Tootfinder

An Empirical Study of Training ID-Agnostic Multi-modal Sequential Recommenders
Youhua Li, Hanwen Du, Yongxin Ni, Yuanqi He, Junchen Fu, Xiangyan Liu, Qi Guo
https://arxiv.org/abs/2403.17372

An Empirical Study of Training ID-Agnostic Multi-modal Sequential Recommenders
Sequential Recommendation (SR) aims to predict future user-item interactions based on historical interactions. While many SR approaches concentrate on user IDs and item IDs, the human perception of the world through multi-modal signals, like text and images, has inspired researchers to delve into constructing SR from multi-modal information without using IDs. However, the complexity of multi-modal learning manifests in diverse feature extractors, fusion methods, and pre-trained models. Conseque…

This https://arxiv.org/abs/2311.09393 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

Taypsi: Static Enforcement of Privacy Policies for Policy-Agnostic Oblivious Computation
Secure multiparty computation (MPC) techniques enable multiple parties to compute joint functions over their private data without sharing that data to other parties, typically by employing powerful cryptographic protocols to protect individual's data. One challenge when writing such functions is that most MPC languages force users to intermix programmatic and privacy concerns in a single application, making it difficult to change or audit a program's underlying privacy policy. Existing policy-a…

Using Stratified Sampling to Improve LIME Image Explanations
Muhammad Rashid, Elvio G. Amparore, Enrico Ferrari, Damiano Verda
https://arxiv.org/abs/2403.17742

Using Stratified Sampling to Improve LIME Image Explanations
We investigate the use of a stratified sampling approach for LIME Image, a popular model-agnostic explainable AI method for computer vision tasks, in order to reduce the artifacts generated by typical Monte Carlo sampling. Such artifacts are due to the undersampling of the dependent variable in the synthetic neighborhood around the image being explained, which may result in inadequate explanations due to the impossibility of fitting a linear regressor on the sampled data. We then highlight a co…

Leveraging Pretrained Latent Representations for Few-Shot Imitation Learning on a Dexterous Robotic Hand
Davide Liconti, Yasunori Toshimitsu, Robert Katzschmann
https://arxiv.org/abs/2404.16483

Leveraging Pretrained Latent Representations for Few-Shot Imitation Learning on a Dexterous Robotic Hand
In the context of imitation learning applied to dexterous robotic hands, the high complexity of the systems makes learning complex manipulation tasks challenging. However, the numerous datasets depicting human hands in various different tasks could provide us with better knowledge regarding human hand motion. We propose a method to leverage multiple large-scale task-agnostic datasets to obtain latent representations that effectively encode motion subtrajectories that we included in a transforme…

This https://arxiv.org/abs/2306.13185 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
We study the cost of overfitting in noisy kernel ridge regression (KRR), which we define as the ratio between the test error of the interpolating ridgeless model and the test error of the optimally-tuned model. We take an "agnostic" view in the following sense: we consider the cost as a function of sample size for any target function, even if the sample size is not large enough for consistency or the target is outside the RKHS. We analyze the cost of overfitting under a Gaussian universality an…

Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
Johnathan Xie, Yoonho Lee, Annie S. Chen, Chelsea Finn
https://arxiv.org/abs/2402.14789

Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-trivial because the specifics of existing methods are tailored to each domain, such as domain-specific augmentations which reflect the invariances in the target task. While masked modeling is promising as a domain-agnostic framework for self-supervised learning because it does not…

Towards Model-Driven Dashboard Generation for Systems-of-Systems
Maria Teresa Rossi, Alessandro Tundo, Leonardo Mariani
https://arxiv.org/abs/2402.15257 ht…

Towards Model-Driven Dashboard Generation for Systems-of-Systems
Configuring and evolving dashboards in complex and large-scale Systems-of-Systems (SoS) can be an expensive and cumbersome task due to the many Key Performance Indicators (KPIs) that are usually collected and have to be arranged in a number of visualizations. Unfortunately, setting up dashboards is still a largely manual and error-prone task requiring extensive human intervention. This short paper describes emerging results about the definition of a model-driven technology-agnostic approach t…

A study of the Inspiral-Merger-Ringdown Consistency Test with gravitational-wave signals from compact binaries in eccentric orbits
Md Arif Shaikh, Sajad A. Bhat, Shasvath J. Kapadia
https://arxiv.org/abs/2402.15110

A study of the Inspiral-Merger-Ringdown Consistency Test with gravitational-wave signals from compact binaries in eccentric orbits
The Inspiral Merger Ringdown Consistency Test (IMRCT) is one among a battery of tests of general relativity (GR) employed by the LIGO-Virgo-KAGRA (LVK) collaboration. It is used to search for deviations from GR in detected gravitational waves (GWs) from compact binary coalescences (CBCs) in a model-agnostic way. The test compares source parameter estimates extracted independently from the inspiral and post-inspiral portions of the CBC signals and, therefore, crucially relies on the accurate mod…

HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation
Changkun Liu, Shuai Chen, Yukun Zhao, Huajian Huang, Victor Prisacariu, Tristan Braud
https://arxiv.org/abs/2402.14371

HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation
Absolute Pose Regressors (APRs) directly estimate camera poses from monocular images, but their accuracy is unstable for different queries. Uncertainty-aware APRs provide uncertainty information on the estimated pose, alleviating the impact of these unreliable predictions. However, existing uncertainty modelling techniques are often coupled with a specific APR architecture, resulting in suboptimal performance compared to state-of-the-art (SOTA) APR methods. This work introduces a novel APR-agno…

This https://arxiv.org/abs/2301.07010 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hepe…

$Λ^+_\mathrm{c}$ polarimetry using the dominant hadronic mode
The polarimeter vector field for multibody decays of a spin-half baryon is introduced as a generalisation of the baryon asymmetry parameters. Using a recent amplitude analysis of the $Λ^+_\mathrm{c} \to p K^- π^+$ decay performed at the LHCb experiment, we compute the distribution of the kinematic-dependent polarimeter vector for this process in the space of Mandelstam variables to express the polarised decay rate in a model-agnostic form. The obtained representation can facilitate polarisati…

Statistical analysis and method to propagate the impact of measurement uncertainty on dynamic mode decomposition
P. Algikar, P. Sharma, M. Netto, L. Mili
https://arxiv.org/abs/2403.17318

Statistical analysis and method to propagate the impact of measurement uncertainty on dynamic mode decomposition
We apply random matrix theory to study the impact of measurement uncertainty on dynamic mode decomposition. Specifically, when the measurements follow a normal probability density function, we show how the moments of that density propagate through the dynamic mode decomposition. While we focus on the first and second moments, the analytical expressions we derive are general and can be extended to higher-order moments. Further, the proposed numerical method to propagate uncertainty is agnostic o…

This https://arxiv.org/abs/2306.13185 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
We study the cost of overfitting in noisy kernel ridge regression (KRR), which we define as the ratio between the test error of the interpolating ridgeless model and the test error of the optimally-tuned model. We take an "agnostic" view in the following sense: we consider the cost as a function of sample size for any target function, even if the sample size is not large enough for consistency or the target is outside the RKHS. We analyze the cost of overfitting under a Gaussian universality an…

Reversible Jump Attack to Textual Classifiers with Modification Reduction
Mingze Ni, Zhensu Sun, Wei Liu
https://arxiv.org/abs/2403.14731 https://

Reversible Jump Attack to Textual Classifiers with Modification Reduction
Recent studies on adversarial examples expose vulnerabilities of natural language processing (NLP) models. Existing techniques for generating adversarial examples are typically driven by deterministic hierarchical rules that are agnostic to the optimal adversarial examples, a strategy that often results in adversarial samples with a suboptimal balance between magnitudes of changes and attack successes. To this end, in this research we propose two algorithms, Reversible Jump Attack (RJA) and Met…

DistriFS: A Platform and User Agnostic Approach to File Distribution
Julian Boesch
https://arxiv.org/abs/2402.13387 https://arxiv.org…

DistriFS: A Platform and User Agnostic Approach to File Distribution
In an age where the distribution of information is crucial, current file sharing solutions suffer significant deficiencies. Popular systems such as Google Drive, torrenting and IPFS suffer issues with compatibility, accessibility and censorship. This paper introduces DistriFS, a novel decentralized approach tailored for efficient and large-scale distribution of files. The architecture of DistriFS is grounded in three foundational pillars: scalability, security, and seamless integration. The pro…

A look at Playtron, which raised a $10M seed to build a Linux-based, platform-agnostic gaming OS to replace Windows or SteamOS, starting with handheld consoles (Sean Hollister/The Verge)
https://www.theverge.com/24090470/playtron-gaming-os-linux-hand…

Playtron: the startup hoping to Steam Deck-ify the world
Exclusive: Playtron tells us about its ambitions to create an operating system specifically for PC gaming handhelds, following in footsteps of Steam Deck, Legion Go, and more.

Breaching the Bottleneck: Evolutionary Transition from Reward-Driven Learning to Reward-Agnostic Domain-Adapted Learning in Neuromodulated Neural Nets
Solvi Arnold, Reiji Suzuki, Takaya Arita, Kimitoshi Yamazaki
https://arxiv.org/abs/2404.12631

Breaching the Bottleneck: Evolutionary Transition from Reward-Driven Learning to Reward-Agnostic Domain-Adapted Learning in Neuromodulated Neural Nets
Advanced biological intelligence learns efficiently from an information-rich stream of stimulus information, even when feedback on behaviour quality is sparse or absent. Such learning exploits implicit assumptions about task domains. We refer to such learning as Domain-Adapted Learning (DAL). In contrast, AI learning algorithms rely on explicit externally provided measures of behaviour quality to acquire fit behaviour. This imposes an information bottleneck that precludes learning from diverse …

Drag & Drop • by FormKit
FormKit’s Drag and Drop is a small library for adding data-first drag and drop sorting and transferring for lists in your app. It’s simple, flexible, framework agnostic, and clocks in at only ~4Kb gzipped
https://drag-and-drop.formkit.com/?s=09…

Double Cross-fit Doubly Robust Estimators: Beyond Series Regression
Alec McClean, Sivaraman Balakrishnan, Edward H. Kennedy, Larry Wasserman
https://arxiv.org/abs/2403.15175

Double Cross-fit Doubly Robust Estimators: Beyond Series Regression
Doubly robust estimators with cross-fitting have gained popularity in causal inference due to their favorable structure-agnostic error guarantees. However, when additional structure, such as Hölder smoothness, is available then more accurate "double cross-fit doubly robust" (DCDR) estimators can be constructed by splitting the training data and undersmoothing nuisance function estimators on independent samples. We study a DCDR estimator of the Expected Conditional Covariance, a functional of i…

Time to learn about the people following me here... Are you?
Follower of an established religion
Deist/Agnostic
Atheist
Other (please explain)

Neural Slicer for Multi-Axis 3D Printing
Tao Liu, Tianyu Zhang, Yongxue Chen, Yuming Huang, Charlie C. L. Wang
https://arxiv.org/abs/2404.15061 https://

Neural Slicer for Multi-Axis 3D Printing
We introduce a novel neural network-based computational pipeline as a representation-agnostic slicer for multi-axis 3D printing. This advanced slicer can work on models with diverse representations and intricate topology. The approach involves employing neural networks to establish a deformation mapping, defining a scalar field in the space surrounding an input model. Isosurfaces are subsequently extracted from this field to generate curved layers for 3D printing. Creating a differentiable pipe…

This https://arxiv.org/abs/2311.14918 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Resolution- and Stimulus-agnostic Super-Resolution of Ultra-High-Field Functional MRI: Application to Visual Studies
High-resolution fMRI provides a window into the brain's mesoscale organization. Yet, higher spatial resolution increases scan times, to compensate for the low signal and contrast-to-noise ratio. This work introduces a deep learning-based 3D super-resolution (SR) method for fMRI. By incorporating a resolution-agnostic image augmentation framework, our method adapts to varying voxel sizes without retraining. We apply this innovative technique to localize fine-scale motion-selective sites in the e…

Almost Optimal Agnostic Control of Unknown Linear Dynamics
Jacob Carruth, Maximilian F. Eggl, Charles Fefferman, Clarence W. Rowley
https://arxiv.org/abs/2403.06320

Almost Optimal Agnostic Control of Unknown Linear Dynamics
We consider a simple control problem in which the underlying dynamics depend on a parameter $a$ that is unknown and must be learned. We study three variants of the control problem: Bayesian control, in which we have a prior belief about $a$; bounded agnostic control, in which we have no prior belief about $a$ but we assume that $a$ belongs to a bounded set; and fully agnostic control, in which $a$ is allowed to be an arbitrary real number about which we have no prior belief. In the Bayesian var…

This https://arxiv.org/abs/2311.01120 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

EHA: Entanglement-variational Hardware-efficient Ansatz for Eigensolvers
Variational quantum eigensolvers (VQEs) are one of the most important and effective applications of quantum computing, especially in the current noisy intermediate-scale quantum (NISQ) era. There are mainly two ways for VQEs: problem-agnostic and problem-specific. For problem-agnostic methods, they often suffer from trainability issues. For problem-specific methods, their performance usually relies upon choices of initial reference states which are often hard to determine. In this paper, we pro…

This https://arxiv.org/abs/2303.14312 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

GAN-RXA: A Practical Scalable Solution to Receiver-Agnostic Transmitter Fingerprinting
Radio frequency fingerprinting has been proposed for device identification. However, experimental studies also demonstrated its sensitivity to deployment changes. Recent works have addressed channel impacts by developing robust algorithms accounting for time and location variability, but the impacts of receiver impairments on transmitter fingerprints are yet to be solved. In this work, we investigate the receiver-agnostic transmitter fingerprinting problem, and propose a novel two-stage supervi…

Gene-agnostic approaches to treating inherited retinal degenerations https://www.frontiersin.org/articles/10.3389/fcell.2023.1177838/full Funny how they write a whole section on the BrainPort Vision Pro without even mentioning The vOICe - more agnosticism…

Gene-agnostic approaches to treating inherited retinal degenerations
Most patients with inherited retinal degenerations (IRDs) have been waiting for treatments that are “just around the corner” for decades, with only a handful of seminal breakthroughs happening in recent years. Highlighting the difficulties in the quest for curative therapeutics, Luxturna required 16 years of development before finally obtaining United States Food and Drug Administration (FDA) approval and its international equivalents. IRDs are both genetically and phenotypically heterogen…

Amazingly, this article is agnostic about whether having narcissistic employees is good or bad. Narcissists are bad news! https://mastodon.online/@jchyip/111935966004916789

Here it is, my 1541-RAMBoard][.
A solution to have extra 8K of RAM for disk copying that turned out to be also a very simple way to have DolphinDOS 2.
I have already patched JiffyDOS to use extra RAM for track cache too, so it's faster (10.5x instead of 9.8x) and sector interleave agnostic.
I will be switching between JiffyDOS and DolphinDOS, depending on my needs.
Full project is here:

Language-Agnostic Modeling of Wikipedia Articles for Content Quality Assessment across Languages
Paramita Das, Isaac Johnson, Diego Saez-Trumper, Pablo Arag\'on
https://arxiv.org/abs/2404.09764

Language-Agnostic Modeling of Wikipedia Articles for Content Quality Assessment across Languages
Wikipedia is the largest web repository of free knowledge. Volunteer editors devote time and effort to creating and expanding articles in more than 300 language editions. As content quality varies from article to article, editors also spend substantial time rating articles with specific criteria. However, keeping these assessments complete and up-to-date is largely impossible given the ever-changing nature of Wikipedia. To overcome this limitation, we propose a novel computational framework for…

Fractal time scale-free agnostic messaging: amplitude modulation of carriers given by the Weierstrass function's components
Hector Zenil, Luan Carlos de Sena Monteiro
https://arxiv.org/abs/2403.06633

Fractal time scale-free agnostic messaging: amplitude modulation of carriers given by the Weierstrass function's components
In the context of interstellar communication, it is not known beforehand if the receiver of a given signal would be a plant, an insect, or even life forms unknown to terrestrial scientists. Regardless of the situation, the message time scale could be too fast or too slow and those beings would probably never decode it. Therefore, it is of interest to devise a way to encode messages agnostic of time scale. Fractal messaging would allow one to do this due to their structural self-similarity and, …

This https://arxiv.org/abs/2402.15213 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Statistical Agnostic Regression: a machine learning method to validate regression models
Regression analysis is a central topic in statistical modeling, aiming to estimate the relationships between a dependent variable, commonly referred to as the response variable, and one or more independent variables, i.e., explanatory variables. Linear regression is by far the most popular method for performing this task in several fields of research, such as prediction, forecasting, or causal inference. Beyond various classical methods to solve linear regression problems, such as Ordinary Leas…

Is there a site that’ll convert a service-specific playlist into a service-agnostic shareable link, sorta like a song.link but for a whole playlist? 🤔

Optimal State Estimation in the Presence of Non-Gaussian Uncertainty via Wasserstein Distance Minimization
Himanshu Prabhat, Raktim Bhattacharya
https://arxiv.org/abs/2403.13828 <…

Optimal State Estimation in the Presence of Non-Gaussian Uncertainty via Wasserstein Distance Minimization
This paper presents a novel distribution-agnostic Wasserstein distance-based estimation framework. The goal is to determine an optimal map combining prior estimate with measurement likelihood such that posterior estimation error optimally reaches the Dirac delta distribution with minimal effort. The Wasserstein metric is used to quantify the effort of transporting from one distribution to another. We hypothesize that minimizing the Wasserstein distance between the posterior error and the Dirac …

@… I would think about it this way:
version 2.1.1 of the codebase now exists. That fact itself is arch agnostic. That source is then compiled and released for all supported platforms.
The fact that the binary diff on one of the platforms would show no changes is irrelevant. Because the source code of the project is what is versioned,…

CoPlay: Audio-agnostic Cognitive Scaling for Acoustic Sensing
Yin Li, Rajalakshmi Nanadakumar
https://arxiv.org/abs/2403.10796 https://

CoPlay: Audio-agnostic Cognitive Scaling for Acoustic Sensing
Acoustic sensing manifests great potential in various applications that encompass health monitoring, gesture interface and imaging by leveraging the speakers and microphones on smart devices. However, in ongoing research and development in acoustic sensing, one problem is often overlooked: the same speaker, when used concurrently for sensing and other traditional applications (like playing music), could cause interference in both making it impractical to use in the real world. The strong ultras…

This https://arxiv.org/abs/2310.00542 has been replaced.
link: https://scholar.google.com/scholar?q=a

Watch Out! Simple Horizontal Class Backdoors Can Trivially Evade Defenses
All current backdoor attacks on deep learning (DL) models fall under the category of a vertical class backdoor (VCB) -- class-dependent. In VCB attacks, any sample from a class activates the implanted backdoor when the secret trigger is present. Existing defense strategies overwhelmingly focus on countering VCB attacks, especially those that are source-class-agnostic. This narrow focus neglects the potential threat of other simpler yet general backdoor types, leading to false security implicati…

An Agnostic Biosignature Based on Modeling Panspermia and Terraformation
Harrison B. Smith, Lana Sinapayen
https://arxiv.org/abs/2403.14195 https://…

An Agnostic Biosignature Based on Modeling Panspermia and Terraformation
A fundamental goal of astrobiology is to detect life outside of Earth. This proves to be an exceptional challenge outside of our solar system, where strong assumptions must be made about how life would manifest and interact with its planet. Such assumptions are required because of the lack of a consensus theory of living systems, or an understanding of the possible extent of planetary dynamics. Here we explore a model of life spreading between planetary systems via panspermia and terraformation…

This https://arxiv.org/abs/2402.11453 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Despite its importance, the use of Large Language Models (LLMs) for scientific data visualization remains rather unexplored. In this study, we introduce MatPlotAgent, an efficient model-agnostic LLM agent framework designed to automate scientific data visualization tasks. Leveraging the capabilities of both code LLMs and…

This https://arxiv.org/abs/2310.18962 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_grqc_…

About the ability of agnostic X-ray tests of the Kerr Hypothesis to discover new physics
In the past decade, we have seen an unprecedented progress in our ability of testing general relativity in the strong field regime with black hole observations. Most studies have focused on the so-called tests of the Kerr hypothesis: they have tried to verify whether the spacetime geometry around black holes is described by the Kerr solution as expected in general relativity. One can follow either a theory-specific analysis or an agnostic approach. Each strategy has its advantages and disadvant…

Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis
Vishnu Sashank Dorbala, Sanjoy Chowdhury, Dinesh Manocha
https://arxiv.org/abs/2403.11487

Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis
We present a novel approach to automatically synthesize "wayfinding instructions" for an embodied robot agent. In contrast to prior approaches that are heavily reliant on human-annotated datasets designed exclusively for specific simulation platforms, our algorithm uses in-context learning to condition an LLM to generate instructions using just a few references. Using an LLM-based Visual Question Answering strategy, we gather detailed information about the environment which is used by the LLM f…

#Museums join the #Fediverse:
"Ultimately the goal is to expand and broaden the “surface area of interests” allowing us to reach a broader audience and increasing awareness of the Museum’s programming and offerings. To that end having a platform-agnostic means by which our visitors can subscribe…

Holding Hands with the "Fediverse" – ActivityPub at SFO Museum
SFO Museum has joined the “Fediverse”. We have begun to operate a series of automated “bot” accounts that are published using the ActivityPub protocols and that can be subscribed to from any client, like Mastodon, that supports those standards. These are automated, low-frequency, accounts and they currently only support a limited set of interactions: Accounts can be followed or unfollowed, individual posts can be “liked”, “boosted” or replied to but those replies will not be ans…

Constructing model-agnostic likelihoods, a method for the reinterpretation of particle physics results
Lorenz G\"artner, Nikolai Hartmann, Lukas Heinrich, Malin Horstmann, Thomas Kuhr, M\'eril Reboud, Slavomira Stefkova, Danny van Dyk
https://arxiv.org/abs/2402.08417

Constructing model-agnostic likelihoods, a method for the reinterpretation of particle physics results
Experimental High Energy Physics has entered an era of precision measurements. However, measurements of many of the accessible processes assume that the final states' underlying kinematic distribution is the same as the Standard Model prediction. This assumption introduces an implicit model-dependency into the measurement, rendering the reinterpretation of the experimental analysis complicated without reanalysing the underlying data. We present a novel reweighting method in order to perform rei…

This https://arxiv.org/abs/2402.15213 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Statistical Agnostic Regression: a machine learning method to validate regression models
Regression analysis is a central topic in statistical modeling, aiming to estimate the relationships between a dependent variable, commonly referred to as the response variable, and one or more independent variables, i.e., explanatory variables. Linear regression is by far the most popular method for performing this task in several fields of research, such as prediction, forecasting, or causal inference. Beyond various classical methods to solve linear regression problems, such as Ordinary Leas…

Full-Atom Peptide Design with Geometric Latent Diffusion
Xiangzhe Kong, Wenbing Huang, Yang Liu
https://arxiv.org/abs/2402.13555 https://

Full-Atom Peptide Design with Geometric Latent Diffusion
Peptide design plays a pivotal role in therapeutics, allowing brand new possibility to leverage target binding sites that are previously undruggable. Most existing methods are either inefficient or only concerned with the target-agnostic design of 1D sequences. In this paper, we propose a generative model for full-atom \textbf{Pep}tide design with \textbf{G}eometric \textbf{LA}tent \textbf{D}iffusion (PepGLAD). We first collect a dataset consisting of both 1D sequences and 3D structures from Pr…

I’ve always wanted someone to tell me I autocomplete them.
:awesome:
https://www.npmjs.com/package/aral
(That feeling when someone makes a Node package with your name. Hey, at least it’s not a German petroleum company…)

aral
An Agnostic Resources Access Layer system. Latest version: 0.2.58, last published: a year ago. Start using aral in your project by running `npm i aral`. There are no other projects in the npm registry using aral.

Principal Component Analysis and biplots. A Back-to-Basics Comparison of Implementations
Ettore Settanni
https://arxiv.org/abs/2404.15115 https://

Principal Component Analysis and biplots. A Back-to-Basics Comparison of Implementations
Principal Component Analysis and biplots are so well-established and readily implemented that it is just too tempting to give for granted their internal workings. In this note I get back to basics in comparing how PCA and biplots are implemented in base-R and contributed R packages, leveraging an implementation-agnostic understanding of the computational structure of each technique. I do so with a view to illustrating discrepancies that users might find elusive, as these arise from seemingly in…

On mainstreaming.
The most important point here is that the concept and mechanisms described are value agnostic. They're available to anyone. And those with fewer scruples have more tools available to them.
https://youtube.com/watch?v=Gq0ZHgKT2tc

General Item Representation Learning for Cold-start Content Recommendations
Jooeun Kim, Jinri Kim, Kwangeun Yeo, Eungi Kim, Kyoung-Woon On, Jonghwan Mun, Joonseok Lee
https://arxiv.org/abs/2404.13808

General Item Representation Learning for Cold-start Content Recommendations
Cold-start item recommendation is a long-standing challenge in recommendation systems. A common remedy is to use a content-based approach, but rich information from raw contents in various forms has not been fully utilized. In this paper, we propose a domain/data-agnostic item representation learning framework for cold-start recommendations, naturally equipped with multimodal alignment among various features by adopting a Transformer-based architecture. Our proposed model is end-to-end trainabl…

Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis
Vishnu Sashank Dorbala, Sanjoy Chowdhury, Dinesh Manocha
https://arxiv.org/abs/2403.11487

Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis
We present a novel approach to automatically synthesize "wayfinding instructions" for an embodied robot agent. In contrast to prior approaches that are heavily reliant on human-annotated datasets designed exclusively for specific simulation platforms, our algorithm uses in-context learning to condition an LLM to generate instructions using just a few references. Using an LLM-based Visual Question Answering strategy, we gather detailed information about the environment which is used by the LLM f…

This https://arxiv.org/abs/2312.09988 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Towards Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularization
Untrained networks inspired by deep image prior have shown promising capabilities in recovering a high-quality image from noisy or partial measurements, without requiring training data. Their success has been widely attributed to the spectral bias acting as an implicit regularization induced by suitable network architectures. However, applications of such network-based priors often entail superfluous architectural decisions, overfitting risks, and slow optimization, all of which hinder their pr…

Ok people its nots that fucking hard.
If your #software 's #help is #online (.chm files - so 90s), then thou shalt:
1. make sure it stays there OR
2. if it is version agnostic, any old URLs redirect to the late…

Generalising Multi-Agent Cooperation through Task-Agnostic Communication
Dulhan Jayalath, Steven Morad, Amanda Prorok
https://arxiv.org/abs/2403.06750 http…

Generalising Multi-Agent Cooperation through Task-Agnostic Communication
Existing communication methods for multi-agent reinforcement learning (MARL) in cooperative multi-robot problems are almost exclusively task-specific, training new communication strategies for each unique task. We address this inefficiency by introducing a communication strategy applicable to any task within a given environment. We pre-train the communication strategy without task-specific reward guidance in a self-supervised manner using a set autoencoder. Our objective is to learn a fixed-siz…

1541II-RAMBoard][, my variation on RAMBoard with extra ROM space.
I just wanted a RAM expansion for 1541II (just like I did for 1571CR), but it turns out it is exactly what is needed by DolphinDOS 2!
Now I have best of both worlds - JiffyDOS patched to cache whole tracks (interleave agnostic) in RAM and decode GCR faster using 1571 lookup tables AND DolphinDOS 2 with its 27x speed.
I completed testing today, details and project soon on GitHub.

Mesh-Agnostic Decoders for Supercritical Airfoil Prediction and Inverse Design
Runze Li, Yufei Zhang, Haixin Chen
https://arxiv.org/abs/2402.17299 https://…

Mesh-Agnostic Decoders for Supercritical Airfoil Prediction and Inverse Design
Mesh-agnostic models have advantages in terms of processing unstructured spatial data and incorporating partial differential equations. Recently, they have been widely studied for constructing physics-informed neural networks, but they need to be trained on a case-by-case basis and require large training times. On the other hand, fast prediction and design tools are desired for aerodynamic shape designs, and data-driven mesh-based models have achieved great performance. Therefore, this paper pr…

This https://arxiv.org/abs/2403.06633 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

Fractal time scale-free agnostic messaging: amplitude modulation of carriers given by the Weierstrass function's components
In the context of interstellar communication, it is not known beforehand if the receiver of a given signal would be a plant, an insect, or even life forms unknown to terrestrial scientists. Regardless of the situation, the message time scale could be too fast or too slow and those beings would probably never decode it. Therefore, it is of interest to devise a way to encode messages agnostic of time scale. Fractal messaging would allow one to do this due to their structural self-similarity and, …

On the Power of Interactive Proofs for Learning
Tom Gur, Mohammad Mahdi Jahanara, Mohammad Mahdi Khodabandeh, Ninad Rajgopal, Bahar Salamatian, Igor Shinkar
https://arxiv.org/abs/2404.08158

On the Power of Interactive Proofs for Learning
We continue the study of doubly-efficient proof systems for verifying agnostic PAC learning, for which we obtain the following results. - We construct an interactive protocol for learning the $t$ largest Fourier characters of a given function $f \colon \{0,1\}^n \to \{0,1\}$ up to an arbitrarily small error, wherein the verifier uses $\mathsf{poly}(t)$ random examples. This improves upon the Interactive Goldreich-Levin protocol of Goldwasser, Rothblum, Shafer, and Yehudayoff (ITCS 2021) whose…

Leveraging Fine-Grained Information and Noise Decoupling for Remote Sensing Change Detection
Qiangang Du, Jinlong Peng, Changan Wang, Xu Chen, Qingdong He, Wenbing Zhu, Mingmin Chi, Yabiao Wang, Chengjie Wang
https://arxiv.org/abs/2404.11318

Leveraging Fine-Grained Information and Noise Decoupling for Remote Sensing Change Detection
Change detection aims to identify remote sense object changes by analyzing data between bitemporal image pairs. Due to the large temporal and spatial span of data collection in change detection image pairs, there are often a significant amount of task-specific and task-agnostic noise. Previous effort has focused excessively on denoising, with this goes a great deal of loss of fine-grained information. In this paper, we revisit the importance of fine-grained features in change detection and prop…

This https://arxiv.org/abs/2311.12528 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Inverse Problems with Learned Forward Operators
Solving inverse problems requires the knowledge of the forward operator, but accurate models can be computationally expensive and hence cheaper variants that do not compromise the reconstruction quality are desired. This chapter reviews reconstruction methods in inverse problems with learned forward operators that follow two different paradigms. The first one is completely agnostic to the forward operator and learns its restriction to the subspace spanned by the training data. The framework of …

Prior-agnostic Multi-scale Contrastive Text-Audio Pre-training for Parallelized TTS Frontend Modeling
Quanxiu Wang, Hui Huang, Mingjie Wang, Yong Dai, Jinzuomu Zhong, Benlai Tang
https://arxiv.org/abs/2404.09192

Prior-agnostic Multi-scale Contrastive Text-Audio Pre-training for Parallelized TTS Frontend Modeling
Over the past decade, a series of unflagging efforts have been dedicated to developing highly expressive and controllable text-to-speech (TTS) systems. In general, the holistic TTS comprises two interconnected components: the frontend module and the backend module. The frontend excels in capturing linguistic representations from the raw text input, while the backend module converts linguistic cues to speech. The research community has shown growing interest in the study of the frontend componen…

A Cross-Cultural Analysis of Social Norms in Bollywood and Hollywood Movies
Sunny Rai, Khushang Zilesh Zaveri, Shreya Havaldar, Soumna Nema, Lyle Ungar, Sharath Chandra Guntuku
https://arxiv.org/abs/2402.11333

A Cross-Cultural Analysis of Social Norms in Bollywood and Hollywood Movies
Understanding how social norms vary across cultures can help us build culturally aligned NLP systems. We propose a culture agnostic approach to norm discovery, using moral emotions, shame and pride, to identify examples of normative expectations and extract corresponding social norms. We present the first cross cultural self-conscious emotions dataset, obtained from 5.4K Bollywood and Hollywood movies, along with over 10K extracted social norms. We validate our dataset using native speakers and…

This https://arxiv.org/abs/2403.04287 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives
Graph Convolutional Networks (GCNs) have become pivotal in recommendation systems for learning user and item embeddings by leveraging the user-item interaction graph's node information and topology. However, these models often face the famous over-smoothing issue, leading to indistinct user and item embeddings and reduced personalization. Traditional desmoothing methods in GCN-based systems are model-specific, lacking a universal solution. This paper introduces a novel, model-agnostic approach …

This https://arxiv.org/abs/2403.02686 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Hierarchy of the echo state property in quantum reservoir computing
The echo state property (ESP) represents a fundamental concept in the reservoir computing (RC) framework that ensures output-only training of reservoir networks by being agnostic to the initial states and far past inputs. However, the traditional definition of ESP does not describe possible non-stationary systems in which statistical properties evolve. To address this issue, we introduce two new categories of ESP: $\textit{non-stationary ESP}$, designed for potentially non-stationary systems, a…

The 'Sandwich' meta-framework for architecture agnostic deep privacy-preserving transfer learning for non-invasive brainwave decoding
Xiaoxi Wei, Jyotindra Narayan, A. Aldo Faisal
https://arxiv.org/abs/2404.06868

The 'Sandwich' meta-framework for architecture agnostic deep privacy-preserving transfer learning for non-invasive brainwave decoding
Machine learning has enhanced the performance of decoding signals indicating human behaviour. EEG decoding, as an exemplar indicating neural activity and human thoughts non-invasively, has been helpful in neural activity analysis and aiding patients via brain-computer interfaces. However, training machine learning algorithms on EEG encounters two primary challenges: variability across data sets and privacy concerns using data from individuals and data centres. Our objective is to address these …

This https://arxiv.org/abs/2304.05323 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

A nonparametric framework for treatment effect modifier discovery in high dimensions
Heterogeneous treatment effects are driven by treatment effect modifiers, pre-treatment covariates that modify the effect of a treatment on an outcome. Current approaches for uncovering these variables are limited to low-dimensional data, data with weakly correlated covariates, or data generated according to parametric processes. We resolve these issues by developing a framework for defining model-agnostic treatment effect modifier variable importance parameters applicable to high-dimensional d…

1541II-RAMBoard][, my variation on RAMBoard with extra ROM space.
I just wanted a RAM expansion for 1541II (just like I did for 1571CR), but it turns out it is exactly what is needed by DolphinDOS 2!
Now I have best of both worlds - JiffyDOS patched to cache whole tracks (interleave agnostic) in RAM and decode GCR faster using 1571 lookup tables AND DolphinDOS 2 with its 27x speed.
I completed testing today, details and project soon on GitHub.

This https://arxiv.org/abs/2311.09393 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

Taypsi: Static Enforcement of Privacy Policies for Policy-Agnostic Oblivious Computation
Secure multiparty computation (MPC) techniques enable multiple parties to compute joint functions over their private data without sharing that data to other parties, typically by employing powerful cryptographic protocols to protect individual's data. One challenge when writing such functions is that most MPC languages force users to intermix programmatic and privacy concerns in a single application, making it difficult to change or audit a program's underlying privacy policy. Existing policy-a…

$\texttt{COSMIC}$: Mutual Information for Task-Agnostic Summarization Evaluation
Maxime Darrin, Philippe Formont, Jackie Chi Kit Cheung, Pablo Piantanida
https://arxiv.org/abs/2402.19457

$\texttt{COSMIC}$: Mutual Information for Task-Agnostic Summarization Evaluation
Assessing the quality of summarizers poses significant challenges. In response, we propose a novel task-oriented evaluation approach that assesses summarizers based on their capacity to produce summaries that are useful for downstream tasks, while preserving task outcomes. We theoretically establish a direct relationship between the resulting error probability of these tasks and the mutual information between source texts and generated summaries. We introduce $\texttt{COSMIC}$ as a practical im…

This https://arxiv.org/abs/2311.00884 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Predictive Optimization of Hybrid Energy Systems with Temperature Dependency
Hybrid Energy Systems (HES), amalgamating renewable sources, energy storage, and conventional generation, have emerged as a responsive resource for providing valuable grid services. Subsequently, modeling and analysis of HES has become critical, and the quality of grid services hedges on it. Currently, most HES models are temperature-agnostic. However, the temperature-dependent factors can significantly impact HES performance, necessitating advanced modeling and optimization techniques. With th…

This https://arxiv.org/abs/2311.14803 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_grqc_…

Black hole spectroscopy beyond Kerr: agnostic and theory-based tests with next-generation interferometers
Black hole spectroscopy is a clean and powerful tool to test gravity in the strong-field regime and to probe the nature of compact objects. Next-generation ground-based detectors, such as the Einstein Telescope and Cosmic Explorer, will observe thousands of binary black hole mergers with large signal-to-noise ratios, allowing for accurate measurements of the remnant black hole quasinormal mode frequencies and damping times. In previous work we developed an observable-based parametrization of th…

Leveraging Fine-Grained Information and Noise Decoupling for Remote Sensing Change Detection
Qiangang Du, Jinlong Peng, Changan Wang, Xu Chen, Qingdong He, Wenbing Zhu, Mingmin Chi, Yabiao Wang, Chengjie Wang
https://arxiv.org/abs/2404.11318

Leveraging Fine-Grained Information and Noise Decoupling for Remote Sensing Change Detection
Change detection aims to identify remote sense object changes by analyzing data between bitemporal image pairs. Due to the large temporal and spatial span of data collection in change detection image pairs, there are often a significant amount of task-specific and task-agnostic noise. Previous effort has focused excessively on denoising, with this goes a great deal of loss of fine-grained information. In this paper, we revisit the importance of fine-grained features in change detection and prop…

This https://arxiv.org/abs/2310.01205 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Local disclosure of quantum memory in non-Markovian dynamics
Non-Markovian processes may arise in physics due to memory effects of environmental degrees of freedom. For quantum non-Markovianity, it is an ongoing debate to clarify whether such memory effects have a verifiable quantum origin, or whether they might equally be modeled by a classical memory. In this contribution, we propose a criterion to test locally for a truly quantum memory. The approach is agnostic with respect to the environment, as it solely depends on the local dynamics of the system …

This https://arxiv.org/abs/2310.19064 has been replaced.
link: https://scholar.google.com/scholar?q=a

Apple Tasting: Combinatorial Dimensions and Minimax Rates
In online binary classification under \emph{apple tasting} feedback, the learner only observes the true label if it predicts ``1". First studied by \cite{helmbold2000apple}, we revisit this classical partial-feedback setting and study online learnability from a combinatorial perspective. We show that the Littlestone dimension continues to provide a tight quantitative characterization of apple tasting in the agnostic setting, closing an open question posed by \cite{helmbold2000apple}. In additio…

This https://arxiv.org/abs/2301.07010 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hepe…

$Λ^+_\mathrm{c}$ polarimetry using the dominant hadronic mode
The polarimeter vector field for multibody decays of a spin-half baryon is introduced as a generalisation of the baryon asymmetry parameters. Using a recent amplitude analysis of the $Λ^+_\mathrm{c} \to p K^- π^+$ decay performed at the LHCb experiment, we compute the distribution of the kinematic-dependent polarimeter vector for this process in the space of Mandelstam variables to express the polarised decay rate in a model-agnostic form. The obtained representation can facilitate polarisati…

Adaptive Constellation Multiple Access for Beyond 5G Wireless Systems
Indu L. Shakya, Falah H. Ali
https://arxiv.org/abs/2402.11050 https://

Adaptive Constellation Multiple Access for Beyond 5G Wireless Systems
We propose a novel nonorthogonal multiple access (NOMA) scheme referred as adaptive constellation multiple access (ACMA) which addresses key limitations of existing NOMA schemes for beyond 5G wireless systems. Unlike the latter, that are often constrained in choices of allocation of power, modulations and phases to allow enough separation of clusters from users combined signals, ACMA is power, modulation and phase agnostic forming unified constellations instead where distances of all possible n…

D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Manipulation
Jun Yamada, Shaohong Zhong, Jack Collins, Ingmar Posner
https://arxiv.org/abs/2403.12861

D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Manipulation
Mastering dexterous robotic manipulation of deformable objects is vital for overcoming the limitations of parallel grippers in real-world applications. Current trajectory optimisation approaches often struggle to solve such tasks due to the large search space and the limited task information available from a cost function. In this work, we propose D-Cubed, a novel trajectory optimisation method using a latent diffusion model (LDM) trained from a task-agnostic play dataset to solve dexterous def…

Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders
Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez
https://arxiv.org/abs/2403.08941

Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders
Inference for Variational Autoencoders (VAEs) consists of learning two models: (1) a generative model, which transforms a simple distribution over a latent space into the distribution over observed data, and (2) an inference model, which approximates the posterior of the latent codes given data. The two components are learned jointly via a lower bound to the generative model's log marginal likelihood. In early phases of joint training, the inference model poorly approximates the latent code pos…

Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulations
Jiarui Lu, Zuobai Zhang, Bozitao Zhong, Chence Shi, Jian Tang
https://arxiv.org/abs/2402.10433

Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulations
The protein dynamics are common and important for their biological functions and properties, the study of which usually involves time-consuming molecular dynamics (MD) simulations in silico. Recently, generative models has been leveraged as a surrogate sampler to obtain conformation ensembles with orders of magnitude faster and without requiring any simulation data (a "zero-shot" inference). However, being agnostic of the underlying energy landscape, the accuracy of such generative model may st…

Multi-Level Attention Aggregation for Language-Agnostic Speaker Replication
Yejin Jeon, Gary Geunbae Lee
https://arxiv.org/abs/2403.04111 https://

Multi-Level Attention Aggregation for Language-Agnostic Speaker Replication
This paper explores the task of language-agnostic speaker replication, a novel endeavor that seeks to replicate a speaker's voice irrespective of the language they are speaking. Towards this end, we introduce a multi-level attention aggregation approach that systematically probes and amplifies various speaker-specific attributes in a hierarchical manner. Through rigorous evaluations across a wide range of scenarios including seen and unseen speakers conversing in seen and unseen lingua, we esta…

Review-Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems
Shiyi Yang, Lina Yao, Chen Wang, Xiwei Xu, Liming Zhu
https://arxiv.org/abs/2402.09023

ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data
Liana Patel, Peter Kraft, Carlos Guestrin, Matei Zaharia
https://arxiv.org/abs/2403.04871

ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data
Applications increasingly leverage mixed-modality data, and must jointly search over vector data, such as embedded images, text and video, as well as structured data, such as attributes and keywords. Proposed methods for this hybrid search setting either suffer from poor performance or support a severely restricted set of search predicates (e.g., only small sets of equality predicates), making them impractical for many applications. To address this, we present ACORN, an approach for performant …

This https://arxiv.org/abs/2311.14803 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_grqc_…

Black hole spectroscopy beyond Kerr: agnostic and theory-based tests with next-generation interferometers
Black hole spectroscopy is a clean and powerful tool to test gravity in the strong-field regime and to probe the nature of compact objects. Next-generation ground-based detectors, such as the Einstein Telescope and Cosmic Explorer, will observe thousands of binary black hole mergers with large signal-to-noise ratios, allowing for accurate measurements of the remnant black hole quasinormal mode frequencies and damping times. In previous work we developed an observable-based parametrization of th…

Efficient and Model-Agnostic Parameter Estimation Under Privacy-Preserving Post-randomization Data
Qinglong Tian, Jiwei Zhao
https://arxiv.org/abs/2403.07288

Efficient and Model-Agnostic Parameter Estimation Under Privacy-Preserving Post-randomization Data
Protecting individual privacy is crucial when releasing sensitive data for public use. While data de-identification helps, it is not enough. This paper addresses parameter estimation in scenarios where data are perturbed using the Post-Randomization Method (PRAM) to enhance privacy. Existing methods for parameter estimation under PRAM data suffer from limitations like being parameter-specific, model-dependent, and lacking efficiency guarantees. We propose a novel, efficient method that overcome…

This https://arxiv.org/abs/2103.06712 has been replaced.
link: https://scholar.google.com/scholar?q=a

A semi-agnostic ansatz with variable structure for quantum machine learning
Quantum machine learning -- and specifically Variational Quantum Algorithms (VQAs) -- offers a powerful, flexible paradigm for programming near-term quantum computers, with applications in chemistry, metrology, materials science, data science, and mathematics. Here, one trains an ansatz, in the form of a parameterized quantum circuit, to accomplish a task of interest. However, challenges have recently emerged suggesting that deep ansatzes are difficult to train, due to flat training landscapes …

This https://arxiv.org/abs/2304.09820 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

A Two-Stage Framework with Self-Supervised Distillation For Cross-Domain Text Classification
Cross-domain text classification aims to adapt models to a target domain that lacks labeled data. It leverages or reuses rich labeled data from the different but related source domain(s) and unlabeled data from the target domain. To this end, previous work focuses on either extracting domain-invariant features or task-agnostic features, ignoring domain-aware features that may be present in the target domain and could be useful for the downstream task. In this paper, we propose a two-stage frame…

This https://arxiv.org/abs/2311.09393 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

Taypsi: Static Enforcement of Privacy Policies for Policy-Agnostic Oblivious Computation
Secure multiparty computation (MPC) techniques enable multiple parties to compute joint functions over their private data without sharing that data with other parties, typically by employing powerful cryptographic protocols to protect individual's data. One challenge when writing such functions is that most MPC languages force users to intermix programmatic and privacy concerns in a single application, making it difficult to change or audit a program's underlying privacy policy. Prior policy-ag…

ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data
Liana Patel, Peter Kraft, Carlos Guestrin, Matei Zaharia
https://arxiv.org/abs/2403.04871

ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data
Applications increasingly leverage mixed-modality data, and must jointly search over vector data, such as embedded images, text and video, as well as structured data, such as attributes and keywords. Proposed methods for this hybrid search setting either suffer from poor performance or support a severely restricted set of search predicates (e.g., only small sets of equality predicates), making them impractical for many applications. To address this, we present ACORN, an approach for performant …

This https://arxiv.org/abs/2305.00521 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

StyleLipSync: Style-based Personalized Lip-sync Video Generation
In this paper, we present StyleLipSync, a style-based personalized lip-sync video generative model that can generate identity-agnostic lip-synchronizing video from arbitrary audio. To generate a video of arbitrary identities, we leverage expressive lip prior from the semantically rich latent space of a pre-trained StyleGAN, where we can also design a video consistency with a linear transformation. In contrast to the previous lip-sync methods, we introduce pose-aware masking that dynamically loc…

This https://arxiv.org/abs/2311.14803 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_grqc_…

Black hole spectroscopy beyond Kerr: agnostic and theory-based tests with next-generation interferometers
Black hole spectroscopy is a clean and powerful tool to test gravity in the strong-field regime and to probe the nature of compact objects. Next-generation ground-based detectors, such as the Einstein Telescope and Cosmic Explorer, will observe thousands of binary black hole mergers with large signal-to-noise ratios, allowing for accurate measurements of the remnant black hole quasinormal mode frequencies and damping times. In previous work we developed an observable-based parametrization of th…

This https://arxiv.org/abs/2401.07782 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote Sensing
Self-supervised learning through masked autoencoders (MAEs) has recently attracted great attention for remote sensing (RS) image representation learning, and thus embodies a significant potential for content-based image retrieval (CBIR) from ever-growing RS image archives. However, the existing studies on MAEs in RS assume that the considered RS images are acquired by a single image sensor, and thus are only suitable for uni-modal CBIR problems. The effectiveness of MAEs for cross-sensor CBIR, …

Distribution-Agnostic Database De-Anonymization Under Obfuscation And Synchronization Errors
Serhat Bakirtas, Elza Erkip
https://arxiv.org/abs/2404.01366 h…

Distribution-Agnostic Database De-Anonymization Under Obfuscation And Synchronization Errors
Database de-anonymization typically involves matching an anonymized database with correlated publicly available data. Existing research focuses either on practical aspects without requiring knowledge of the data distribution yet provides limited guarantees, or on theoretical aspects assuming known distributions. This paper aims to bridge these two approaches, offering theoretical guarantees for database de-anonymization under synchronization errors and obfuscation without prior knowledge of dat…

This https://arxiv.org/abs/2402.11333 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

A Cross-Cultural Analysis of Social Norms in Bollywood and Hollywood Movies
Understanding how social norms vary across cultures can help us build culturally aligned NLP systems. We propose a culture agnostic approach to norm discovery, using moral emotions, shame and pride, to identify examples of normative expectations and extract corresponding social norms. We present the first cross cultural self-conscious emotions dataset, obtained from 5.4K Bollywood and Hollywood movies, along with over 10K extracted social norms. We validate our dataset using native speakers and…

This https://arxiv.org/abs/2302.01421 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Follower Agnostic Methods for Stackelberg Games
In this paper, we present an efficient algorithm to solve online Stackelberg games, featuring multiple followers, in a follower-agnostic manner. Unlike previous works, our approach works even when leader has no knowledge about the followers' utility functions or strategy space. Our algorithm introduces a unique gradient estimator, leveraging specially designed strategies to probe followers. In a departure from traditional assumptions of optimal play, we model followers' responses using a conver…

Learning Cross-hand Policies for High-DOF Reaching and Grasping
Qijin She, Shishun Zhang, Yunfan Ye, Min Liu, Ruizhen Hu, Kai Xu
https://arxiv.org/abs/2404.09150

Learning Cross-hand Policies for High-DOF Reaching and Grasping
Reaching-and-grasping is a fundamental skill for robotic manipulation, but existing methods usually train models on a specific gripper and cannot be reused on another gripper without retraining. In this paper, we propose a novel method that can learn a unified policy model that can be easily transferred to different dexterous grippers. Our method consists of two stages: a gripper-agnostic policy model that predicts the displacements of predefined key points on the gripper, and a gripper specifi…

A Flow-based Credibility Metric for Safety-critical Pedestrian Detection
Maria Lyssenko, Christoph Gladisch, Christian Heinzemann, Matthias Woehrle, Rudolph Triebel
https://arxiv.org/abs/2402.07642

A Flow-based Credibility Metric for Safety-critical Pedestrian Detection
Safety is of utmost importance for perception in automated driving (AD). However, a prime safety concern in state-of-the art object detection is that standard evaluation schemes utilize safety-agnostic metrics to argue sufficient detection performance. Hence, it is imperative to leverage supplementary domain knowledge to accentuate safety-critical misdetections during evaluation tasks. To tackle the underspecification, this paper introduces a novel credibility metric, called c-flow, for pedestr…

This https://arxiv.org/abs/2403.00054 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Agnostic Phase Estimation
The goal of quantum metrology is to improve measurements' sensitivities by harnessing quantum resources. Metrologists often aim to maximize the quantum Fisher information, which bounds the measurement setup's sensitivity. In studies of fundamental limits on metrology, a paradigmatic setup features a qubit (spin-half system) subject to an unknown rotation. One obtains the maximal quantum Fisher information about the rotation if the spin begins in a state that maximizes the variance of the rotati…

Misinformation Resilient Search Rankings with Webgraph-based Interventions
Peter Carragher, Evan M. Williams, Kathleen M. Carley
https://arxiv.org/abs/2404.08869

Misinformation Resilient Search Rankings with Webgraph-based Interventions
The proliferation of unreliable news domains on the internet has had wide-reaching negative impacts on society. We introduce and evaluate interventions aimed at reducing traffic to unreliable news domains from search engines while maintaining traffic to reliable domains. We build these interventions on the principles of fairness (penalize sites for what is in their control), generality (label/fact-check agnostic), targeted (increase the cost of adversarial behavior), and scalability (works at w…

NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning
Ruihua Han, Shuai Wang, Shuaijun Wang, Zeqing Zhang, Jianjun Chen, Shijie Lin, Chengyang Li, Chengzhong Xu, Yonina C. Eldar, Qi Hao, Jia Pan
https://arxiv.org/abs/2403.06828

NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning
Navigating a nonholonomic robot in a cluttered environment requires extremely accurate perception and locomotion for collision avoidance. This paper presents NeuPAN: a real-time, highly-accurate, map-free, robot-agnostic, and environment-invariant robot navigation solution. Leveraging a tightly-coupled perception-locomotion framework, NeuPAN has two key innovations compared to existing approaches: 1) it directly maps raw points to a learned multi-frame distance space, avoiding error propagation…

This https://arxiv.org/abs/2403.03309 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data
Visual understanding and segmentation of materials and their states is fundamental for understanding the physical world. The infinite textures, shapes and often blurry boundaries formed by material make this task particularly hard to generalize. Whether it's identifying wet regions of a surface, minerals in rocks, infected regions in plants, or pollution in water, each material state has its own unique form. For neural nets to learn class-agnostic materials segmentation it is necessary to first…

NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning
Ruihua Han, Shuai Wang, Shuaijun Wang, Zeqing Zhang, Jianjun Chen, Shijie Lin, Chengyang Li, Chengzhong Xu, Yonina C. Eldar, Qi Hao, Jia Pan
https://arxiv.org/abs/2403.06828

NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning
Navigating a nonholonomic robot in a cluttered environment requires extremely accurate perception and locomotion for collision avoidance. This paper presents NeuPAN: a real-time, highly-accurate, map-free, robot-agnostic, and environment-invariant robot navigation solution. Leveraging a tightly-coupled perception-locomotion framework, NeuPAN has two key innovations compared to existing approaches: 1) it directly maps raw points to a learned multi-frame distance space, avoiding error propagation…