Stars
SGLang is a high-performance serving framework for large language models and multimodal models.
Representation Engineering: A Top-Down Approach to AI Transparency
A proxy for minimax-m2, enabling interleaved thinking, and tool calls.
A high-throughput and memory-efficient inference and serving engine for LLMs
Python package to parse, analyse, and plot Apple HealthKit data
"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspi…
Framework enabling modular interchange of language agents, environments, and optimizers
This is the repository for the Python based program for automated deep phenotype analysis of clinical information using large language models (LLMs) and Retrieval Augmented Generation (RAG)
A Survey of Attributions for Large Language Models
MIMIC-III corpus parsing and section prediction with MedSecId (COLING paper)
LLM-based ontological extraction tools, including SPIRES
tracking papers, datasets, and models of "large language model (LLM) for time series"
In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.
Revealing Hidden Patterns in Deep Neural Network Feature Space Continuum via Manifold Learning (Nature Communications, 2023)
A package of distributionally robust optimization (DRO) methods. Implemented via cvxpy and PyTorch
Generation of protein sequences and evolutionary alignments via discrete diffusion models
Phenome Exome Association and Correlation Of Key phenotypes
The Polygenic Score Catalog Calculator is a nextflow pipeline for polygenic score calculation
DataComp: In search of the next generation of multimodal datasets
Automatic extraction of relevant features from time series:
Implementation of the Equiformer, SE3/E3 equivariant attention network that reaches new SOTA, and adopted for use by EquiFold for protein folding