Goto

Collaborating Authors

 Qingdao



Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image Y u Zhao

Neural Information Processing Systems

In the visual spatial understanding (VSU) area, spatial image-to-text (SI2T) and spatial text-to-image (ST2I) are two fundamental tasks that appear in dual form. Existing methods for standalone SI2T or ST2I perform imperfectly in spatial understanding, due to the difficulty of 3D-wise spatial feature modeling.



Aligning Gradient and Hessian for Neural Signed Distance Function

Neural Information Processing Systems

Our motivation is grounded in a fundamental observation: aligning the gradient and the Hessian of the SDF provides a more efficient mechanism to govern gradient directions.




Distributional Reward Decomposition for Reinforcement Learning

Zichuan Lin, Li Zhao, Derek Yang, Tao Qin, Tie-Yan Liu, Guangwen Yang

Neural Information Processing Systems

Van Seijen et al. [2017] propose to split a state into different sub-states, each with a sub-reward obtained bytraining ageneral valuefunction, andlearnmultiple valuefunctions withsub-rewards. The architecture is rather limited due to requiring prior knowledge of how to split into sub-states.