UMass Foundation Model

UMass Foundation Model's repositories

Code for 3D-LLM: Injecting the 3D World into Large Language Models

Language:PythonMIT868 16 62

[ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model

Language:Python261 18 6

Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"

Language:Python199 3 22

Code for MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World

Language:Python109 11 4

Language:PythonNOASSERTION67 1 6

Official implementation for CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding

Language:PythonMIT39 3 1

HAZARD challenge

Language:PythonBSD-2-Clause25 2 5

Source codes for the paper "COMBO: Compositional World Models for Embodied Multi-Agent Cooperation"

Language:Python2300

Language:PythonApache-2.015 1 2

Code for paper "RapVerse: Coherent Vocals and Whole-Body Motions Generations from Text"

MIT1100

Codebase for AAAI 2024 conference paper Visual Chain-of-Thought Prompting for Knowledge-based Visual Reasoning

Language:Python11 10

000