ACTIVE-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO
-
Updated
May 30, 2025
ACTIVE-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO
Code for NeurIPS 2023 paper "Active Vision Reinforcement Learning with Limited Visual Observability"
Code for the paper: "Active Vision Might Be All You Need: Exploring Active Vision in Bimanual Robotic Manipulation"
GapFlyt: Active Vision Based Minimalist Structure-less Gap Detection For Quadrotor Flight
Bebop 2 custom firmware
The code release of "Real-time Active Vision for a Humanoid Soccer Robot Using Deep Reinforcement Learning" paper, ICAART 2021
Code basis for the paper "Monitoring and Adapting the Physical State of a Camera for Autonomous Vehicles" (2023)
A one-shot method for selecting next best view for active object recognition
Active object localization framework incorporating the bio-plausible mechanisms of foveation and saccades for improved and resilient weakly supervised object localization
An active vision system on the PR2 humanoid robot to dynamically detect objects via the head and arm cameras
A dataset for testing next best view methods as a part of active vision systems.
An active vision system which builds a 3D environment map autonomously using visual attention mechanisms.
Add a description, image, and links to the active-vision topic page so that developers can more easily learn about it.
To associate your repository with the active-vision topic, visit your repo's landing page and select "manage topics."