Math

Optimizers

• Adaptive Friction in Deep Learning: Enhancing Optimizers with Sigmoid and Tanh Function
• Enhancing Convolutional Neural Networks with Higher-Order Numerical Difference Methods
• Revisiting the Noise Model of Stochastic Gradient Descent

KAN

• How to Learn More? Exploring Kolmogorov–Arnold Networks for Hyperspectral Image Classification
• fKAN: Fractional Kolmogorov–Arnold Networks with trainable Jacobi basis functions
• ConvKAN: Towards Robust, High-Performance and Interpretable Image Classification

NERF / Gaussian Splatting

• REGULARIZING NEURAL RADIANCE FIELDS FROM SPARSE RGB-D INPUTS

GNN

• Deep Learning-Based User Information Behavior Mining and Personalized Recommendation Optimization
• Robust Soft Sensor Model based on Frequency-Domain Adaptive Graph

Activations

• A Periodic Mapping Activation Function: Mathematical Properties and Application in Convolutional Neural Networks

Hardware

• Squeezing Operator Performance Potential for the Ascend Architecture
• Towards on-device continual learning with Binary Neural Networks in industrial scenarios
• CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge
• Ariel-ML: Computing Parallelization with Embedded Rust for Neural Networks on Heterogeneous Multi-core Microcontrollers

VQA

• Integrating Vision-Language Models for Enhanced Robotic Grasping and Interaction Using RGB Image and Prompt
• Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models
• VecNav: Vector Goal Robot Navigation from In-the-wild Videos

Augmentation

• Positive Data Augmentation Based on Manifold Heuristic Optimization for Image Classification