Code and models of MOCA (Modular Object-Centric Approach) proposed in "Factorizing Perception and Policy for Interactive Instruction Following" (ICCV 2021). We address the task of long horizon instruction following with a modular architecture that decouples a task into visual perception and action policy prediction.
☆40Jun 21, 2024Updated 2 years ago
Alternatives and similar repositories for moca
Users that are interested in moca are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal tra…☆93Jul 11, 2023Updated 2 years ago
- Official Implementation of CAPEAM (ICCV'23)☆16Nov 30, 2024Updated last year
- Official code for the ACL 2021 Findings paper "Yichi Zhang and Joyce Chai. Hierarchical Task Learning from Language Instructions with Uni…☆24Jun 28, 2021Updated 5 years ago
- ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks☆519Feb 5, 2026Updated 5 months ago
- Prompter for Embodied Instruction Following☆18Nov 30, 2023Updated 2 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- ☆17Mar 26, 2021Updated 5 years ago
- Implementation of "Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation"☆27Mar 4, 2021Updated 5 years ago
- A visual semantic planner for the ALFRED virtual agent challenge using the GPT-2 language model☆16Oct 1, 2020Updated 5 years ago
- Official repository of ICLR 2022 paper FILM: Following Instructions in Language with Modular Methods☆128Apr 9, 2023Updated 3 years ago
- Code for EmBERT, a transformer model for embodied, language-guided visual task completion.☆60Apr 10, 2024Updated 2 years ago
- Official Implementation of ISR-DPO:Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO (AAAI'25)☆23Nov 25, 2025Updated 7 months ago
- TEACh is a dataset of human-human interactive dialogues to complete tasks in a simulated household environment.