Search papers, labs, and topics across Lattice.
4
0
7
Teleopit achieves 95% task success in humanoid teleoperation by seamlessly mapping human body and hand signals to a robotic counterpart without specialized sensors.
Retired EV components can be re-engineered into affordable, AI-enabled agricultural robots, bridging the automation gap for smallholder farms.
TACO effectively mitigates the reinforcement of erroneous reasoning in LLMs by distinguishing between useful and unreliable tokens, leading to improved training stability and performance.
On-policy distillation can lead to catastrophic length inflation in student models, but a simple fix stabilizes training and boosts performance by 7%.
