Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation Paper • 2610.05608 • Published 4 days ago • 139
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs Paper • 2609.29845 • Published 14 days ago • 105
GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression Paper • 2609.25963 • Published 16 days ago • 17
D3DR: Lighting-Aware Object Insertion in Gaussian Splatting Paper • 2503.06740 • Published Mar 9, 2025 • 1
SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for RGB+Thermal 3D Reconstruction Paper • 2603.18774 • Published Mar 19 • 1