OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic Segmentation Paper • 2604.08110 • Published Apr 10 • 2
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction Paper • 2605.26115 • Published 13 days ago • 51
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Paper • 2507.19457 • Published Jul 25, 2025 • 34
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Paper • 2604.14268 • Published Apr 15 • 123
SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning Paper • 2412.04077 • Published Dec 5, 2024
SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design Paper • 2401.16456 • Published Jan 29, 2024
Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models Paper • 2603.25750 • Published Mar 20 • 36