We have 3 of 74 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
MindCue is proposed, a training-free spatial evidence selector guided by a target-view hypothesis that reverses the drop in overall score under expanded context and outperforms the standard-context baseline, and provides a concrete testbed for generative multi-view spatial intelligence.
Experimental results show that Diffusion-SDF is capable of generating both high-quality and highly diversified 3D shapes that conform well to the given text descriptions, and Diffusion-SDF++ further outperforms Diffusion-SDF with more precise shape details due to the adaptive voxelization strategy.
Improved text-visual attention patterns are introduced to enhance the fidelity of query-aware vision token selection and the Attention Gravity effect is correct, and a rank-based strategy to adaptively determine the sparsification ratio for each layer is introduced.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
