Tootfinder

Eric Kendricks switches to Cowboys after picking Niners in free agency, AP source says https://www.foxsports.com/articles/nfl/eric-kendricks-switches-to-cowboys-after-picking-niners-in-free-agency-ap-source-say…

Eric Kendricks switches to Cowboys after picking Niners in free agency, AP source says
A person with knowledge of the deal says free agent linebacker Eric Kendricks has agreed to join the Dallas Cowboys after initially choosing the San Francisco 49ers

Aligning LLMs for FL-free Program Repair
Junjielong Xu, Ying Fu, Shin Hwei Tan, Pinjia He
https://arxiv.org/abs/2404.08877 https://ar…

Aligning LLMs for FL-free Program Repair
Large language models (LLMs) have achieved decent results on automated program repair (APR). However, the next token prediction training objective of decoder-only LLMs (e.g., GPT-4) is misaligned with the masked span prediction objective of current infilling-style methods, which impedes LLMs from fully leveraging pre-trained knowledge for program repair. In addition, while some LLMs are capable of locating and repairing bugs end-to-end when using the related artifacts (e.g., test cases) as inpu…

To the best of my knowledge the very word "autistic" first appeared in #PopCulture in Trots & Bonnie.
#ActuallyAutistic
#NationalLampoon

Eric Kendricks switches to Cowboys after picking Niners in free agency, AP source says https://www.foxsports.com/articles/nfl/eric-kendricks-switches-to-cowboys-after-picking-niners-in-free-agency-ap-source-say…

Eric Kendricks switches to Cowboys after picking Niners in free agency, AP source says
A person with knowledge of the deal says free agent linebacker Eric Kendricks has agreed to join the Dallas Cowboys after initially choosing the San Francisco 49ers

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…

Prototyping and Experimental Results for Environment-Aware Millimeter Wave Beam Alignment via Channel Knowledge Map
Zhuoyin Dai, Di Wu, Zhenjun Dong, Kun Li, Dingyang Ding, Sihan Wang, Yong Zeng
https://arxiv.org/abs/2403.08200

Prototyping and Experimental Results for Environment-Aware Millimeter Wave Beam Alignment via Channel Knowledge Map
Channel knowledge map (CKM), which aims to directly reflect the intrinsic channel properties of the local wireless environment, is a novel technique for achieving environmentaware communication. In this paper, to alleviate the large training overhead in millimeter wave (mmWave) beam alignment, an environment-aware and training-free beam alignment prototype is established based on a typical CKM, termed beam index map (BIM). To this end, a general CKM construction method is first presented, and a…

Australia’s chief scientist takes on the journal publishers gatekeeping knowledge
Before Latin mass was abandoned in the late 1960s, the average church-goer got by picking up snippets of phrases and the meanings of gestures.
To Dr Averil Cook, that’s what scientific research is like in the 21st century. The public relies on information to be synthesised for us, trickled down until it is devoid of its origin.
Cook, a clinical psychologist, is lucky. She can access the full b…

“In religion and politics, on the contrary, though there is as yet nothing approaching scientific knowledge, everybody considers it _de rigueur_ to have a dogmatic opinion, to be backed up by inflicting starvation, prison, and war, and to be carefully guarded from argumentative competition with any different opinion.”
Bertrand Russell, “Free Thought and Official Propaganda”, March 24th, 1922.

Free Thought and Official Propaganda - Wikipedia

#Australia’s chief scientist takes on the journal #publishers gatekeeping knowledge. Under Dr Cathy Foley’s world-first #OpenAccess model, all Australians would have

Hot take because I like the #GoodTechThings newsletter Forrest makes:
Stack overflow exists because primary documentation generally sucks and will continue to.
Otherwise why would (usually outdated) tutorials exist?
As @… points out... ChatGPT is good at being welcoming, stackoverflow is bad at it, and both are good at outdated wrong answers.
All docs on the internet have sucked longer than you think (yes, before SEO ruined things). It's just the paradox of knowledge: when you've known something so long you forget how far you've come and how hard it was to learn.
Was helping someone new to tech, tried looking back at some tutorials and gosh they didn't include all the papercuts I went through. Even official docs of commercial providers are not free of that. Some primary docs are just plain wrong or outdated.
#StackOverflow #DevRel
https://newsletter.goodtechthings.com/p/closed-as-unhelpful-an-elegy-for

Epidemic modelling requires knowledge of the social network
Samuel Johnson
https://arxiv.org/abs/2403.07881 https://arxiv.org/pdf/240…

Epidemic modelling requires knowledge of the social network
Compartmental models of epidemics are widely used to forecast the effects of communicable diseases such as COVID-19 and to guide policy. Although it has long been known that such processes take place on social networks, the assumption of random mixing is usually made, which ignores network structure. However, super-spreading events have been found to be power-law distributed, suggesting that the underlying networks may be scale free or at least highly heterogeneous. The random-mixing assumption…

This https://arxiv.org/abs/2312.11477 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Reconstructing relaxed configurations in elastic bodies: Mathematical formulations and numerical methods for cardiac modeling
Modeling the behavior of biological tissues and organs often necessitates the knowledge of their shape in the absence of external loads. However, when their geometry is acquired in-vivo through imaging techniques, bodies are typically subject to mechanical deformation due to the presence of external forces, and the load-free configuration needs to be reconstructed. This paper addresses this crucial and frequently overlooked topic, known as the inverse elasticity problem (IEP), by delving into b…

Prototyping and Experimental Results for Environment-Aware Millimeter Wave Beam Alignment via Channel Knowledge Map
Zhuoyin Dai, Di Wu, Zhenjun Dong, Kun Li, Dingyang Ding, Sihan Wang, Yong Zeng
https://arxiv.org/abs/2403.08200

Prototyping and Experimental Results for Environment-Aware Millimeter Wave Beam Alignment via Channel Knowledge Map
Channel knowledge map (CKM), which aims to directly reflect the intrinsic channel properties of the local wireless environment, is a novel technique for achieving environmentaware communication. In this paper, to alleviate the large training overhead in millimeter wave (mmWave) beam alignment, an environment-aware and training-free beam alignment prototype is established based on a typical CKM, termed beam index map (BIM). To this end, a general CKM construction method is first presented, and a…

Buffalo Bills begin replenishing receiver depth by agreeing to sign Mack Hollins, AP source says https://www.foxsports.com/articles/nfl/buffalo-bills-begin-replenishing-receiver-depth-by-agreeing-to-s…

Buffalo Bills begin replenishing receiver depth by agreeing to sign Mack Hollins, AP source says
A person with direct knowledge of discussions tells The Associated Press that the Buffalo Bills have begun replenishing their receiver depth by agreeing to sign free agent Mack Hollins

This https://arxiv.org/abs/2403.15304 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

KTbench: A Novel Data Leakage-Free Framework for Knowledge Tracing
Knowledge Tracing (KT) is concerned with predicting students' future performance on learning items in intelligent tutoring systems. Learning items are tagged with skill labels called knowledge concepts (KCs). Many KT models expand the sequence of item-student interactions into KC-student interactions by replacing learning items with their constituting KCs. This often results in a longer sequence length. This approach addresses the issue of sparse item-student interactions and minimises model pa…

This https://arxiv.org/abs/2402.18678 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

RORA: Robust Free-Text Rationale Evaluation
Free-text rationales play a pivotal role in explainable NLP, bridging the knowledge and reasoning gaps behind a model's decision-making. However, due to the diversity of potential reasoning paths and a corresponding lack of definitive ground truth, their evaluation remains a challenge. Existing evaluation metrics rely on the degree to which a rationale supports a target label, but we find these fall short in evaluating rationales that inadvertently leak the labels. To address this problem, we p…

Latest report on key pending free agent is music to Cowboys' ears https://www.yardbarker.com/nfl/articles/latest_report_on_key_pending_free_agent_is_music_to_cowboys_ears/s1_17313_40066454

Latest report on key pending free agent is music to Cowboys' ears
One of the biggest questions ahead of free agency is what will happen with Dallas Cowboys running back Tony Pollard.  A year after receiving the franchise tag, Pollard is now trending toward becoming a free agent next week, which will allow him to test the market and field offers from across the league.  Fortunately for the Cowboys though, it's starting to sound sounding as if Pollard could make things real easy on them to secure a reunion with America's Team.  "A person with knowledge of Po…

Pose-free object classification from surface contact features in sequences of Robotic grasps
Teresa Alves, Alexandre Bernardino, Plinio Moreno
https://arxiv.org/abs/2403.19840

Pose-free object classification from surface contact features in sequences of Robotic grasps
In this work, we propose two cost efficient methods for object identification, using a multi-fingered robotic hand equipped with proprioceptive sensing. Both methods are trained on known objects and rely on a limited set of features, obtained during a few grasps on an object. Contrary to most methods in the literature, our methods do not rely on the knowledge of the relative pose between object and hand, which greatly expands the domain of application. However, if that knowledge is available, w…

This https://arxiv.org/abs/2211.00912 has been replaced.
link: https://scholar.google.com/scholar?q=a

Bipartite mixed membership distribution-free model. A novel model for community detection in overlapping bipartite weighted networks
Modeling and estimating mixed memberships for overlapping unipartite un-weighted networks has been well studied in recent years. However, to our knowledge, there is no model for a more general case, the overlapping bipartite weighted networks. To close this gap, we introduce a novel model, the Bipartite Mixed Membership Distribution-Free (BiMMDF) model. Our model allows an adjacency matrix to follow any distribution as long as its expectation has a block structure related to node membership. In…

Coexistence of eMBB and mMTC in Uplink Cell-Free Massive MIMO Networks
Sergi Liesegang, Stefano Buzzi
https://arxiv.org/abs/2404.19117 https://

Coexistence of eMBB+ and mMTC+ in Uplink Cell-Free Massive MIMO Networks
This paper tackles the problem of designing proper uplink multiple access (MA) schemes for coexistence between enhanced mobile broadband+ (eMBB+) users and massive machine-type communications+ (mMTC+) devices in a terminal-centric cell-free massive MIMO system. Specifically, the use of a time-frequency spreading technique for the mMTC+ devices has been proposed. Coupled with the assumption of imperfect channel knowledge, closed-form bounds of the achievable (ergodic) rate for the two types of d…

FedD2S: Personalized Data-Free Federated Knowledge Distillation
Kawa Atapour, S. Jamal Seyedmohammadi, Jamshid Abouei, Arash Mohammadi, Konstantinos N. Plataniotis
https://arxiv.org/abs/2402.10846

FedD2S: Personalized Data-Free Federated Knowledge Distillation
This paper addresses the challenge of mitigating data heterogeneity among clients within a Federated Learning (FL) framework. The model-drift issue, arising from the noniid nature of client data, often results in suboptimal personalization of a global model compared to locally trained models for each client. To tackle this challenge, we propose a novel approach named FedD2S for Personalized Federated Learning (pFL), leveraging knowledge distillation. FedD2S incorporates a deep-to-shallow layer-…

I am getting old.
The many hoops of pre-requisite knowledge and specific software skills and ‘free by request to download at one not-Google place’ is more hoopage than my mild curiosity in a local LLM can manage.
I’m going for my nap. I’ll wake up for my evening meds later. https://mastodon.socia…

Ars Technica (@arstechnica@mastodon.social)
Attached: 1 image Google goes “open AI” with Gemma, a free, open-weights chatbot family Gemma chatbots can run locally, and they reportedly outperform Meta's Llama 2. https://arstechnica.com/information-technology/2024/02/google-goes-open-ai-with-gemma-a-free-open-weights-chatbot-family/?utm_brand=arstechnica&utm_social-type=owned&utm_source=mastodon&utm_medium=social

This https://arxiv.org/abs/2211.01126 has been replaced.
link: https://scholar.google.com/scholar?q=a

Likelihood-free hypothesis testing
Consider the problem of binary hypothesis testing. Given $Z$ coming from either $\mathbb P^{\otimes m}$ or $\mathbb Q^{\otimes m}$, to decide between the two with small probability of error it is sufficient, and in many cases necessary, to have $m\asymp1/ε^2$, where $ε$ measures the separation between $\mathbb P$ and $\mathbb Q$ in total variation ($\mathsf{TV}$). Achieving this, however, requires complete knowledge of the distributions and can be done, for example, using the Neyman-Pearson t…

This https://arxiv.org/abs/2403.18442 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Backpropagation-free Network for 3D Test-time Adaptation
Real-world systems often encounter new data over time, which leads to experiencing target domain shifts. Existing Test-Time Adaptation (TTA) methods tend to apply computationally heavy and memory-intensive backpropagation-based approaches to handle this. Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data. Our model uses a two-stream architecture to maintain knowledge about the source domain as well as complementary target-domain-sp…

Cool matter distribution in inner solar corona from 2023 total solar eclipse observation
Z. Q. Qu, H. Su, Y. Liang, Z. Xu, R. Y. Zhou
https://arxiv.org/abs/2404.18563

Cool matter distribution in inner solar corona from 2023 total solar eclipse observation
Solar corona has been judged to consist of free electrons and highly ionized ions with extremely high temperature as a widely accepted knowledge. This view is changed by our eclipse observations. Distributions of cool matter represented by neutral iron atoms in hot inner solar corona are presented via derived global maps of solar Fraunhofer(F-) and Emission(E-) coronae, compared with those of continuum(Kontinuierlich, K-) corona formed by free electrons. The maps are obtained from simultaneous …

This https://arxiv.org/abs/2403.13688 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Scalable Projection-Free Optimization Methods via MultiRadial Duality Theory
Recent works have developed new projection-free first-order methods based on utilizing linesearches and normal vector computations to maintain feasibility. These oracles can be cheaper than orthogonal projection or linear optimization subroutines but have the drawback of requiring a known strictly feasible point to do these linesearches with respect to. In this work, we develop new theory and algorithms which can operate using these cheaper linesearches while only requiring knowledge of points …

MisGUIDE : Defense Against Data-Free Deep Learning Model Extraction
Mahendra Gurve, Sankar Behera, Satyadev Ahlawat, Yamuna Prasad
https://arxiv.org/abs/2403.18580

MisGUIDE : Defense Against Data-Free Deep Learning Model Extraction
The rise of Machine Learning as a Service (MLaaS) has led to the widespread deployment of machine learning models trained on diverse datasets. These models are employed for predictive services through APIs, raising concerns about the security and confidentiality of the models due to emerging vulnerabilities in prediction APIs. Of particular concern are model cloning attacks, where individuals with limited data and no knowledge of the training dataset manage to replicate a victim model's functio…

This https://arxiv.org/abs/2402.18678 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

RORA: Robust Free-Text Rationale Evaluation
Free-text rationales play a pivotal role in explainable NLP, bridging the knowledge and reasoning gaps behind a model's decision-making. However, due to the diversity of potential reasoning paths and a corresponding lack of definitive ground truth, their evaluation remains a challenge. Existing evaluation metrics rely on the degree to which a rationale supports a target label, but we find these fall short in evaluating rationales that inadvertently leak the labels. To address this problem, we p…

I finally setup a robots.txt to prevent my site from being scraped by AI bots:
http://idbrii.com/robots.txt
(Hopefully I got everything right.)
Not totally against AI, but I post my stuff free and without ads to spread knowledge. Scraping the web to create closed models behind paywall…

Distilling Privileged Information for Dubins Traveling Salesman Problems with Neighborhoods
Min Kyu Shin, Su-Jeong Park, Seung-Keol Ryu, Heeyeon Kim, Han-Lim Choi
https://arxiv.org/abs/2404.16721

Distilling Privileged Information for Dubins Traveling Salesman Problems with Neighborhoods
This paper presents a novel learning approach for Dubins Traveling Salesman Problems(DTSP) with Neighborhood (DTSPN) to quickly produce a tour of a non-holonomic vehicle passing through neighborhoods of given task points. The method involves two learning phases: initially, a model-free reinforcement learning approach leverages privileged information to distill knowledge from expert trajectories generated by the LinKernighan heuristic (LKH) algorithm. Subsequently, a supervised learning phase tr…

Identification of SNPs in genomes using GRAMEP, an alignment-free method based on the Principle of Maximum Entropy
Matheus Henrique Pimenta-Zanon, Andr\'e Yoshiaki Kashiwabara, Andr\'e Lu\'is Laforga Vanzela, Fabricio Martins Lopes
https://arxiv.org/abs/2405.01715

Identification of SNPs in genomes using GRAMEP, an alignment-free method based on the Principle of Maximum Entropy
Advances in high throughput sequencing technologies provide a large number of genomes to be analyzed, so computational methodologies play a crucial role in analyzing and extracting knowledge from the data generated. Investigating genomic mutations is critical because of their impact on chromosomal evolution, genetic disorders, and diseases. It is common to adopt aligning sequences for analyzing genomic variations, however, this approach can be computationally expensive and potentially arbitrary…

KTbench: A Novel Data Leakage-Free Framework for Knowledge Tracing
Yahya Badran, Christine Preisach
https://arxiv.org/abs/2403.15304 https://

KTbench: A Novel Data Leakage-Free Framework for Knowledge Tracing
Knowledge Tracing (KT) is concerned with predicting students' future performance on learning items in intelligent tutoring systems. Learning items are tagged with skill labels called knowledge concepts (KCs). Many KT models expand the sequence of item-student interactions into KC-student interactions by replacing learning items with their constituting KCs. This often results in a longer sequence length. This approach addresses the issue of sparse item-student interactions and minimises model pa…

FhGenie: A Custom, Confidentiality-preserving Chat AI for Corporate and Scientific Use
Ingo Weber, Hendrik Linka, Daniel Mertens, Tamara Muryshkin, Heinrich Opgenoorth, Stefan Langer
https://arxiv.org/abs/2403.00039

FhGenie: A Custom, Confidentiality-preserving Chat AI for Corporate and Scientific Use
Since OpenAI's release of ChatGPT, generative AI has received significant attention across various domains. These AI-based chat systems have the potential to enhance the productivity of knowledge workers in diverse tasks. However, the use of free public services poses a risk of data leakage, as service providers may exploit user input for additional training and optimization without clear boundaries. Even subscription-based alternatives sometimes lack transparency in handling user data. To addr…

This https://arxiv.org/abs/2302.07289 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

A Parameter-Free Tour of the Binary Black Hole Population
The continued operation of the Advanced LIGO and Advanced Virgo gravitational-wave detectors is enabling the first detailed measurements of the mass, spin, and redshift distributions of the merging binary black hole population. Our present knowledge of these distributions, however, is based largely on strongly parameteric models; such models typically assume the distributions of binary parameters to be superpositions of power laws, peaks, dips, and breaks, and then measure the parameters govern…

This https://arxiv.org/abs/2309.14510 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

An Empathy-Based Sandbox Approach to Bridge the Privacy Gap among Attitudes, Goals, Knowledge, and Behaviors
Managing privacy to reach privacy goals is challenging, as evidenced by the privacy attitude-behavior gap. Mitigating this discrepancy requires solutions that account for both system opaqueness and users' hesitations in testing different privacy settings due to fears of unintended data exposure. We introduce an empathy-based approach that allows users to experience how privacy attributes may alter system outcomes in a risk-free sandbox environment from the perspective of artificially generated …

This https://arxiv.org/abs/2308.11959 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Scalable δ-Level Coherent State Synchronization of Multi-Agent Systems in the Presence of Bounded Disturbances
In this paper, we study scalable δ-Level coherent state synchronization for multi-agent systems (MAS) where the agents are subject to bounded disturbances/noises. We propose a scale-free framework designed solely based on the knowledge of agent models and agnostic to the communication graphs and size of the network. We define the level of coherency for each agent as the norm of the weighted sum of the disagreement dynamics with its neighbors. The objective is to restrict the level of coherency…

Scalable Projection-Free Optimization Methods via MultiRadial Duality Theory
Thabo Samakhoana, Benjamin Grimmer
https://arxiv.org/abs/2403.13688 https://…

Scalable Projection-Free Optimization Methods via MultiRadial Duality Theory
Recent works have developed new projection-free first-order methods based on utilizing linesearches and normal vector computations to maintain feasibility. These oracles can be cheaper than orthogonal projection or linear optimization subroutines but have the drawback of requiring a known strictly feasible point to do these linesearches with respect to. In this work, we develop new theory and algorithms which can operate using these cheaper linesearches while only requiring knowledge of points …

Bridging the Gap Between Theory and Practice: Benchmarking Transfer Evolutionary Optimization
Yaqing Hou, Wenqiang Ma, Abhishek Gupta, Kavitesh Kumar Bali, Hongwei Ge, Qiang Zhang, Carlos A. Coello Coello, Yew-Soon Ong
https://arxiv.org/abs/2404.13377

Bridging the Gap Between Theory and Practice: Benchmarking Transfer Evolutionary Optimization
In recent years, the field of Transfer Evolutionary Optimization (TrEO) has witnessed substantial growth, fueled by the realization of its profound impact on solving complex problems. Numerous algorithms have emerged to address the challenges posed by transferring knowledge between tasks. However, the recently highlighted ``no free lunch theorem'' in transfer optimization clarifies that no single algorithm reigns supreme across diverse problem types. This paper addresses this conundrum by adopt…

This https://arxiv.org/abs/2310.08869 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection
Most research in synthetic speech detection (SSD) focuses on improving performance on standard noise-free datasets. However, in actual situations, noise interference is usually present, causing significant performance degradation in SSD systems. To improve noise robustness, this paper proposes a dual-branch knowledge distillation synthetic speech detection (DKDSSD) method. Specifically, a parallel data flow of the clean teacher branch and the noisy student branch is designed, and interactive fu…

This https://arxiv.org/abs/2308.05788 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Correlated electrons tunneling through pseudo Fermi arcs in hyperbolic Fermi surfaces of topological materials
Understanding the intricate relationship between Fermi surface (FS) and electron transport in materials is crucial for advancing our knowledge of condensed matter physics. Commonly, FS properties are used to predict current within the framework of Fermi-liquid theory, where locally on the FS electron behavior can be estimated by nearly free election gas with slowly switched-on interactions. In this study, we go beyond the limits of this theory and explore how the geometry of the FS can result i…

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…

Machine learning for climate physics and simulations
Ching-Yao Lai, Pedram Hassanzadeh, Aditi Sheshadri, Maike Sonnewald, Raffaele Ferrari, Venkatramani Balaji
https://arxiv.org/abs/2404.13227

Machine learning for climate physics and simulations
We discuss the emerging advances and opportunities at the intersection of machine learning (ML) and climate physics, highlighting the use of ML techniques, including supervised, unsupervised, and equation discovery, to accelerate climate knowledge discoveries and simulations. We delineate two distinct yet complementary aspects: (1) ML for climate physics and (2) ML for climate simulations. While physics-free ML-based models, such as ML-based weather forecasting, have demonstrated success when d…

This https://arxiv.org/abs/2403.05881 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques
Large Language Models (LLMs) have significantly advanced healthcare innovation on generation capabilities. However, their application in real clinical settings is challenging due to potential deviations from medical facts and inherent biases. In this work, we develop an augmented LLM framework, KG-Rank, which leverages a medical knowledge graph (KG) with ranking and re-ranking techniques, aiming to improve free-text question-answering (QA) in the medical domain. Specifically, upon receiving a q…

This https://arxiv.org/abs/2404.00044 has been replaced.
link: https://scholar.google.com/scholar?q=a

UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment
Motivation: Retrosynthesis planning poses a formidable challenge in the organic chemical industry. Single-step retrosynthesis prediction, a crucial step in the planning process, has witnessed a surge in interest in recent years due to advancements in AI for science. Various deep learning-based methods have been proposed for this task in recent years, incorporating diverse levels of additional chemical knowledge dependency. Results: This paper introduces UAlign, a template-free graph-to-sequen…

This https://arxiv.org/abs/2210.04047 has been replaced.
link: https://scholar.google.com/scholar?q=a

Motion Planning on Visual Manifolds
In this thesis, we propose an alternative characterization of the notion of Configuration Space, which we call Visual Configuration Space (VCS). This new characterization allows an embodied agent (e.g., a robot) to discover its own body structure and plan obstacle-free motions in its peripersonal space using a set of its own images in random poses. Here, we do not assume any knowledge of geometry of the agent, obstacles or the environment. We demonstrate the usefulness of VCS in (a) building an…

This https://arxiv.org/abs/2310.08869 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection
Most research in synthetic speech detection (SSD) focuses on improving performance on standard noise-free datasets. However, in actual situations, noise interference is usually present, causing significant performance degradation in SSD systems. To improve noise robustness, this paper proposes a dual-branch knowledge distillation synthetic speech detection (DKDSSD) method. Specifically, a parallel data flow of the clean teacher branch and the noisy student branch is designed, and interactive fu…

This https://arxiv.org/abs/2205.13055 has been replaced.
link: https://scholar.google.com/scholar?q=a

Complexity-optimal and Parameter-free First-order Methods for Finding Stationary Points of Composite Optimization Problems
This paper develops and analyzes an accelerated proximal descent method for finding stationary points of nonconvex composite optimization problems. The objective function is of the form $f+h$ where $h$ is a proper closed convex function, $f$ is a differentiable function on the domain of $h$, and $\nabla f$ is Lipschitz continuous on the domain of $h$. The main advantage of this method is that it is "parameter-free" in the sense that it does not require knowledge of the Lipschitz constant of $\n…

Machine learning for climate physics and simulations
Ching-Yao Lai, Pedram Hassanzadeh, Aditi Sheshadri, Maike Sonnewald, Raffaele Ferrari, Venkatramani Balaji
https://arxiv.org/abs/2404.13227

Machine learning for climate physics and simulations
We discuss the emerging advances and opportunities at the intersection of machine learning (ML) and climate physics, highlighting the use of ML techniques, including supervised, unsupervised, and equation discovery, to accelerate climate knowledge discoveries and simulations. We delineate two distinct yet complementary aspects: (1) ML for climate physics and (2) ML for climate simulations. While physics-free ML-based models, such as ML-based weather forecasting, have demonstrated success when d…

This https://arxiv.org/abs/2404.00044 has been replaced.
link: https://scholar.google.com/scholar?q=a

UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment
Motivation: Retrosynthesis planning poses a formidable challenge in the organic chemical industry. Single-step retrosynthesis prediction, a crucial step in the planning process, has witnessed a surge in interest in recent years due to advancements in AI for science. Various deep learning-based methods have been proposed for this task in recent years, incorporating diverse levels of additional chemical knowledge dependency. Results: This paper introduces UAlign, a template-free graph-to-sequen…