Search papers, labs, and topics across Lattice.
8
0
10
Current multimodal agents can build sophisticated perception-control pipelines but fail to reliably execute physical tasks, losing object states and mistaking unfinished goals for completion.
The Cartesian Hand is introduced, a 7-DoF end-effector that rethinks dexterous manipulation by combining independent grasping and relative manipulation within a single end-effector using only linear motion.
Copying human head-neck kinematics leaves over 60% of reachable manipulation space unobservable; independently actuating onboard RGB-D cameras surges visible-reachable coverage to 97% while cutting manipulation energy by 19%.
Targeted post-training interventions can boost code generation performance by over 6 points on key benchmarks, challenging the notion that larger models are always better.
Real-time object navigation can see up to an 11% boost in success rates by addressing inference latency and asynchronous stepping in model design.
Fine-tuning on planning-aware trajectories can enhance model performance across diverse CLI environments, mitigating the pitfalls of scaffold-specific training.
