Sifei Liu

QeRL: Beyond Efficiency - Quantization-enhanced Reinforcement Learning for LLMs

3D Aware Region Prompted Vision Language Model

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

Compact GSPN: Scaling Spatial Propagation to Vision Foundation Models

EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos

Real Deep Research from Foundation Model to Robotics

No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

Scaling RL to Long Videos

GSPN-2: Efficient Parallel Sequence Modeling

3D-SPATIAL MULTIMODAL MEMORY

NaVILA: Legged Robot Vision-Language-Action Model for Navigation

CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation

Temporal Prompting Matters: Rethinking Referring Video Object Segmentation