Repository Index

:grey_question: Visual Question Answering in Torch

• torch
• deep-learning
• computer-vision
• natural-language-processing

Code for PaperRobot: Incremental Draft Generation of Scientific Ideas

• pytorch
• memory-networks
• generation
• end-to-end-learning

[Reimplementation Antol et al 2015] Keras-based LSTM/CNN models for Visual Question Answering

Intensity-based_Lidar_Camera_Calibration

• calibration
• lidar
• panoramic
• camera

Learning Multi-Domain Convolutional Neural Networks for Visual Tracking

Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving

• semantic-segmentation
• lidar
• semantickitti
• 3d-lidar-data

Official implementation of “UniForge3D: Joint 3D Reconstruction and Generation in a Shared Anchor-Guided Space.”

ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission (CHIL 2020 Workshop)

• clinicalbert
• hospital-readmission
• prediction

The repository host gives no description.

Python implementation of the rulefit algorithm

Solve captcha without manually labeling a training set

• keras
• gan
• neural-network
• generative-adversarial-network

Code and data for GeneGPT.

The repository host gives no description.

Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"

• audio
• audio-classification
• audio-processing
• audio-tagging

[IROS 2020] se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains

• robotics
• tracking
• computer-vision
• pose-estimation

Crop Yield Prediction with Deep Learning

Implementation for PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (CVPR 2020)

GEARS is a geometric deep learning model that predicts outcomes of novel multi-gene perturbations

Repository for MolFormer

CellViT: Vision Transformers for Precise Cell Segmentation and Classification

• ai
• cell
• digitalpathology
• microscopy

This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data

🎆 A visualization of the CapsNet layers to better understand how it works

• capsule-network
• tensorflow
• python
• hinton

Reproduction of SuperMimic (arXiv:2610.28480): learned differentiable world model + BPTT policy for G1 humanoid motion tracking, on mjlab/MuJoCo Warp

Phoebus is a distributed framework for large scale graph processing written in Erlang.