aleSuglia
Assistant Professor at the Heriot-Watt University teaching machine how to speak via situated/embodied language games.
Heriot-Watt UniversityEdinburgh, Scotland
Pinned Repositories
CoGeLoT
A comprehensive framework to explore whether embodied multimodal models are plausibly resilient
embert
Code for EmBERT, a transformer model for embodied, language-guided visual task completion.
emma-datasets
Create efficient datasets for training Multimodal Foundation Models
emma-policy
Model code for Embodied MultiModal Agent (EMMA)
EVUD
Egocentric Video Understanding Dataset (EVUD)
imnamap
Code for the paper "Iterative Multi-document Neural Attention for Multiple Answer Prediction"
KDNuggets-Data-Mining-Course
A simple Golang program which let you download all the slide from the website of the KDNuggets data mining course.
slideshare_down
A simple Golang program which is able to download private and public slideshare presentation
squadgym
Environment that can be used to evaluate reasoning capabilities of artificial agents
wilde
Wilde will help you remember all the terms that you will learn in a foreign language
aleSuglia's Repositories
aleSuglia/lingtech-summer-school-rasa
Example code used for RASA NLU tutorial at the LingTech Summer School 2022 (Lecce, Italy)
aleSuglia/CoGeLoT
A comprehensive framework to explore whether embodied multimodal models are plausibly resilient
aleSuglia/embert
Code for EmBERT, a transformer model for embodied, language-guided visual task completion.
aleSuglia/emma-datasets
Create efficient datasets for training Multimodal Foundation Models
aleSuglia/emma-policy
Model code for Embodied MultiModal Agent (EMMA)
aleSuglia/EVUD
Egocentric Video Understanding Dataset (EVUD)
aleSuglia/alesuglia.github.io
aleSuglia/alfred
ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
aleSuglia/clembench
A Framework for the Systematic Evaluation of Chat-Optimized Language Models as Conversational Agents and an Extensible Benchmark
aleSuglia/CSrankings
A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.
aleSuglia/flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
aleSuglia/generic
Generic package with basic tools and abstract class to run experiments
aleSuglia/guesswhat
GuessWhat?! Baselines
aleSuglia/gym
A toolkit for developing and comparing reinforcement learning algorithms.
aleSuglia/homebrew-brewery
Homebrew formulas
aleSuglia/image-feature-extractors
Feature extraction and visualization scripts for nocaps baselines.
aleSuglia/mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
aleSuglia/nlp
🤗 nlp: datasets and evaluation metrics for Natural Language Processing in NumPy, Pandas, PyTorch and TensorFlow
aleSuglia/pixar
Repository of PIXAR, a Pixel-based Auto-Regressive Language Model
aleSuglia/py-bottom-up-attention
PyTorch bottom-up attention with Detectron2
aleSuglia/pytorch-lightning
The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.
aleSuglia/ray
A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
aleSuglia/StarterCode
Starter Code for VALUE benchmark
aleSuglia/streaming
A Data Streaming Library for Efficient Neural Network Training
aleSuglia/teach
TEACh is a dataset of human-human interactive dialogues to complete tasks in a simulated household environment.
aleSuglia/transformers
🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
aleSuglia/visual_genome_python_driver
A python wrapper for the Visual Genome API
aleSuglia/visualbert
Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"
aleSuglia/vlm-evaluation-harness
A framework for few-shot evaluation of vision+language models.
aleSuglia/VLP-1
Vision-Language Pre-training for Image Captioning and Question Answering