EgoAlign: Situated 3D Understanding without Situation Descriptions
cs.CV
Submitted: 2026-10-12
Updated: 2026-10-12
Code: https://github.com/Yiyang-Ian-Li/EgoAlign
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Grounded 3D-LLM with Referent Tokens
- Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
- An Embodied Generalist Agent in 3D World
- Direction-aware 3D Large Multimodal Models
- SQA3D: Situated Question Answering in 3D Scenes
- Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes
- SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models
- LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness
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