📊 Small Datasets - hecko

Discussed on DEV

🧠Neural Networks biorxiv.org·

Few-Shot Classification of C. elegans Developmental Stages via Explainable Hierarchical Hyperbolic Graph Embeddings

Less-relevant results

🧠Neural Networks Nature·

Predicting the strength of waste aggregate concrete blocks using novel hybrid machine learning models and graphical user interface deployment

🧠Neural Networks GitHub·

Show HN: Alloy – a PyTorch backend and inference engine for Apple Silicon

Discussed on Hacker News

🧠Neural Networks arXiv·

Memory-Efficient Policy Libraries with Low-Rank Adaptation in Reinforcement Learning

🧠Neural Networks Search Engine Journal·

Google Research Shows How AI Spam Can Be Detected via @sejournal, @martinibuster

🧠Neural Networks arXiv·

Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers

🧠Neural Networks Hugging Face·

bwen-14b - benthecarman model trained on benthecarman

🧠Neural Networks kaggle.com·

QLoRA: Fine-Tuning a 7B Model on a 16GB GPU (It Shrank to 5.4GB in Front of Me)

Discussed on DEV

🧠Neural Networks arXiv·

MixedPEFT: Combining Multiple PEFT Methods with Mixed Objectives for Unsupervised Domain Adaptation

🧠Neural Networks fareedkhan-dev.github.io·

Train LLM from Scratch

Discussed on Hacker News

🐍Python GitHub·

PsychAdapter: Personality in LLM output via trait-language patterns, not prompts

Discussed on Hacker News

🧠Neural Networks arXiv·

Learning Dynamical Systems from Multiple Sparse Datasets: A Hierarchical Bayesian Modeling Approach

🧠Neural Networks arXiv·

Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios

🧠Neural Networks biorxiv.org·

Bioinf-Farma: supervised integration of epitope prediction and recombinant protein developability for automated vaccine candidate prioritization

🧠Neural Networks journals.plos.org·

pyhgf: A neural network library for predictive coding

🧠Neural Networks arXiv·

Reconstructing Randomly Masked Spectra Helps DNNs Identify Discriminant Wavenumbers

🧠Neural Networks people.idsia.ch·

Munich 1991: The Roots of the Current AI Boom

Covers 2 stories including DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Discussed on Hacker News and Lobsters

🧠Neural Networks arXiv·

Tri-Efficient Transfer Learning for Point Cloud Videos

LoRA: I Trained <1% of a 1.5B Model and Matched a Full Fine-Tune

Few-Shot Classification of C. elegans Developmental Stages via Explainable Hierarchical Hyperbolic Graph Embeddings

Predicting the strength of waste aggregate concrete blocks using novel hybrid machine learning models and graphical user interface deployment

Show HN: Alloy – a PyTorch backend and inference engine for Apple Silicon

Memory-Efficient Policy Libraries with Low-Rank Adaptation in Reinforcement Learning

Google Research Shows How AI Spam Can Be Detected via @sejournal, @martinibuster

Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers

bwen-14b - benthecarman model trained on benthecarman

QLoRA: Fine-Tuning a 7B Model on a 16GB GPU (It Shrank to 5.4GB in Front of Me)

MixedPEFT: Combining Multiple PEFT Methods with Mixed Objectives for Unsupervised Domain Adaptation

Train LLM from Scratch

PsychAdapter: Personality in LLM output via trait-language patterns, not prompts

Learning Dynamical Systems from Multiple Sparse Datasets: A Hierarchical Bayesian Modeling Approach

Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios

Bioinf-Farma: supervised integration of epitope prediction and recombinant protein developability for automated vaccine candidate prioritization

pyhgf: A neural network library for predictive coding

Reconstructing Randomly Masked Spectra Helps DNNs Identify Discriminant Wavenumbers

Munich 1991: The Roots of the Current AI Boom

Interpretable Meta-Learning for Multi-Objective Chemical Search