Tag: faang

Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM (Less Gaussians, Texture More), a feed-forward framework that overcomes this resolution scaling barrier. By predicting compact Gaussian primitives coupled with …

Read more “Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting”

State Space Models (SSMs) have become the leading alternative to Transformers for sequence modeling. Their primary advantage is efficiency in long-context and long-form generation, enabled by fixed-size memory and linear scaling of computational complexity. We begin this work by showing a simple theoretical result stating that SSMs cannot accurately solve any “truly long-form” generation problem …

Read more “To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models”

Despite their output being ultimately consumed by human viewers, 3D Gaussian Splatting (3DGS) methods often rely on ad-hoc combinations of pixel-level losses, resulting in blurry renderings. To address this, we systematically explore perceptual optimization strategies for 3DGS by searching over a diverse set of distortion losses. We conduct the first-of-its-kind large-scale human subjective study on …

Read more “Drop-In Perceptual Optimization for 3D Gaussian Splatting”

AI has made it easier than ever for student developers to work efficiently, tackle harder problems, and pursue ambitious projects. But for students earning technical degrees, these new capabilities also create genuine tensions around learning.  How much should I use AI? What should I use it for?  As 90% of technology professionals now use AI …

Read more “The new AI literacy: Insights from student developers”

We introduce exclusive self attention (XSA), a simple modification of self attention (SA) that improves Transformer’s sequence modeling performance. The key idea is to constrain attention to capture only information orthogonal to the token’s own value vector (thus excluding information of self position), encouraging better context modeling. Evaluated on the standard language modeling task, XSA …

Read more “Exclusive Self Attention”