Toyota Research Institute - Machine Learning

packnet-sfm

TRI-ML Monocular Depth Estimation Repository

vidar

DDAD

Dense Depth for Autonomous Driving (DDAD) dataset.

dd3d

Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park*, Rares Ambrus*, Vitor Guizilini, Jie Li, and Adrien Gaidon.

prismatic-vlms

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

KP3D

Code for "Self-Supervised 3D Keypoint Learning for Ego-motion Estimation"

PF-Track

Implementation of PF-Track

KP2D

sdflabel

Official PyTorch implementation of CVPR 2020 oral "Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors"

permatrack

Implementation for Learning to Track with Object Permanence

camviz

Visualization Library

dgp

ML Dataset Governance Policy for Autonomous Vehicle Datasets

linear_open_lm

A repository for research on medium sized language models.

vlm-evaluation

VLM Evaluation: Benchmark for VLMs, spanning text generation tasks from VQA to Captioning

VEDet

RAP

This is the official code for the paper RAP: Risk-Aware Prediction for Robust Planning: https://arxiv.org/abs/2210.01368

VOST

Code for the VOST dataset

RAM

Implementation for Object Permanence Emerges in a Random Walk along Memory

road

ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapes (CoRL 2022)

efm_datasets

TRI-ML Embodied Foundation Datasets

HAICU

binomial_cis

Computation of binomial confidence intervals that achieve exact coverage.

stochastic_verification

Official repository for the paper "How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation"

refine

Official PyTorch implementation of the SIGGRAPH 2024 paper "ReFiNe: Recursive Field Networks for Cross-Modal Multi-Scene Representation"

pndr

clip-video-encode

Easily compute clip embeddings from video frames

DD3Dv2

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

japanese-llm-ranking

lm-evaluation-harness

A framework for few-shot evaluation of language models.