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

October 17, 2024

Diffusing States and Matching Scores: A New Framework for Imitation Learning
Runzhe Wu, Yiding Chen, Gokul Swamy, Kianté Brantley, Wen Sun
LeArning Abstract New Framework Imitation Learning GAN Model Adversarial Learning Feature Imitation Score Matching Adversarial Imitation Learning Adversarial Imitation
Enhancing Text Generation in Joint NLG/NLU Learning Through Curriculum Learning, Semi-Supervised Training, and Advanced Optimization Techniques
Rahimanuddin Shaik, Katikela Sreeharsha Kishore
Language Model LeArning Abstract Text Generation Language Understanding Natural Language Generation Natural Language Understanding Semi Supervised Training
Learning to Route with Confidence Tokens
Yu-Neng Chuang, Helen Zhou, Prathusha Kameswara Sarma, Parikshit Gopalan, John Boccio, Sara Bolouki, Xia Hu
Large Language Model LeArning Abstract Token Prediction Confidence Score Human Generated Route Token Level Uncertainty
From PINNs to PIKANs: Recent Advances in Physics-Informed Machine Learning
Juan Diego Toscano, Vivek Oommen, Alan John Varghese, Zongren Zou, Nazanin Ahmadi Daryakenari, Chenxi Wu, George Em Karniadakis
LeArning Abstract Physic Informed Neural Network Recent Advance Kolmogorov Arnold Network Computational Approach Scientific Machine Learning PINN Method Physic Informed Machine
Investigating Effective Speaker Property Privacy Protection in Federated Learning for Speech Emotion Recognition
Chao Tan, Sheng Li, Yang Cao, Zhao Ren, Tanja Schultz
LeArning Abstract Speech Emotion Recognition Speech Data Speech Processing Federated Prompt Cooperation Inference Attack Property Inference Attack

October 16, 2024

Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds
Xingzhi Sun, Danqi Liao, Kincaid MacDonald, Yanlei Zhang, Chen Liu, Guillaume Huguet, Guy Wolf, Ian Adelstein, Tim G. J. Rudner, Smita Krishnaswamy
LeArning Abstract Generative Modeling Manifold Learning Data Manifold Riemannian Metric Cell Clustering Geometric Generative Model
Learning to Predict Usage Options of Product Reviews with LLM-Generated Labels
Leo Kohlenberg, Leonard Horns, Frederic Sadrieh, Nils Kiele, Matthis Clausen, Konstantin Ketterer, Avetis Navasardyan, Tamara Czinczoll, Gerard de Melo, Ralf Herbrich
LeArning Abstract Greater Public Use Label Information Large Datasets Annotation System Sequence to Sequence Task Product Review
Improving the Generalization of Unseen Crowd Behaviors for Reinforcement Learning based Local Motion Planners
Wen Zheng Terence Ng, Jianda Chen, Sinno Jialin Pan, Tianwei Zhang
LeArning Abstract Strong Generalization Collision Avoidance Positive Reinforcement Robot Policy Multi Agent Framework Local Path Planning Conditioned Policy Crowd Dynamic
When to Trust Your Data: Enhancing Dyna-Style Model-Based Reinforcement Learning With Data Filter
Yansong Li, Zeyu Dong, Ertai Luo, Yu Wu, Shuo Wu, Shuo Han
Reinforcement Learning LeArning Abstract Raw Data Positive Reinforcement Free Learning Model Free Algorithm Data Filtering Dynamic Algorithm Model Based Policy

October 15, 2024

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
Fengyu Gao, Ruida Zhou, Tianhao Wang, Cong Shen, Jing Yang
LeArning Abstract Context Learning Different Context Differential Privacy Guarantee Private Datasets Non Private
Learning with Importance Weighted Variational Inference: Asymptotics for Gradient Estimators of the VR-IWAE Bound
Kamélia Daudel, François Roueff
LeArning Abstract Variational Inference Gradient Estimator Asymptotic Behavior Annealed Importance Sampling Matrix Based Variational Bound
LocoMotion: Learning Motion-Focused Video-Language Representations
Hazel Doughty, Fida Mohammad Thoker, Cees G. M. Snoek
LeArning Abstract Human Like Locomotion Behavior Video Language Representation Synthesized Motion
Learning Goal-oriented Bimanual Dough Rolling Using Dynamic Heterogeneous Graph Based on Human Demonstration
Junjia Liu, Chenzui Li, Shixiong Wang, Zhipeng Dong, Sylvain Calinon, Miao Li, Fei Chen
LeArning Abstract Heterogeneous Graph Policy Learning Human Demonstration Manipulation Policy Object Dynamic Soft Body Manipulation Bi Manual
Advanced Persistent Threats (APT) Attribution Using Deep Reinforcement Learning
Animesh Singh Basnet, Mohamed Chahine Ghanem, Dipo Dunsin, Wiktor Sowinski-Mydlarz
LeArning Abstract Deep Reinforcement Learning Deep Reinforcement Source Attribution Advanced Persistent Threat Malware Representation Behavioural Analysis Threat Attribution
Towards More Effective Table-to-Text Generation: Assessing In-Context Learning and Self-Evaluation with Open-Source Models
Sahar Iravani, Tim .O .F Conrad
Large Language Model Language Model LeArning Abstract Natural Language Processing Different Context Open Source Model Self Feedback Table to Text Generation Traditional Evaluation Metric
Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning
Minoo Jafarlou, Mario M. Kubek
LeArning Abstract Semi Supervised Learning Sentiment Analysis Pseudo Label Label Propagation Label Efficiency
Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning
Jingyang Li, Jiachun Pan, Vincent Y. F. Tan, Kim-Chuan Toh, Pan Zhou
LeArning Abstract Convolutional Neural Network Deep Neural Network Semantic Class

LeArning Abstract

Papers

Explainable AI in Handwriting Detection for Dyslexia Using Transfer Learning

Fine-Tuning Pre-trained Language Models for Robust Causal Representation Learning

Learning autonomous driving from aerial imagery

Diffusing States and Matching Scores: A New Framework for Imitation Learning

Enhancing Text Generation in Joint NLG/NLU Learning Through Curriculum Learning, Semi-Supervised Training, and Advanced Optimization Techniques

Learning to Route with Confidence Tokens

From PINNs to PIKANs: Recent Advances in Physics-Informed Machine Learning

Investigating Effective Speaker Property Privacy Protection in Federated Learning for Speech Emotion Recognition

Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds

Learning to Predict Usage Options of Product Reviews with LLM-Generated Labels

Improving the Generalization of Unseen Crowd Behaviors for Reinforcement Learning based Local Motion Planners

When to Trust Your Data: Enhancing Dyna-Style Model-Based Reinforcement Learning With Data Filter

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning

Learning with Importance Weighted Variational Inference: Asymptotics for Gradient Estimators of the VR-IWAE Bound

LocoMotion: Learning Motion-Focused Video-Language Representations

Learning Goal-oriented Bimanual Dough Rolling Using Dynamic Heterogeneous Graph Based on Human Demonstration

Advanced Persistent Threats (APT) Attribution Using Deep Reinforcement Learning

Towards More Effective Table-to-Text Generation: Assessing In-Context Learning and Self-Evaluation with Open-Source Models

Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning

Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning