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

November 21, 2024

Learning Two-agent Motion Planning Strategies from Generalized Nash Equilibrium for Model Predictive Control
Hansung Kim, Edward L. Zhu, Chang Seok Lim, Francesco Borrelli
LeArning Abstract Predictive Control Game Theoretic Equilibrium State Agent Motion Multi Agent Motion Planning
Cooperative Grasping and Transportation using Multi-agent Reinforcement Learning with Ternary Force Representation
Ing-Sheng Bernard-Tiong, Yoshihisa Tsurumine, Ryosuke Sota, Kazuki Shibata, Takamitsu Matsubara
LeArning Abstract Multi Agent Reinforcement Learning Transportation System Ternary Neural Network Grip Force

November 20, 2024

Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios
Shantanu Jaiswal, Debaditya Roy, Basura Fernando, Cheston Tan
LeArning Abstract Spatio Temporal Reasoning Ability Visual Reasoning Iterative Neural Network Visual Complexity
AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations
Gaurav Verma, Rachneet Kaur, Nishan Srishankar, Zhen Zeng, Tucker Balch, Manuela Veloso
LeArning Abstract Meta Learning Human Demonstration Multimodal Agent Adaptive Agent
Learning based Ge'ez character handwritten recognition
Hailemicael Lulseged Yimer, Hailegabriel Dereje Degefa, Marco Cristani, Federico Cunico
LeArning Abstract Long Short Term Memory Handwriting Recognition Handwritten Document Recognition Amharic Scene Text
Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning
Tim Lenz, Peter Neidlinger, Marta Ligero, Georg Wölflein, Marko van Treeck, Jakob Nikolas Kather
LeArning Abstract State of the Art Encoders Slide Representation Histopathology Foundation Model
Intensity-Spatial Dual Masked Autoencoder for Multi-Scale Feature Learning in Chest CT Segmentation
Yuexing Ding, Jun Wang, Hongbing Lyu
LeArning Abstract Masked Autoencoders Multi Scale Feature Masked AutoEncoder Feature Masking Lung Originated Tumor Segmentation
MEGL: Multimodal Explanation-Guided Learning
Yifei Zhang, Tianxu Jiang, Bo Pan, Jingyu Wang, Guangji Bai, Liang Zhao
LeArning Abstract Multimodal Phenomenon Visual Explanation Textual Explanation Unimodal Bias
A Theory for Compressibility of Graph Transformers for Transductive Learning
Hamed Shirzad, Honghao Lin, Ameya Velingker, Balaji Venkatachalam, David Woodruff, Danica Sutherland
LeArning Abstract Theoretical Understanding Graph Transformer Sparse Attention Attention Matrix Machine Learning Task

November 19, 2024

Learning multivariate Gaussians with imperfect advice
Arnab Bhattacharyya, Davin Choo, Philips George John, Themis Gouleakis
LeArning Abstract Sample Complexity RSD Difference of Gaussian Gaussian Distribution PAC Learning Learning Augmented Algorithm Advice Quality
Learning from Label Proportions and Covariate-shifted Instances
Sagalpreet Singh, Navodita Sharma, Shreyas Havaldar, Rishi Saket, Aravindan Raghuveer
LeArning Abstract Covariate Shift Label Proportion Instance Level Label Instance Prediction
Prototype Optimization with Neural ODE for Few-Shot Learning
Baoquan Zhang, Shanshan Feng, Bingqi Shan, Xutao Li, Yunming Ye, Yew-Soon Ong
LeArning Abstract Neural Ordinary Differential Equation Latent Prototype Meta Optimization Prototype Adaptation Prototype Quality
UrbanDiT: A Foundation Model for Open-World Urban Spatio-Temporal Learning
Yuan Yuan, Chonghua Han, Jingtao Ding, Depeng Jin, Yong Li
LeArning Abstract Foundation Model Open World Urban Environment Spatio Temporal Prediction Spatio Temporal Learning
Reinforcement Learning with Action Sequence for Data-Efficient Robot Learning
Younggyo Seo, Pieter Abbeel
Reinforcement Learning LeArning Abstract Behavior Cloning Action Sequence Humanoid Control

November 18, 2024

Hierarchical-Graph-Structured Edge Partition Models for Learning Evolving Community Structure
Xincan Yu, Sikun Yang
LeArning Abstract Community Detection Dynamic Network Temporal Network Community Structure Network Dynamic
LeC$^2$O-NeRF: Learning Continuous and Compact Large-Scale Occupancy for Urban Scenes
Zhenxing Mi, Dan Xu
LeArning Abstract Embracing CompAct Urban Scene Occupancy Grid Occupancy Network REF$^2$ NeRF
Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
Yang Chen, Jingcai Guo, Song Guo, Dacheng Tao
LeArning Abstract Zero Shot Action Recognition Meaningful Representation Single Neuron Level Skeleton Representation Fine Grained Cross Modal Alignment
Artificial Intelligence Mangrove Monitoring System Based on Deep Learning and Sentinel-2 Satellite Data in the UAE (2017-2024)
Linlin Tan, Haishan Wu
LeArning Abstract Sentinel 2 Coastline Detection

November 17, 2024

CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning
Depeng Chen, Xiao Liu, Jie Cui, Hong Zhong (School of Computer Science and Technology, Anhui University)
LeArning Abstract Machine Learning Model Membership Inference Attack Attack Method Attack Model
Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning
Ting Zhu, Yue Jin, Jeremie Houssineau, Giovanni Montana
LeArning Abstract Collaborative Task Minimax Q Learning Relative Over Generalization Joint Policy

LeArning Abstract

Papers

Learning Two-agent Motion Planning Strategies from Generalized Nash Equilibrium for Model Predictive Control

Cooperative Grasping and Transportation using Multi-agent Reinforcement Learning with Ternary Force Representation

Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios

AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations

Learning based Ge'ez character handwritten recognition

Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning

Intensity-Spatial Dual Masked Autoencoder for Multi-Scale Feature Learning in Chest CT Segmentation

MEGL: Multimodal Explanation-Guided Learning

A Theory for Compressibility of Graph Transformers for Transductive Learning

Learning multivariate Gaussians with imperfect advice

Learning from Label Proportions and Covariate-shifted Instances

Prototype Optimization with Neural ODE for Few-Shot Learning

UrbanDiT: A Foundation Model for Open-World Urban Spatio-Temporal Learning

Reinforcement Learning with Action Sequence for Data-Efficient Robot Learning

Hierarchical-Graph-Structured Edge Partition Models for Learning Evolving Community Structure

LeC$^2$O-NeRF: Learning Continuous and Compact Large-Scale Occupancy for Urban Scenes

Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition

Artificial Intelligence Mangrove Monitoring System Based on Deep Learning and Sentinel-2 Satellite Data in the UAE (2017-2024)

CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning

Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning