Highlights
- Pro
Lists (1)
Stars
GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.
The agent that grows with you
Experimental materials for testing the long-read mapping abilities of vg giraffe
Flash Attention with exact per-head relative position bias. 1.5x overhead, 79x faster than FlexAttention+score_mod.
AI agents running research on single-GPU nanochat training automatically
New state-of-the-art bounds for open problems
AI-Driven Scientific and Algorithmic Discovery
Benchmarking Language Agents Under Controllable and Extreme Context Growth
An ARC-AGI solution using Agentica from Symbolica
Terminal-Bench-Science: Evaluating AI Agents on Complex Real-World Scientific Workflows in the Terminal
The Claude Code background agent for Linear, Slack, Github, GitLab etc. you deploy anywhere. Supports Codex, Cursor and Gemini too.
Measuring agents' ability to get work done on a computer
Dataloader for applying sequence models to personalized genomics
A simple yet versatile context engineered for scalable online data collection
Implementation of AlphaGenome, Deepmind's updated genomic attention model
Harbor is a framework for running agent evaluations and creating and using RL environments.
A benchmark for LLMs on complicated tasks in the terminal
Code repository for the manuscript: Nucleotide dependency analysis of DNA language models reveals genomic functional elements
[ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
The absolute trainer to light up AI agents.
[EMNLP2025] From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery
Causal discovery of gene regulatory programs from single-cell genomics
Pytorch implementation of the Borzoi model from Calico, and Flashzoi, a 3x faster Borzoi enhancement.
The computational and statistical analyses of TenK10K phase 1 multiome data