LeArning Abstract

Learning, in the context of these papers, encompasses a broad range of research focused on improving the efficiency, robustness, and adaptability of machine learning models across diverse applications. Current efforts concentrate on developing novel self-supervised learning techniques, particularly for structured data like tabular formats, and on leveraging low-rank adaptations for efficient fine-tuning of large language and other foundation models. These advancements are significant because they address key challenges in data efficiency, computational cost, and the generalization capabilities of machine learning systems, impacting fields ranging from personalized medicine to autonomous robotics.

Papers

December 12, 2024

Stellar parameter prediction and spectral simulation using machine learning
Vojtěch Cvrček, Martino Romaniello, Radim Šára, Wolfram Freudling, Pascal Ballester
LeArning Abstract New Machine Reference Dataset Spectral Model Stellar Parameter Radial Velocity Stellar Spectrum
Structurally Consistent MRI Colorization using Cross-modal Fusion Learning
Mayuri Mathur, Anav Chaudhary, Saurabh Kumar Gupta, Ojaswa Sharma
LeArning Abstract Image Colorization Color Transfer
Words of War: Exploring the Presidential Rhetorical Arsenal with Deep Learning
Wyatt Scott, Brett Genz, Sarah Elmasry, Sodiq Adewole
LeArning Abstract Word List Political Discourse Rhetorical Structure

December 11, 2024

Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
Prajwal Koirala, Zhanhong Jiang, Soumik Sarkar, Cody Fleming
LeArning Abstract Intermediate Latent Conditional Variational Offline Safe Reinforcement Learning
TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning
Jimmy Wu, William Chong, Robert Holmberg, Aaditya Prasad, Yihuai Gao, Oussama Khatib, Shuran Song, Szymon Rusinkiewicz, Jeannette Bohg
LeArning Abstract Robot Person Imitation Learning Mobile Manipulator Mobile Manipulation Teleoperation Framework
Learning Sketch Decompositions in Planning via Deep Reinforcement Learning
Michael Aichmüller, Hector Geffner
Reinforcement Learning LeArning Abstract Deep Reinforcement Learning Task Planning Deep Reinforcement Classical Planning Sketch Based Sketch Extraction
Improving Satellite Imagery Masking using Multi-task and Transfer Learning
Rangel Daroya, Luisa Vieira Lucchese, Travis Simmons, Punwath Prum, Tamlin Pavelsky, John Gardner, Colin J. Gleason, Subhransu Maji
LeArning Abstract Multi Task Formality Transfer Satellite Imagery Mask Guided Cloud Detection Landsat 8
Protecting Confidentiality, Privacy and Integrity in Collaborative Learning
Dong Chen, Alice Dethise, Istemi Ekin Akkus, Ivica Rimac, Klaus Satzke, Antti Koskela, Marco Canini, Wei Wang, Ruichuan Chen
LeArning Abstract Differential Privacy Privacy Policy Model Training Privacy Mechanism Privacy Preserving Training Dataset Management
Comparative Opinion Mining in Product Reviews: Multi-perspective Prompt-based Learning
Hai-Yen Thi Nguyen, Cam-Van Thi Nguyen
LeArning Abstract Opinion Mining Product Review Prompt LEarning Argument Quadruplet Extraction
Learning to Reason via Self-Iterative Process Feedback for Small Language Models
Kaiyuan Chen, Jin Wang, Xuejie Zhang
Large Language Model Language Model LeArning Abstract Domain Generalization Supervised Fine Tuning Preference Optimization Reason Giving Small Scale
Structured IB: Improving Information Bottleneck with Structured Feature Learning
Hanzhe Yang, Youlong Wu, Dingzhu Wen, Yong Zhou, Yuanming Shi
LeArning Abstract Information Bottleneck Lagrangian Multiplier
Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning
Chongyi Zheng, Jens Tuyls, Joanne Peng, Benjamin Eysenbach
LeArning Abstract Self Supervised Learning General Analysis Skill Learning Modern Reinforcement Learning Successor Feature Key Ingredient
Adaptive Querying for Reward Learning from Human Feedback
Yashwanthi Anand, Sandhya Saisubramanian
LeArning Abstract Human Feedback Reward Learning Feedback Mechanism Adaptive Query

December 10, 2024

Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning
Can Yaras, Siyi Chen, Peng Wang, Qing Qu
LeArning Abstract Contrastive Learning Line by Line Explanation Multimodal Learning Modality Gap
Predicting NOx emissions in Biochar Production Plants using Machine Learning
Marius Köppel, Niklas Witzig, Tim Klausmann, Mattia Cerrato, Tobias Schweitzer, Jochen Weber, Erdem Yilmaz, Juan Chimbo, Bernardo del Campo, Lissete Davila, David Barreno
LeArning Abstract New Machine
Predictive Modeling of Homeless Service Assignment: A Representation Learning Approach
Khandker Sadia Rahman, Charalampos Chelmis
LeArning Abstract Latent Representation Predictive Model Individual Representation Relation Pattern Learning Approach
Real-time Sign Language Recognition Using MobileNetV2 and Transfer Learning
Smruti Jagtap, Kanika Jadhav, Rushikesh Temkar, Minal Deshmukh
LeArning Abstract Convolutional Neural Network Formality Transfer Sign Language Indian Language Sign Language Recognition L MobileNet Language Recognition
MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning
Yufei Ma, Zihan Liang, Huangyu Dai, Ben Chen, Dehong Gao, Zhuoran Ran, Wang Zihan, Linbo Jin, Wen Jiang, Guannan Zhang, Xiaoyan Cai, Libin Yang
LeArning Abstract Multi Task Learning Multi Task Domain Specific Hui Walter Paradigm Fast LoRA LLM Based Framework
Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networks
Junwei Su, Shan Wu
LeArning Abstract Network Programming Temporal Graph Neural Network Time Series Clustering Volatility Surface
A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning
Jacob Adkins, Michael Bowling, Adam White
LeArning Abstract Practical Method Hyperparameter Tuning Related Hyperparameters Positive Reinforcement Hyperparameter Configuration Modern Reinforcement Learning Hyperparameter Importance

LeArning Abstract

Papers

Stellar parameter prediction and spectral simulation using machine learning

Structurally Consistent MRI Colorization using Cross-modal Fusion Learning

Words of War: Exploring the Presidential Rhetorical Arsenal with Deep Learning

Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning

TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning

Learning Sketch Decompositions in Planning via Deep Reinforcement Learning

Improving Satellite Imagery Masking using Multi-task and Transfer Learning

Protecting Confidentiality, Privacy and Integrity in Collaborative Learning

Comparative Opinion Mining in Product Reviews: Multi-perspective Prompt-based Learning

Learning to Reason via Self-Iterative Process Feedback for Small Language Models

Structured IB: Improving Information Bottleneck with Structured Feature Learning

Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning

Adaptive Querying for Reward Learning from Human Feedback

Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning

Predicting NOx emissions in Biochar Production Plants using Machine Learning

Predictive Modeling of Homeless Service Assignment: A Representation Learning Approach

Real-time Sign Language Recognition Using MobileNetV2 and Transfer Learning

MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning

Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networks

A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning