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.

2549papers

Papers

April 3, 2025

Integrating Human Knowledge Through Action Masking in Reinforcement Learning for Operations Research
Action Masking Heuristic Rule Near Optimal Action Space Reinforcement Learning Operation Research Knowledge Integration LeArning Abstract Positive Reinforcement
Learning Geometrically-Informed Lyapunov Functions with Deep Diffeomorphic RBF Networks
Lyapunov Function LeArning Abstract Radial Basis Function
Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval
Video Text Retrieval Text Video Retrieval Video Representation Video Representation Learning Gated Attention LeArning Abstract Video Understanding Multimodal Retrieval
Toward General and Robust LLM-enhanced Text-attributed Graph Learning
Text Attributed Graph LeArning Abstract Robust Version
MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception
Multi Axis Attention Cross Task Knowledge Vehicle Perception Unified Framework LeArning Abstract Multi Attention
Learning and Improving Backgammon Strategy
Value Function Game Tree TD Learning Monte Carlo Game Solving LeArning Abstract

April 2, 2025

Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning
Loss Gradient Stochastic Gradient Descent Architecture Design Efficient Optimization Neural Network LeArning Abstract Loss Function Learning Rate
Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error
Imitation Learning Step Prediction Model Based Reinforcement Learning Multi Step Weak Model LeArning Abstract Learning Based
Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation
Contextual Representation 2 Dimensional Pose Stream Transformer Representation Learning LeArning Abstract 3D Human Pose Estimation
Incorporating Coupling Knowledge into Echo State Networks for Learning Spatiotemporally Chaotic Dynamics
Echo State Network Chaotic System Weight Coupling Learning LeArning Abstract Chaotic Dynamic Global Attractor Inductive Bias
ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
Medical LLM Information Redundancy Chain of Thought Iterative Pruning Trade Offs Positive Reinforcement LeArning Abstract

April 1, 2025

Alleviating Performance Disparity in Adversarial Spatiotemporal Graph Learning Under Zero-Inflated Distribution
Performance Disparity Temporal Graph Learning Temporal Graph Representation Learning LeArning Abstract Adversarial Training Adversarial Attack Spatial Gradient Zero Inflated
Energy Weighted Learning Progress Guided Interleaved Multi-Task Learning
Human Learning Continual LEArning Interleaved Learning LeArning Abstract Sequential Multi Task Learning
Learning to Normalize on the SPD Manifold under Bures-Wasserstein Geometry
Data Normalisation Geometric Analysis Riemannian Stochastic Covariance Matrix Symmetric Positive Definite LeArning Abstract Riemannian Metric
Generalization-aware Remote Sensing Change Detection via Domain-agnostic Learning
Domain Shift Change Detection Domain Agnostic Generative Adversarial Network LeArning Abstract
FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detection
Cue Fusion Physical Digital Face Attack Detection Adversarial Prompt CLIP TD Outperforms Face Presentation Attack LeArning Abstract Prompt Attack
MPDrive: Improving Spatial Understanding with Marker-Based Prompt Learning for Autonomous Driving
LED Marker Spatial Understanding LeArning Abstract Autonomous Driving

March 31, 2025

Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
Contrastive Reasoner Base Model LeArning Abstract Large Scale Reinforcement Learning DeepSeek Coder Positive Reinforcement Open Source
CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learning
Neurosymbolic Learning Tensor Train LeArning Abstract
Learning 3D-Gaussian Simulators from RGB Videos
3D Gaussian Physic Simulation Single RGB Image LeArning Abstract Object Dynamic Neural Inverse Rendering

LeArning Abstract

Papers

Integrating Human Knowledge Through Action Masking in Reinforcement Learning for Operations Research

Learning Geometrically-Informed Lyapunov Functions with Deep Diffeomorphic RBF Networks

Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval

Toward General and Robust LLM-enhanced Text-attributed Graph Learning

MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception

Learning and Improving Backgammon Strategy

Architect Your Landscape Approach (AYLA) for Optimizations in Deep Learning

Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error

Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation

Incorporating Coupling Knowledge into Echo State Networks for Learning Spatiotemporally Chaotic Dynamics

ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Alleviating Performance Disparity in Adversarial Spatiotemporal Graph Learning Under Zero-Inflated Distribution

Energy Weighted Learning Progress Guided Interleaved Multi-Task Learning

Learning to Normalize on the SPD Manifold under Bures-Wasserstein Geometry

Generalization-aware Remote Sensing Change Detection via Domain-agnostic Learning

FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detection

MPDrive: Improving Spatial Understanding with Marker-Based Prompt Learning for Autonomous Driving

Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learning

Learning 3D-Gaussian Simulators from RGB Videos