Strong Generalization

Strong generalization, the ability of machine learning models to perform well on unseen data, is a central objective in current research. Active areas of investigation include improving the robustness of self-supervised learning, understanding the optimization dynamics of transformers and other architectures (including CNNs and RNNs), and developing methods to enhance generalization through data augmentation, regularization techniques (e.g., logical regularization, consistency regularization), and improved training strategies (e.g., few-shot learning, meta-learning). These advancements are crucial for building reliable and adaptable AI systems across diverse applications, from image classification and natural language processing to healthcare and robotics.

1046papers

Papers - Page 4

March 4, 2025

Classifying States of the Hopfield Network with Improved Accuracy, Generalization, and Interpretability
Finite State Accuracy Improvement Hopfield Network Strong Generalization Inherent Interpretability
Weak-to-Strong Generalization Even in Random Feature Networks, Provably
Strong Generalization Random Feature Weak to Strong Strong Learner
REAct: Rational Exponential Activation for Better Learning and Generalization in PINNs
Strong Generalization Enhanced Learning Exponential Activation Function Shape Learning Physic Informed Neural Network Frontend Component Code Benchmark Platform
CGMatch: A Different Perspective of Semi-supervised Learning
Different Perspective Consistency Regularization Pseudo Labeling Semi Supervised Learning Unlabeled Example Strong Generalization Generalization Performance
Frankenstein Optimizer: Harnessing the Potential by Revisiting Optimization Tricks
Stochastic Gradient Descent Better Optimizers Adaptive Importance Full Potential Gradient Based Optimization Strong Generalization

March 2, 2025

NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains
Symbolic Approach Embodied Task Neuro Symbolic Approach Strong Generalization
On Generalization Across Environments In Multi-Objective Reinforcement Learning
Multiple Objective Reinforcement Learning Strong Generalization Multi Objective LeArning Abstract Environment Feature

February 27, 2025

Data Distributional Properties As Inductive Bias for Systematic Generalization
Strong Generalization Distribution Generalization Neural Representation Systematic Generalization Latent Feature Neural Network Distributional Property Inductive Bias
Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks
Inductive Bias Initial Weight Strong Generalization Neural Network Inductive Task Architecture Perspective Absolute Stance Bias

February 26, 2025

Strong Generalization

Papers - Page 4

Classifying States of the Hopfield Network with Improved Accuracy, Generalization, and Interpretability

Weak-to-Strong Generalization Even in Random Feature Networks, Provably

REAct: Rational Exponential Activation for Better Learning and Generalization in PINNs

CGMatch: A Different Perspective of Semi-supervised Learning

Frankenstein Optimizer: Harnessing the Potential by Revisiting Optimization Tricks

Deep Learning is Not So Mysterious or Different

A Taxonomy for Evaluating Generalist Robot Policies

Enhancing Deep Reinforcement Learning-based Robot Navigation Generalization through Scenario Augmentation

NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains

On Generalization Across Environments In Multi-Objective Reinforcement Learning

Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks

Generalization of CNNs on Relational Reasoning with Bar Charts

Continual Learning-Aided Super-Resolution Scheme for Channel Reconstruction and Generalization in OFDM Systems

Data Distributional Properties As Inductive Bias for Systematic Generalization

Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks

LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM

Partition Tree Weighting for Non-Stationary Stochastic Bandits

ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration

GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation

Investigating Generalization of One-shot LLM Steering Vectors