InstructMol: Multi-Modal Molecular Assistant
A multi-modal LLM aligning 2D molecular graphs with text via two-stage instruction tuning for drug discovery tasks.
Embeddings
Party Matters: Enhancing Legislative Embeddings
A method for improving legislative vote prediction across sessions by augmenting bill text embeddings with sponsor …
High-Performance Word2Vec in Pure PyTorch
Production-grade Word2Vec in PyTorch with vectorized Hierarchical Softmax, Negative Sampling, and torch.compile support.
Analytical Solution to Word2Vec Softmax & Bias Probing
Analytical derivation of Word2Vec's softmax objective factorization and a new framework for detecting semantic bias in …
EigenNoise: Data-Free Word Vector Initialization
Investigation into EigenNoise, a data-free initialization scheme for word vectors that approaches pre-trained model …
Data-Driven WordNet Construction from Wiktionary
We introduce an unsupervised algorithm for inducing semantic networks from noisy, crowd-sourced data, producing a …
Count Vectorization with scikit-learn in Python
Learn count vectorization in Python: convert text to numerical vectors using scikit-learn's CountVectorizer with …
Word Embeddings in NLP: An Introduction
Learn about word embeddings in NLP: from basic one-hot encoding to contextual models like ELMo. Guide with examples.