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

May 30, 2024

SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning
Avetik Karagulyan, Egor Shulgin, Abdurakhmon Sadiev, Peter Richtárik
LeArning Abstract Convex Loss Cross Device Federated Learning Stochastic Proximal Point Data Similarity Cross Device
Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf
Xuanfa Jin, Ziyan Wang, Yali Du, Meng Fang, Haifeng Zhang, Jun Wang
Reinforcement Learning LeArning Abstract Case Study Language Agent Discussion Paper Dialogue Policy Werewolf Game Discussion Mechanism
Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition
Masashi Hatano, Ryo Hachiuma, Ryo Fujii, Hideo Saito
LeArning Abstract Multi Modal Egocentric Video Cross Domain Few Shot Learning Egocentric Data Egocentric Action Recognition Multimodal Distillation
Learning from Random Demonstrations: Offline Reinforcement Learning with Importance-Sampled Diffusion Models
Zeyu Fang, Tian Lan
LeArning Abstract Diffusion Model Offline Reinforcement Learning Policy Evaluation Offline Policy Evaluation Predictive World Model

May 29, 2024

Learning to Recover from Plan Execution Errors during Robot Manipulation: A Neuro-symbolic Approach
Namasivayam Kalithasan, Arnav Tuli, Vishal Bindal, Himanshu Gaurav Singh, Parag Singla, Rohan Paul
LeArning Abstract Autonomous Robot Neuro Symbolic Robot Manipulation Error Detection State Representation Prompt Recovery Symbolic Computation Neuro Symbolic Approach
Learning Mixture-of-Experts for General-Purpose Black-Box Discrete Optimization
Shengcai Liu, Zhiyuan Wang, Yew-Soon Ong, Xin Yao, Ke Tang
Neural Network LeArning Abstract Better Optimizers Data Driven Optimization General Purpose
Learning to Continually Learn with the Bayesian Principle
Soochan Lee, Hyeonseong Jeon, Jaehyeon Son, Gunhee Kim
LeArning Abstract Continual LEArning Catastrophic Forgetting Continual Learning Meta Learning Meta Continual Learning
Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain
Juntao Zhang, Kun Bian, Peng Cheng, Wenbo An, Jianning Liu, Jun Zhou
LeArning Abstract Vision Transformer Deep Learning Model Long Sequence Frequency Domain Visual State Space Model GTR CTRL

May 28, 2024

Learning from Uncertain Data: From Possible Worlds to Possible Models
Jiongli Zhu, Su Feng, Boris Glavic, Babak Salimi
LeArning Abstract Gradient Descent Prediction Uncertainty Data Uncertainty Diverse Model Optimal Model Predictive Multiplicity Possible World
Learning Staged Trees from Incomplete Data
Jack Storror Carter, Manuele Leonelli, Eva Riccomagno, Gherardo Varando
LeArning Abstract Tree Specie Probabilistic Graphical Model Structure Learning Incomplete Data Tree Model Pseudo Likelihood Different Missingness
From Learning to Optimize to Learning Optimization Algorithms
Camille Castera, Peter Ochs
LeArning Abstract Optimization Algorithm Learned Optimizers Classical Algorithm Classical Optimization L BFGS
Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation
JuneHyoung Kwon, Eunju Lee, Yunsung Cho, YoungBin Kim
LeArning Abstract Semantic Segmentation Pixel Level Weakly Supervised Semantic Segmentation Background Generation Efficient Augmentation

May 27, 2024

Learning with User-Level Local Differential Privacy
Puning Zhao, Li Shen, Rongfei Fan, Qingming Li, Huiwen Wu, Jiafei Wu, Zhe Liu
LeArning Abstract Information Theoretic User Level Differential Privacy Privacy Level
Hawk: Learning to Understand Open-World Video Anomalies
Jiaqi Tang, Hao Lu, Ruizheng Wu, Xiaogang Xu, Ke Ma, Cheng Fang, Bin Guo, Jiangbo Lu, Qifeng Chen, Ying-Cong Chen
LeArning Abstract Video Anomaly Detection Video Anomaly Motion Modality

May 24, 2024

Learning accurate and interpretable decision trees
Maria-Florina Balcan, Dravyansh Sharma
LeArning Abstract Decision Tree Bayesian Decision Tree
Learning the Language of Protein Structure
Benoit Gaujac, Jérémie Donà, Liviu Copoiu, Timothy Atkinson, Thomas Pierrot, Thomas D. Barrett
LeArning Abstract Human Language Protein Design Protein Structure Vector Quantized Variational Autoencoder Protein Model
Learning from Linear Algebra: A Graph Neural Network Approach to Preconditioner Design for Conjugate Gradient Solvers
Vladislav Trifonov, Alexander Rudikov, Oleg Iliev, Ivan Oseledets, Ekaterina Muravleva
LeArning Abstract Adaptive Preconditioner Conjugate Gradient Linear Algebra Iterative Solver Neural Preconditioners
Learning to Discretize Denoising Diffusion ODEs
Vinh Tong, Anji Liu, Trung-Dung Hoang, Guy Van den Broeck, Mathias Niepert
LeArning Abstract Generative Model Pre Trained Diffusion Model Diffusion Probabilistic Model Time Discretization Discrete Denoising Diffusion

LeArning Abstract

Papers

SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning

Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf

Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition

Learning from Random Demonstrations: Offline Reinforcement Learning with Importance-Sampled Diffusion Models

Learning to Recover from Plan Execution Errors during Robot Manipulation: A Neuro-symbolic Approach

Learning Mixture-of-Experts for General-Purpose Black-Box Discrete Optimization

Learning to Continually Learn with the Bayesian Principle

Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain

Learning from Uncertain Data: From Possible Worlds to Possible Models

Learning Staged Trees from Incomplete Data

From Learning to Optimize to Learning Optimization Algorithms

Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation

Learning with User-Level Local Differential Privacy

Hawk: Learning to Understand Open-World Video Anomalies

Learning to Reason via Program Generation, Emulation, and Search

Learning Visual-Semantic Subspace Representations for Propositional Reasoning

Learning accurate and interpretable decision trees

Learning the Language of Protein Structure

Learning from Linear Algebra: A Graph Neural Network Approach to Preconditioner Design for Conjugate Gradient Solvers

Learning to Discretize Denoising Diffusion ODEs