Submissions by taikon

TripoSG – Text to 3D Model

Facebook Uncommon Objects in 3D Dataset

Nvidia/cosmos: Physics-aware Text2Video

KAG – Knowledge Graph RAG Framework

IDX – AI powered development by Google

Auto-RAG

StableV2V: AI video editing that maintains object shapes across frames

Apple ML – Reduce LLM training memory without speed loss

WALA: AI convert sketches, images and text to 3D

DreamClear: AI model restores degraded images while preserving privacy

SAM2Long: Sam 2 for Long Video Segmentation with a Training-Free Memory Tree

Hallo2 – Portrait to Video with AI

Mini-Omni2: Towards Open-Source GPT-4o with Vision, Speech, Duplex Capabilities

LightRAG: Simple and Fast Retrieval-Augmented Generation