Search papers, labs, and topics across Lattice.
4
0
6
4
Grounding action representations in environmental context can drastically improve robotic manipulation performance, especially for complex tasks.
Bridging the gaps in physical intelligence could enable agents to learn and adapt in real-world scenarios more effectively than ever before.
Existing text-to-image models struggle to capture individual aesthetic preferences, but PIPBench reveals critical gaps in their performance that could redefine personalized image generation.
Forget imitation: reward-aware trajectory shaping lets few-step generative models outperform their multi-step teachers.
