4 papers
Thinking from Above: Efficient Spatial Reasoning with Bird's-Eye-View Visual Tokens
Faizan Siddiqui, Nirav Savaliya, Sahith Reddy Chada +1
Existing video multimodal large language models (MLLMs) organize observations primarily in time, but embodied spatial reasoning requires organizing them in space. Consequently, the…
HRDX: A Large-Scale Vector HD-Map Dataset
Sahith Reddy Chada, Isht Dwivedi, Nirav Savaliya
Reliable autonomous driving requires vectorized HD maps that are geometrically accurate, semantically rich, and scalable to long-horizon driving. However, existing public HD map da…
PredMapNet: Future and Historical Reasoning for Consistent Online HD Vectorized Map Construction
Bo Lang, Nirav Savaliya, Zhihao Zheng +3
High-definition (HD) maps are crucial to autonomous driving, providing structured representations of road elements to support navigation and planning. However, existing query-based…
FAST-EQA: Efficient Embodied Question Answering with Global and Local Region Relevancy
Haochen Zhang, Nirav Savaliya, Faizan Siddiqui +1
Embodied Question Answering (EQA) combines visual scene understanding, goal-directed exploration, spatial and temporal reasoning under partial observability. A central challenge is…