Projets
—-Gaming/Mix-Reality/Robots Knowledge-memory augmented interaction for cross-modality and reality-agnostic integration with Emergence Mechanism. Selected as the project in HackBox 2023 (opens in new tab) Shipped to Office Teams
Établi:
Machine learning, in particular Large Language Models, has shown great promise at automating several aspects of programming and software development such as coding, testing, integration, static analysis, verification etc. in recent years. In this project, we leverage and extend large…
Établi:
This is the home page of project GODEL (Grounded Open Dialogue Language Model), a large open-source pre-trained language model for dialog. In contrast with its predecessor DialoGPT (opens in new tab), GODEL leverages a new phase of grounded pretraining designed to better…
This project develops techniques that enable AI to use computing infrastructure more efficiently. The goals are to maintain predictive accuracy while reducing carbon emissions, whether embodied in manufactured hardware, or produced from electricity usage when green energy is not available.
Établi:
Embedding symbolic computation within neural computation via Tensor Product Representations This is the long term project to embed symbolic computation within neural computation via Tensor Product Representations, using continuous structured representations for deeper, more fluid and general knowledge representation than…
Établi:
Increasing the compositional power of Transformer with Tensor Product Representations. This project seeks to improve the compositional power of the Transformer model by leveraging critical theoretical properties of Tensor Product Representations (TPR’s). Several new diagnostic datasets for systematicity and compositionality…
Établi:
Implementing a Neural Blackboard with Tensor Product Representation encoded tree structures. The TP Blackboard model uses Tensor Product Representations (TPR’s) to represent a neural blackboard, which neural agents then use to communicate, coordinate, and compose their results of transforming an…
Établi:
Neural Networks processing information as chunks of structured items, encoded into Tensor Product Representations. The theory of chunking developed out of George Miller’s study of working memory in humans (opens in new tab). It can be used to explain how…
Établi:
The project focuses on the integration of neuroscience and symbolic computation for modeling generation, especially, inference reasoning in the Natural Language Processing and multi-modality.