factor for Glaucoma
“We also highlight preclinical studies that demonstrate larger vision and RGC (retinal ganglion cells) loss following surgical menopause and how estrogen is protective in models of RGC injury.”

Evidence for Menopause as a Sex-Specific Risk Factor for Glaucoma
Glaucoma is a leading cause of irreversible blindness worldwide and is characterized by progressive loss of visual function and retinal ganglion cells (RGC). Current epidemiological, clinical, and basic science evidence suggest that estrogen plays a role ...

Causal blind spots when using prediction models for treatment decisions
Nan van Geloven, Ruth H Keogh, Wouter van Amsterdam, Giovanni Cin\`a, Jesse H. Krijthe, Niels Peek, Kim Luijken, Sara Magliacane, Pawe{\l} Morzywo{\l}ek, Thijs van Ommen, Hein Putter, Matthew Sperrin, Junfeng Wang, Daniala L. Weir, Vanessa Didelez
https://ar…

Causal blind spots when using prediction models for treatment decisions
Prediction models are increasingly proposed for guiding treatment decisions, but most fail to address the special role of treatments, leading to inappropriate use. This paper highlights the limitations of using standard prediction models for treatment decision support. We identify 'causal blind spots' in three common approaches to handling treatments in prediction modelling and illustrate potential harmful consequences in several medical applications. We advocate for an extension of guidelines …

Inefficient star formation in high Mach number environments. II. Numerical simulations and comparison with analytical models
No\'e Brucy, Patrick Hennebelle, Tine Colman, Ralf S. Klessen, Corentin Le Yhuelic
https://arxiv.org/abs/2404.17374

Inefficient star formation in high Mach number environments. II. Numerical simulations and comparison with analytical models
Predicting the star formation rate (SFR) in galaxies is crucial to understand their evolution and morphology. To do so requires a fine understanding of how dense structures of gas are created and collapse. In that, turbulence and gravity play a major role. Within the gravo-turbulent framework, we assume that turbulence shapes the ISM, creating density fluctuations that, if gravitationally unstable, will collapse and form stars. The goal of this work is to quantify how different regimes of turbu…

This https://arxiv.org/abs/2403.17240 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

The Role of $n$-gram Smoothing in the Age of Neural Networks
For nearly three decades, language models derived from the $n$-gram assumption held the state of the art on the task. The key to their success lay in the application of various smoothing techniques that served to combat overfitting. However, when neural language models toppled $n$-gram models as the best performers, $n$-gram smoothing techniques became less relevant. Indeed, it would hardly be an understatement to suggest that the line of inquiry into $n$-gram smoothing techniques became dorman…

Towards a FAIR Documentation of Workflows and Models in Applied Mathematics
Marco Reidelbach, Bj\"orn Schembera, Marcus Weber
https://arxiv.org/abs/2403.17778

Towards a FAIR Documentation of Workflows and Models in Applied Mathematics
Modeling-Simulation-Optimization workflows play a fundamental role in applied mathematics. The Mathematical Research Data Initiative, MaRDI, responded to this by developing a FAIR and machine-interpretable template for a comprehensive documentation of such workflows. MaRDMO, a Plugin for the Research Data Management Organiser, enables scientists from diverse fields to document and publish their workflows on the MaRDI Portal seamlessly using the MaRDI template. Central to these workflows are mat…

Adaptive Testing Environment Generation for Connected and Automated Vehicles with Dense Reinforcement Learning
Jingxuan Yang, Ruoxuan Bai, Haoyuan Ji, Yi Zhang, Jianming Hu, Shuo Feng
https://arxiv.org/abs/2402.19275

Adaptive Testing Environment Generation for Connected and Automated Vehicles with Dense Reinforcement Learning
The assessment of safety performance plays a pivotal role in the development and deployment of connected and automated vehicles (CAVs). A common approach involves designing testing scenarios based on prior knowledge of CAVs (e.g., surrogate models), conducting tests in these scenarios, and subsequently evaluating CAVs' safety performances. However, substantial differences between CAVs and the prior knowledge can significantly diminish the evaluation efficiency. In response to this issue, existi…

Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks
Lorenzo Pes, Rick Luiken, Federico Corradi, Charlotte Frenkel
https://arxiv.org/abs/2404.19419

Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks
While the human brain efficiently adapts to new tasks from a continuous stream of information, neural network models struggle to learn from sequential information without catastrophically forgetting previously learned tasks. This limitation presents a significant hurdle in deploying edge devices in real-world scenarios where information is presented in an inherently sequential manner. Active dendrites of pyramidal neurons play an important role in the brain ability to learn new tasks incrementa…

The Emergence of Large Language Models in Static Analysis: A First Look through Micro-Benchmarks
Ashwin Prasad Shivarpatna Venkatesh, Samkutty Sabu, Amir M. Mir, Sofia Reis, Eric Bodden
https://arxiv.org/abs/2402.17679

The Emergence of Large Language Models in Static Analysis: A First Look through Micro-Benchmarks
The application of Large Language Models (LLMs) in software engineering, particularly in static analysis tasks, represents a paradigm shift in the field. In this paper, we investigate the role that current LLMs can play in improving callgraph analysis and type inference for Python programs. Using the PyCG, HeaderGen, and TypeEvalPy micro-benchmarks, we evaluate 26 LLMs, including OpenAI's GPT series and open-source models such as LLaMA. Our study reveals that LLMs show promising results in type…

Rethinking Annotator Simulation: Realistic Evaluation of Whole-Body PET Lesion Interactive Segmentation Methods
Zdravko Marinov, Moon Kim, Jens Kleesiek, Rainer Stiefelhagen
https://arxiv.org/abs/2404.01816

Rethinking Annotator Simulation: Realistic Evaluation of Whole-Body PET Lesion Interactive Segmentation Methods
Interactive segmentation plays a crucial role in accelerating the annotation, particularly in domains requiring specialized expertise such as nuclear medicine. For example, annotating lesions in whole-body Positron Emission Tomography (PET) images can require over an hour per volume. While previous works evaluate interactive segmentation models through either real user studies or simulated annotators, both approaches present challenges. Real user studies are expensive and often limited in scale…

Assessment of physical schemes for WRF model in convection-permitting mode over southern Iberian Peninsula
Feliciano Solano-Far\'ias, Matilde Garc\'ia-Valdecasas Ojeda, David Donaire-Monta\~no, Juan Jos\'e Rosa-C\'anovas, Yolanda Castro-Diez, Maria Jes\'us Esteban-Parra, Sonia Raquel G\'amiz-Fortis
https://

Assessment of physical schemes for WRF model in convection-permitting mode over southern Iberian Peninsula
Convection-permitting models (CPMs) enable the representation of meteorological variables at horizontal high resolution spatial scales (higher than 4 km), where convection plays a significant role. Physical schemes need to be evaluated considering factors in the studied region such as orography and climate variability. This study investigates the sensitivity of the WRF model as CPM to the use of different physics schemes on Andalusia, a complex orography region in southern Iberian Peninsula (IP…

This https://arxiv.org/abs/2402.15276 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Text2Pic Swift: Enhancing Long-Text to Image Retrieval for Large-Scale Libraries
Text-to-image retrieval plays a crucial role across various applications, including digital libraries, e-commerce platforms, and multimedia databases, by enabling the search for images using text queries. Despite the advancements in Multimodal Large Language Models (MLLMs), which offer leading-edge performance, their applicability in large-scale, varied, and ambiguous retrieval scenarios is constrained by significant computational demands and the generation of injective embeddings. This paper i…

This https://arxiv.org/abs/2404.14480 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hepp…

Holography for Sp(2$N_c$) Gauge Dynamics: from Composite Higgs to Technicolour
We study Sp(2$N_c$) gauge dynamics with two Dirac fermion flavours in the fundamental representation. These strongly coupled systems underlie some composite Higgs models with a global symmetry breaking pattern SU(4)$\rightarrow$Sp(4), leading to a light quartet of pseudo-Goldstone bosons that can play the role of the Higgs. Including four-fermion interactions can rotate the vacuum to a technicolour breaking pattern. Using gauge/gravity duality, we study the underlying gauge dynamics. Our model …

This https://arxiv.org/abs/2309.11599 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

The Role of Inclusion, Control, and Ownership in Workplace AI-Mediated Communication
Given large language models' (LLMs) increasing integration into workplace software, it is important to examine how biases in the models may impact workers. For example, stylistic biases in the language suggested by LLMs may cause feelings of alienation and result in increased labor for individuals or groups whose style does not match. We examine how such writer-style bias impacts inclusion, control, and ownership over the work when co-writing with LLMs. In an online experiment, participants wro…

This https://arxiv.org/abs/2402.01663 has been replaced.
link: https://scholar.google.com/scholar?q=a

Killer Apps: Low-Speed, Large-Scale AI Weapons
The accelerating advancements in Artificial Intelligence (AI) and Machine Learning (ML), highlighted by the development of cutting-edge Generative Pre-trained Transformer (GPT) models by organizations such as OpenAI, Meta, and Anthropic, present new challenges and opportunities in warfare and security. Much of the current focus is on AI's integration within weapons systems and its role in rapid decision-making in kinetic conflict. However, an equally important but often overlooked aspect is the…

Graph Machine Learning in the Era of Large Language Models (LLMs)
Wenqi Fan, Shijie Wang, Jiani Huang, Zhikai Chen, Yu Song, Wenzhuo Tang, Haitao Mao, Hui Liu, Xiaorui Liu, Dawei Yin, Qing Li
https://arxiv.org/abs/2404.14928

Graph Machine Learning in the Era of Large Language Models (LLMs)
Graphs play an important role in representing complex relationships in various domains like social networks, knowledge graphs, and molecular discovery. With the advent of deep learning, Graph Neural Networks (GNNs) have emerged as a cornerstone in Graph Machine Learning (Graph ML), facilitating the representation and processing of graph structures. Recently, LLMs have demonstrated unprecedented capabilities in language tasks and are widely adopted in a variety of applications such as computer v…

Can MAG be an EFT? Radiative Stability and Ghost Resurgence in Massive Vector Models
Carlo Marzo
https://arxiv.org/abs/2403.15003 https://

Can MAG be an EFT? Radiative Stability and Ghost Resurgence in Massive Vector Models
We explore the one-loop structure of some ghost and tachyon-free vector theories to illustrate the role of structural constraints in their interactions, even in the absence of gauge symmetries. While the presence of explicit soft-breaking terms might suggest otherwise, we illustrate how the hopes of casting a model within the predictive frame of effective field methods require a gauge-like treatment of their interactions.

This https://arxiv.org/abs/2402.14846 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Stick to your Role! Context-dependence and Stability of Personal Values Expression in Large Language Models
The standard way to study Large Language Models (LLMs) with benchmarks or psychology questionnaires is to provide many different queries from similar minimal contexts (e.g. multiple choice questions). However, due to LLMs' highly context-dependent nature, conclusions from such minimal-context evaluations may be little informative about the model's behavior in deployment (where it will be exposed to many new contexts). We argue that context-dependence (specifically, value stability) should be st…

Rethinking Annotator Simulation: Realistic Evaluation of Whole-Body PET Lesion Interactive Segmentation Methods
Zdravko Marinov, Moon Kim, Jens Kleesiek, Rainer Stiefelhagen
https://arxiv.org/abs/2404.01816

Rethinking Annotator Simulation: Realistic Evaluation of Whole-Body PET Lesion Interactive Segmentation Methods
Interactive segmentation plays a crucial role in accelerating the annotation, particularly in domains requiring specialized expertise such as nuclear medicine. For example, annotating lesions in whole-body Positron Emission Tomography (PET) images can require over an hour per volume. While previous works evaluate interactive segmentation models through either real user studies or simulated annotators, both approaches present challenges. Real user studies are expensive and often limited in scale…

Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks
Lorenzo Pes, Rick Luiken, Federico Corradi, Charlotte Frenkel
https://arxiv.org/abs/2404.19419

Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks
While the human brain efficiently adapts to new tasks from a continuous stream of information, neural network models struggle to learn from sequential information without catastrophically forgetting previously learned tasks. This limitation presents a significant hurdle in deploying edge devices in real-world scenarios where information is presented in an inherently sequential manner. Active dendrites of pyramidal neurons play an important role in the brain ability to learn new tasks incrementa…

Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts
Lotem Golany, Filippo Galgani, Maya Mamo, Nimrod Parasol, Omer Vandsburger, Nadav Bar, Ido Dagan
https://arxiv.org/abs/2405.01121

Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts
Existing methods for creating source-grounded information-seeking dialog datasets are often costly and hard to implement due to their sole reliance on human annotators. We propose combining large language models (LLMs) prompting with human expertise for more efficient and reliable data generation. Instead of the labor-intensive Wizard-of-Oz (WOZ) method, where two annotators generate a dialog from scratch, role-playing agent and user, we use LLM generation to simulate the two roles. Annotators …

Characterizing Role Models in Software Practitioners' Career: An Interview Study
Mary S\'anchez-Gord\'on, Ricardo Colomo-Palacios, Alex Sanchez Gordon
https://arxiv.org/abs/2402.09925

Characterizing Role Models in Software Practitioners' Career: An Interview Study
A role model is a person who serves as an example for others to follow, especially in terms of values, behavior, achievements, and personal characteristics. In this paper, authors study how role models influence software practitioners careers, an aspect not studied in the literature before. By means of this study, authors aim to understand if there are any salient role model archetypes and what characteristics are valued by participants in their role models. To do so, authors use a thematic cod…

Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations
Carlos Jose Xavier Cruz
https://arxiv.org/abs/2403.07769

Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations
This article explores the dynamic influence of computational entities based on multi-agent systems theory (SMA) combined with large language models (LLM), which are characterized by their ability to simulate complex human interactions, as a possibility to revolutionize human user interaction from the use of specialized artificial agents to support everything from operational organizational processes to strategic decision making based on applied knowledge and human orchestration. Previous invest…

Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation
Shicheng Xu, Liang Pang, Mo Yu, Fandong Meng, Huawei Shen, Xueqi Cheng, Jie Zhou
https://arxiv.org/abs/2402.18150

Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating additional information from retrieval. However, studies have shown that LLMs still face challenges in effectively using the retrieved information, even ignoring it or being misled by it. The key reason is that the training of LLMs does not clearly make LLMs learn how to utilize input retrieved texts with varied quality. In this paper, we propose a novel perspective that considers the role of LLMs in RAG …

Equivalence: An analysis of artists' roles with Image Generative AI from Conceptual Art perspective through an interactive installation design practice
Yixuan Li, Dan C. Baciu, Marcos Novak, George Legrady
https://arxiv.org/abs/2404.18385

Equivalence: An analysis of artists' roles with Image Generative AI from Conceptual Art perspective through an interactive installation design practice
Over the past year, the emergence of advanced text-to-image Generative AI models has significantly impacted the art world, challenging traditional notions of creativity and the role of artists. This study explores how artists interact with these technologies, using a 5P model (Purpose, People, Process, Product, and Press) based on Rhodes' creativity framework to compare the artistic processes behind Conceptual Art and Image Generative AI. To exemplify this framework, a practical case study titl…

Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations
Carlos Jose Xavier Cruz
https://arxiv.org/abs/2403.07769

Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations
This article explores the dynamic influence of computational entities based on multi-agent systems theory (SMA) combined with large language models (LLM), which are characterized by their ability to simulate complex human interactions, as a possibility to revolutionize human user interaction from the use of specialized artificial agents to support everything from operational organizational processes to strategic decision making based on applied knowledge and human orchestration. Previous invest…

This https://arxiv.org/abs/2404.12096 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

LongEmbed: Extending Embedding Models for Long Context Retrieval
Embedding models play a pivot role in modern NLP applications such as IR and RAG. While the context limit of LLMs has been pushed beyond 1 million tokens, embedding models are still confined to a narrow context window not exceeding 8k tokens, refrained from application scenarios requiring long inputs such as legal contracts. This paper explores context window extension of existing embedding models, pushing the limit to 32k without requiring additional training. First, we examine the performance…

This https://arxiv.org/abs/2403.15360 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series
Transformers have widely adopted attention networks for sequence mixing and MLPs for channel mixing, playing a pivotal role in achieving breakthroughs across domains. However, recent literature highlights issues with attention networks, including low inductive bias and quadratic complexity concerning input sequence length. State Space Models (SSMs) like S4 and others (Hippo, Global Convolutions, liquid S4, LRU, Mega, and Mamba), have emerged to address the above issues to help handle longer seq…

Brain Stroke Segmentation Using Deep Learning Models: A Comparative Study
Ahmed Soliman, Yousif Yousif, Ahmed Ibrahim, Yalda Zafari-Ghadim, Essam A. Rashed, Mohamed Mabrok
https://arxiv.org/abs/2403.17177

Brain Stroke Segmentation Using Deep Learning Models: A Comparative Study
Stroke segmentation plays a crucial role in the diagnosis and treatment of stroke patients by providing spatial information about affected brain regions and the extent of damage. Segmenting stroke lesions accurately is a challenging task, given that conventional manual techniques are time consuming and prone to errors. Recently, advanced deep models have been introduced for general medical image segmentation, demonstrating promising results that surpass many state of the art networks when evalu…

Towards behavioral consistency in heterogeneous modeling scenarios
Tim Kr\"auter
https://arxiv.org/abs/2404.12941 https://arxiv.…

Towards behavioral consistency in heterogeneous modeling scenarios
Behavioral models play an essential role in Model-driven engineering (MDE). Keeping inter-related behavioral models consistent is critical to use them successfully in MDE. However, consistency checking for behavioral models, especially in a heterogeneous scenario, is limited. We propose a methodology to integrate heterogeneous behavioral models to achieve consistency checking in broader scenarios. It is based on aligning the respective behavioral metamodels by defining possible inter-model rela…

This https://arxiv.org/abs/2404.13846 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Filtered Direct Preference Optimization
Reinforcement learning from human feedback (RLHF) plays a crucial role in aligning language models with human preferences. While the significance of dataset quality is generally recognized, explicit investigations into its impact within the RLHF framework, to our knowledge, have been limited. This paper addresses the issue of text quality within the preference dataset by focusing on Direct Preference Optimization (DPO), an increasingly adopted reward-model-free RLHF method. We confirm that text…

This https://arxiv.org/abs/2403.05574 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

HealMe: Harnessing Cognitive Reframing in Large Language Models for Psychotherapy
Large Language Models (LLMs) can play a vital role in psychotherapy by adeptly handling the crucial task of cognitive reframing and overcoming challenges such as shame, distrust, therapist skill variability, and resource scarcity. Previous LLMs in cognitive reframing mainly converted negative emotions to positive ones, but these approaches have limited efficacy, often not promoting clients' self-discovery of alternative perspectives. In this paper, we unveil the Helping and Empowering through A…

LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation
Ke Guo, Zhenwei Miao, Wei Jing, Weiwei Liu, Weizi Li, Dayang Hao, Jia Pan
https://arxiv.org/abs/2403.17601

LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation
Microscopic traffic simulation plays a crucial role in transportation engineering by providing insights into individual vehicle behavior and overall traffic flow. However, creating a realistic simulator that accurately replicates human driving behaviors in various traffic conditions presents significant challenges. Traditional simulators relying on heuristic models often fail to deliver accurate simulations due to the complexity of real-world traffic environments. Due to the covariate shift iss…

Modular Blind Video Quality Assessment
Wen Wen, Mu Li, Yabin Zhang, Yiting Liao, Junlin Li, Li Zhang, Kede Ma
https://arxiv.org/abs/2402.19276 https://

Modular Blind Video Quality Assessment
Blind video quality assessment (BVQA) plays a pivotal role in evaluating and improving the viewing experience of end-users across a wide range of video-based platforms and services. Contemporary deep learning-based models primarily analyze the video content in its aggressively downsampled format, while being blind to the impact of actual spatial resolution and frame rate on video quality. In this paper, we propose a modular BVQA model, and a method of training it to improve its modularity. Spec…

This https://arxiv.org/abs/2402.13116 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

A Survey on Knowledge Distillation of Large Language Models
This survey presents an in-depth exploration of knowledge distillation (KD) techniques within the realm of Large Language Models (LLMs), spotlighting the pivotal role of KD in transferring sophisticated capabilities from proprietary giants such as GPT-4 to accessible, open-source models like LLaMA and Mistral. Amidst the evolving AI landscape, this work elucidates the critical disparities between proprietary and open-source LLMs, demonstrating how KD serves as an essential conduit for imbuing t…

This https://arxiv.org/abs/2404.10357 has been replaced.
link: https://scholar.google.com/scholar?q=a

Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models
Vision-Language Models (VLMs), such as CLIP, play a foundational role in various cross-modal applications. To fully leverage VLMs' potential in adapting to downstream tasks, context optimization methods like Prompt Tuning are essential. However, one key limitation is the lack of diversity in prompt templates, whether they are hand-crafted or learned through additional modules. This limitation restricts the capabilities of pretrained VLMs and can result in incorrect predictions in downstream tas…

Automated Generation of High-Quality Medical Simulation Scenarios Through Integration of Semi-Structured Data and Large Language Models
Scott Sumpter
https://arxiv.org/abs/2404.19713 https://arxiv.org/pdf/2404.19713
arXiv:2404.19713v1 Announce Type: new
Abstract: This study introduces a transformative framework for medical education by integrating semi-structured data with Large Language Models (LLMs), primarily OpenAIs ChatGPT3.5, to automate the creation of medical simulation scenarios. Traditionally, developing these scenarios was a time-intensive process with limited flexibility to meet diverse educational needs. The proposed approach utilizes AI to efficiently generate detailed, clinically relevant scenarios that are tailored to specific educational objectives. This innovation has significantly reduced the time and resources required for scenario development, allowing for a broader variety of simulations. Preliminary feedback from educators and learners has shown enhanced engagement and improved knowledge acquisition, confirming the effectiveness of this AI-enhanced methodology in simulation-based learning. The integration of structured data with LLMs not only streamlines the creation process but also offers a scalable, dynamic solution that could revolutionize medical training, highlighting the critical role of AI in advancing educational outcomes and patient care standards.

Just Like Me: The Role of Opinions and Personal Experiences in The Perception of Explanations in Subjective Decision-Making
Sharon Ferguson, Paula Akemi Aoyagui, Young-Ho Kim, Anastasia Kuzminykh
https://arxiv.org/abs/2404.12558

Just Like Me: The Role of Opinions and Personal Experiences in The Perception of Explanations in Subjective Decision-Making
As large language models (LLMs) advance to produce human-like arguments in some contexts, the number of settings applicable for human-AI collaboration broadens. Specifically, we focus on subjective decision-making, where a decision is contextual, open to interpretation, and based on one's beliefs and values. In such cases, having multiple arguments and perspectives might be particularly useful for the decision-maker. Using subtle sexism online as an understudied application of subjective decisi…

Multi-role Consensus through LLMs Discussions for Vulnerability Detection
Zhenyu Mao, Jialong Li, Munan Li, Kenji Tei
https://arxiv.org/abs/2403.14274 http…

Multi-role Consensus through LLMs Discussions for Vulnerability Detection
Recent advancements in large language models (LLMs) have highlighted the potential for vulnerability detection, a crucial component of software quality assurance. Despite this progress, most studies have been limited to the perspective of a single role, usually testers, lacking diverse viewpoints from different roles in a typical software development life-cycle, including both developers and testers. To this end, this paper introduces an approach to employ LLMs to act as different roles to simu…

This https://arxiv.org/abs/2404.10357 has been replaced.
link: https://scholar.google.com/scholar?q=a

Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models
Vision-Language Models (VLMs), such as CLIP, play a foundational role in various cross-modal applications. To fully leverage VLMs' potential in adapting to downstream tasks, context optimization methods like Prompt Tuning are essential. However, one key limitation is the lack of diversity in prompt templates, whether they are hand-crafted or learned through additional modules. This limitation restricts the capabilities of pretrained VLMs and can result in incorrect predictions in downstream tas…

Annotated Biomedical Video Generation using Denoising Diffusion Probabilistic Models and Flow Fields
R\"uveyda Yilmaz, Dennis Eschweiler, Johannes Stegmaier
https://arxiv.org/abs/2403.17808

Annotated Biomedical Video Generation using Denoising Diffusion Probabilistic Models and Flow Fields
The segmentation and tracking of living cells play a vital role within the biomedical domain, particularly in cancer research, drug development, and developmental biology. These are usually tedious and time-consuming tasks that are traditionally done by biomedical experts. Recently, to automatize these processes, deep learning based segmentation and tracking methods have been proposed. These methods require large-scale datasets and their full potential is constrained by the scarcity of annotate…

This https://arxiv.org/abs/2403.13679 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

RoleInteract: Evaluating the Social Interaction of Role-Playing Agents
Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing conversational agents that mimic diverse characters and human behaviors. While prior research has predominantly focused on enhancing the conversational capability, role-specific knowledge, and stylistic attributes of these agents, there has been a noticeable gap in assessing their social intelligence. In this paper, we introduce RoleInteract, the first benchmark designed to sys…

Learning or Self-aligning? Rethinking Instruction Fine-tuning
Mengjie Ren, Boxi Cao, Hongyu Lin, Liu Cao, Xianpei Han, Ke Zeng, Guanglu Wan, Xunliang Cai, Le Sun
https://arxiv.org/abs/2402.18243

Learning or Self-aligning? Rethinking Instruction Fine-tuning
Instruction Fine-tuning~(IFT) is a critical phase in building large language models~(LLMs). Previous works mainly focus on the IFT's role in the transfer of behavioral norms and the learning of additional world knowledge. However, the understanding of the underlying mechanisms of IFT remains significantly limited. In this paper, we design a knowledge intervention framework to decouple the potential underlying factors of IFT, thereby enabling individual analysis of different factors. Surprisingl…

From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models
Kung-Hsiang Huang, Hou Pong Chan, Yi R. Fung, Haoyi Qiu, Mingyang Zhou, Shafiq Joty, Shih-Fu Chang, Heng Ji
https://arxiv.org/abs/2403.12027

From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models
Data visualization in the form of charts plays a pivotal role in data analysis, offering critical insights and aiding in informed decision-making. Automatic chart understanding has witnessed significant advancements with the rise of large foundation models in recent years. Foundation models, such as large language models (LLMs), have revolutionized various natural language processing (NLP) tasks and are increasingly being applied to chart understanding tasks. This survey paper provides a compre…

This https://arxiv.org/abs/2307.05052 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps
We investigate the role of various demonstration components in the in-context learning (ICL) performance of large language models (LLMs). Specifically, we explore the impacts of ground-truth labels, input distribution, and complementary explanations, particularly when these are altered or perturbed. We build on previous work, which offers mixed findings on how these elements influence ICL. To probe these questions, we employ explainable NLP (XNLP) methods and utilize saliency maps of contrastiv…

This https://arxiv.org/abs/2403.13679 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

RoleInteract: Evaluating the Social Interaction of Role-Playing Agents
Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing conversational agents that mimic diverse characters and human behaviors. While prior research has predominantly focused on enhancing the conversational capability, role-specific knowledge, and stylistic attributes of these agents, there has been a noticeable gap in assessing their social intelligence. In this paper, we introduce RoleInteract, the first benchmark designed to sys…

Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering
Hongda Sun, Yuxuan Liu, Chengwei Wu, Haiyu Yan, Cheng Tai, Xin Gao, Shuo Shang, Rui Yan
https://arxiv.org/abs/2403.05217

Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering
Open-domain question answering (ODQA) has emerged as a pivotal research spotlight in information systems. Existing methods follow two main paradigms to collect evidence: (1) The \textit{retrieve-then-read} paradigm retrieves pertinent documents from an external corpus; and (2) the \textit{generate-then-read} paradigm employs large language models (LLMs) to generate relevant documents. However, neither can fully address multifaceted requirements for evidence. To this end, we propose LLMQA, a gen…

Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering
Hongda Sun, Yuxuan Liu, Chengwei Wu, Haiyu Yan, Cheng Tai, Xin Gao, Shuo Shang, Rui Yan
https://arxiv.org/abs/2403.05217

Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering
Open-domain question answering (ODQA) has emerged as a pivotal research spotlight in information systems. Existing methods follow two main paradigms to collect evidence: (1) The \textit{retrieve-then-read} paradigm retrieves pertinent documents from an external corpus; and (2) the \textit{generate-then-read} paradigm employs large language models (LLMs) to generate relevant documents. However, neither can fully address multifaceted requirements for evidence. To this end, we propose LLMQA, a gen…