InfoQ

Google Supercharges Gemini 3 Flash with Agentic Vision

Google has added agentic vision to Gemini 3 Flash, combining visual reasoning with code execution to "ground answers in ...

Waymo leverages Genie 3 to create a world model for self-driving cars

Google-spinoff Waymo is in the midst of expanding its self-driving car fleet into new regions. Waymo touts more than 200 million miles of driving that informs how the vehicles navigate roads, but the ...

Roblox brings 4D creation tools to its open-source AI model, and it looks about as good as you'd expect

Roblox launched its generative Cube Foundation Model last year, and has now expanded its functionality to bring 3D objects to life with AI.
News9Live on MSN

Roblox’s 4D generation is here: Cube AI brings fully functional objects to games

Roblox has launched 4D generation in beta, letting players and creators generate fully functional objects like cars and ...
IEEE

BiTrack: Bidirectional Offline 3D Multi-Object Tracking Using Camera-LiDAR Data

Abstract: Compared with real-time multi-object tracking (MOT), offline multi-object tracking (OMOT) has the advantages to perform 2D-3D detection fusion, erroneous link correction, and full track ...
IEEE

Elemental Composite Prototypical Network: Few-Shot Object Detection on Outdoor 3D Point Cloud Scenes

Abstract: This paper introduces the Elemental Composite Prototypical Network (ECPN), a novel approach to few-shot learning (FSL) in outdoor 3D point cloud object detection. Such point clouds are ...