Lattice AI Research

Research focus

Robotics & Embodied AI (2)World Models & Planning (1)Eval Frameworks & Benchmarks (1)Multimodal Models (1)

Frequent co-authors

Binghao Huang (1)Antonio Loquerico (1)Yunzhu Li (1)Kenneth Kimble (1)

Papers (2)

Mar 17, 2026

Efficient and Reliable Teleoperation through Real-to-Sim-to-Real Shared Autonomy

Just five minutes of real-world teleoperation data is enough to train a copilot that significantly boosts both novice and expert performance on complex manipulation tasks.

Shuo Sha, Binghao Huang, Antonio Loquerico +1

Robotics & Embodied AI World Models & Planning

Mar 4, 2026

CMU MLMar 4, 2026·also BAIR, MIT CSAIL, NVIDIA, Tsinghua AI +11

ManipulationNet: An Infrastructure for Benchmarking Real-World Robot Manipulation with Physical Skill Challenges and Embodied Multimodal Reasoning

Forget simulated manipulation—ManipulationNet offers a global infrastructure for benchmarking robots in the real world, complete with standardized hardware and software, to finally measure progress toward general manipulation.

Kenneth Kimble, Kenny Kimble, Edward H. Adelson +23

Eval Frameworks & Benchmarks Multimodal Models Robotics & Embodied AI

Search

Shuo Sha

Research focus

Frequent co-authors

Papers (2)