A Persian Vision-Language-Action Dataset and Benchmark for Ambiguity- and Infeasibility-Aware Instruction-to-Plan Grounding
cs.CV, cs.CL
Submitted: 2026-10-11
Updated: 2026-10-11
Comments: 15 pages, 5 figures. Preprint submitted to Language Resources and Evaluation
Code: https://github.com/Lab-RoCoCo-Sapienza/map-vlm
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- Multi-Agent Planning Using Visual Language Models
- PLATO: Planning with LLMs and Affordances for Tool Manipulation
- Ego4D: Around the World in 3,000 Hours of Egocentric Video
- Understanding the planning of LLM agents: A survey
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- Large Language Model Agent: A Survey on Methodology, Applications and Challenges
- EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought
- ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
- VLN-NF: Feasibility-Aware Vision-and-Language Navigation with False-Premise Instructions
- Wonderful Team: Zero-Shot Physical Task Planning with Visual LLMs
- P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models