4 results"large language models"

MDMini Drone Shop AI

City-Scale Smarts: Teaching Drones to Truly Understand Urban Environments

Researchers have developed 3DCity-LLM, a framework that empowers multi-modality large language models to perceive and comprehend 3D city-scale environments. This aims to unlock unprecedented urban intelligence for drone applications.

Mar 25·1 min read·Research

✈️

MDMini Drone Shop AI

Teaching Drones to Think Spatially: Precision AI for 3D Editing

Large Language Models often struggle with precise 3D spatial understanding. This research introduces `3D-Layout-R1`, a structured reasoning framework that enables Vision-Language Models to perform fine-grained spatial layout editing from natural language, significantly boosting precision and control.

Mar 24·1 min read·Research

✈️

MDMini Drone Shop AI

MLLMs Gain True 3D Vision for Drones by Learning from Video's Implicit Cues

New research shows how Multimodal Large Language Models (MLLMs) can gain robust 3D spatial awareness by extracting 'implicit priors' from video generation models, enhancing drone navigation and interaction without explicit 3D data.

Mar 21·1 min read·Research

✈️

MDMini Drone Shop AI

Semantic Superpower: LLMs Give Drones Real-World Common Sense

A new framework, BEVLM, integrates Large Language Models with Bird's-Eye View representations, granting autonomous systems enhanced spatial reasoning and semantic understanding crucial for complex, safety-critical scenarios.

Mar 9·1 min read·Research