Wenxin Wang

A novel multi-agent framework enhances zero-shot 3D understanding by iteratively optimizing viewpoints and integrating fragmented observations, leading to significant performance gains.

Local MoE inference can now match cloud-level performance, achieving 1,800 tokens/s on consumer GPUs while maintaining original model precision.

Safe, collaborative transport of payloads by quadruped robots in tight spaces is now possible thanks to a novel reinforcement learning approach that guarantees collision avoidance.