Search papers, labs, and topics across Lattice.
Department of Computer Science, Tufts University, Medford, MA, USA
3
0
7
0
Robots can now learn to manipulate novel objects in dynamic environments by using LLMs to bridge the gap between symbolic planning and reinforcement learning.
Reliably erase broad concepts like "sexual" or "violent" from diffusion models by using learned concept prototypes as negative guidance, outperforming existing methods.
Neuro-symbolic methods crush VLAs on long-horizon manipulation, achieving 95% success vs 34% while using 100x less energy.
