Inside Ring-1T: Ant engineers solve reinforcement learning bottlenecks at trillion scale

Ant Group, an affiliate of Alibaba, released Ring-1T which it says is the first trillion parameter open-source model.
IEEE

Single-View 3D-Aware Representations for Reinforcement Learning by Cross-View Neural Radiance Fields

Abstract: Reinforcement learning (RL) has enabled robots to develop complex skills, but its success in image-based tasks often depends on effective representation learning. Prior works have primarily ...