[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

A Library for Advanced Deep Time Series Models.

Computational framework for reinforcement learning in traffic control

A python package for computing distance between 2D trajectories.

TF2 Deep FloorPlan Recognition using a Multi-task Network with Room-boundary-Guided Attention. Enable tensorboard, quantization, flask, tflite, docker, github actions and google colab.

Real-world benchmarks for urban delivery problems, including vehicle routing and facility location problems.

Python implementation of Traclus algorithm, for 2-D trajectories

The code and dataset of the KDD23 paper 'A Study of Situational Reasoning for Traffic Understanding'

Big data platform that provides aggregated geospatial and temporal 311 trends of NYC.