代码库
A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).
Python
Codebase for LLM Textual Hallucination Benchmark
Python
AIRS-Bench: an AI Research Science benchmark for quantifying the end-to-end AI research abilities of LLM agents
Python
Official repository for "Context Language Models"
Python
Non-invasive decoding of typed sentences from MEG and EEG brain recordings using a convolutional encoder, transformer, and character-level language model.
Python
Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.
Python
CoTracker is a model for tracking any point (pixel) on a video.
Jupyter Notebook
optical-flowpoint-trackingtrack-anything
WybeCoder Verified Generation of Imperative Code with LLMs
Python
Official repository for PALM, a scan-based dataset with 263 subjects, including 13k registered 3dMD scans and 90k calibrated multiview RGB images.
Python
TestGenEval A Real World Unit Test Generation and Test Completion Benchmark
Python
Reading Wikipedia to Answer Open-Domain Questions
Python
GPU Cluster Monitoring (GCM): Large-Scale AI Research Cluster Monitoring
Python
aiai-clusterai-trainingdcgmhealth-checkshpcmonitoringnvmlslurm
[CVPR 2026] Pixio: a capable vision encoder dedicated to dense prediction, simply by pixel reconstruction
Python
dense-predictionrepresentation-learningself-supervised-learning
[NeurIPS 2026] Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".
Jupyter Notebook
3d-foundation-modelcamera-pose-estimationdepth-estimationimage-matchinglarge-language-modelsobject-level-3dvlms
Repository to track versions of concrete strength data, models, and active learning proposals.
Jupyter Notebook
Research code base for Automatic Textbook Formalization
Python
GitHub repository of commonly used python scripts that allows everyone to pull data via the Ad Library API
Python
A general physic-based retargeting framework.
Python
A pure-Python implementation of the Nvidia CuTe layout algebra intended to be approachable and easy to learn.
Python
Code, data and weights for the paper **What drives success in physical planning with Joint-Embedding Predictive World Models?**
Python