As the World Cup final approaches, take a moment to appreciate the beautiful symmetries of humanity’s favorite truncated ...

Diffusion policy exhibits promising multimodal property and distributional expressivity in robotic field, while not ready for real-time end-to-end autonomous driving in more dynamic and open-world ...

Abstract: Robust matrix completion refers to recovering a low-rank matrix given a subset of the entries corrupted by gross errors, and has various applications since many real-world signals can be ...

Abstract: We tackle the problem of large-scale robust fitting using the truncated least squares (TLS) loss. Existing approaches commonly optimize this loss by employing a smooth surrogate, which ...