aleSuglia

ukras-summer-school-genair

Material for "Generative AI for Robotics" day at the UK RAS Robotics Summer School 2025

alesuglia.github.io

Personal website

alfred

ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

lingtech-summer-school-rasa

Example code used for RASA NLU tutorial at the LingTech Summer School 2022 (Lecce, Italy)

vlmviz

VlmViz: Visualize Attention in Vision+Language Models

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)

hwu-ollama-tutorial

A brief tutorial on using LLM via Ollama

clembench

A Framework for the Systematic Evaluation of Chat-Optimized Language Models as Conversational Agents and an Extensible Benchmark

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.

discord-research-papers-bot

flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

guesswhat

GuessWhat?! Baselines

gym

A toolkit for developing and comparing reinforcement learning algorithms.

lerobot

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

magikarp

Code for the paper "Fishing for Magikarp"

pixar

Repository of PIXAR, a Pixel-based Auto-Regressive Language Model

py-bottom-up-attention

PyTorch bottom-up attention with Detectron2

pytorch-lightning

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

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.

StarterCode

Starter Code for VALUE benchmark

streaming

A Data Streaming Library for Efficient Neural Network Training

teach

TEACh is a dataset of human-human interactive dialogues to complete tasks in a simulated household environment.

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

virtualhome

API to run VirtualHome, a Multi-Agent Household Simulator

visual_genome_python_driver

A python wrapper for the Visual Genome API

vlm-evaluation-harness

A framework for few-shot evaluation of vision+language models.