Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models Paper β’ 2604.26951 β’ Published Apr 29 β’ 51
RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments Paper β’ 2604.26067 β’ Published Apr 28 β’ 77
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents Paper β’ 2604.26752 β’ Published Apr 29 β’ 115
Goku: Flow Based Video Generative Foundation Models Paper β’ 2502.04896 β’ Published Feb 7, 2025 β’ 103