A Programming Paradigm for Spatiotemporal Composability
Paper • 2608.25512 • Published • 18
Representation
-
-
On the Design Fundamentals of Pixel Text Representation Learning
Paper • 2609.01147 • Published • 30 -
Disentangling Representation Evolution in Transformers through Directional Decomposition
Paper • 2609.15975 • Published • 9 -
FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders
Paper • 2609.31620 • Published • 144 -
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
Paper • 2610.07987 • Published • 60 -
S-Space: Exploring Spatial Workspace in Multimodal Language Models
Paper • 2610.13527 • Published • 272