arXiv (All)
open access
Learning to Think and Explore in 3D World
We study how vision-language models (VLMs) can learn to think and actively explore in 3D space. Instead of providing multi-view images, videos, or 3D representations to the model, we preserve the native visual encoding of VLMs, i.e., a single image, one at a time, just like humans, and treat the 3D
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- BareBones: Benchmarking Zero-Shot Geometric Comprehension in VLMs#1216278
- VLA Foundry: A Unified Framework for Training Vision-Language-Action Models#124125
- EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training#1357146
- FloorSAV: Elucidating Spatial Audio-Visual Context with 2D Floormap for AV-LLMs#1248590
- Toward Comprehensive 3D Grounding: Orientation Grounding through Vision-Language Models#1117821
Record · ID 1357438
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive