Search papers, labs, and topics across Lattice.
D observations into
5
0
10
0
Achieve robust robot manipulation across diverse viewpoints without camera calibration by synthesizing novel views with a geometry-aware video diffusion model.
Turns out, coding agents in the wild are only writing useful code 44% of the time, and are introducing more security vulnerabilities than human developers.
Pocket-sized VLA models can now achieve state-of-the-art robot manipulation performance by pre-training on a curated multimodal dataset and injecting manipulation-relevant representations into the action space.
The rise of AI in finance hasn't necessarily translated to lower operating expenses, suggesting a more complex relationship between technology and labor than simple automation.
GRPO's Achilles' heel in deep search is its coarse advantage assignment, but CalibAdv offers a way to surgically correct it, boosting both performance and training stability.
