Robotics

Yunsong Zhou, Hangxu Liu, Xuekun Jiang et al.

SIM1 builds physics-aligned real-to-sim twins for deformable manipulation, letting purely synthetic training reach real-data parity at a fraction of collection cost and making sim-scaled robotics learning much more practical.

Ruihang Xu, Dewei Zhou, Xiaolong Shen et al.

Adds 3D geometry and physical constraints to image editing, plus a new benchmark, making object manipulation edits far more reliable for world-model, simulation, and synthetic-data workflows.

Jiajun Zhai, Hao Shi, Shangwei Guo et al.

E-VLA uses event cameras—normally used in robotics—to let robots see and act in near-total darkness or blur, where normal cameras fail. This enables real-world robotic systems to operate reliably in challenging environments like smoke-filled rooms or fast-moving scenes.

Songyuan Yang, Huibin Tan, Kailun Yang et al.

Programming domestic robots is often too complex for non-experts. This system allows users to instruct robots by simply sketching on a camera feed, removing the need for coding or pre-existing maps and making home robotics accessible to everyone.