SuanLab에 오신 것을 환영합니다

Current video generation models cannot simulate physical consequences of 3D actions like forces and robotic manipulations, as they lack structural understanding of how actions affect 3D scenes. We pre...

We introduce Helios, the first 14B video generation model that runs at 19.5 FPS on a single NVIDIA H100 GPU and supports minute-scale generation while matching the quality of a strong baseline. We mak...

We present Phi-4-reasoning-vision-15B, a compact open-weight multimodal reasoning model, and share the motivations, design choices, experiments, and learnings that informed its development. Our goal i...

The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models remains opaque. We pr...

Vision-Language-Action (VLA) models are a promising path toward embodied intelligence, yet they often overlook the predictive and temporal-causal structure underlying visual dynamics. World-model VLAs...

Continuous knowledge updating for pre-trained large language models (LLMs) is increasingly necessary yet remains challenging. Although inference-time methods like In-Context Learning (ICL) and Retriev...