aleSuglia
Follow
Stars
A comprehensive framework to explore whether embodied multimodal models are plausibly resilient
Manage scalable open LLM inference endpoints in Slurm clusters
Open weights LLM from Google DeepMind.
Non-cooperative satellite operations challenge problems implemented in the Kerbal Space Program game engine
A playbook for systematically maximizing the performance of deep learning models.
Code for "Learning to Model the World with Language."
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
Community for applying LLMs to robotics and a robot simulator with ChatGPT integration
An unofficial implementation of the paper "Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning"
LAVIS - A One-stop Library for Language-Vision Intelligence
Code and documentation to train Stanford's Alpaca models, and generate the data.
A Data Streaming Library for Efficient Neural Network Training
🦜🔗 Build context-aware reasoning applications
PyTorch code for "Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention" (WACV 2023)
Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
VideoCC is a dataset containing (video-URL, caption) pairs for training video-text machine learning models. It is created using an automatic pipeline starting from the Conceptual Captions Image-Cap…
A 3D video game environment and benchmark designed from scratch for reinforcement learning research
[EMNLP 2021] Code and data for our paper "Visually Grounded Reasoning across Languages and Cultures"
🏘️ Scaling Embodied AI by Procedurally Generating Interactive 3D Houses
A modular RL library to fine-tune language models to human preferences
Code Release for the COLING 2022 Paper ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments
Research code for pixel-based encoders of language (PIXEL)
CLIP (Contrastive Language–Image Pre-training) for Italian