4 papers · 1 filter
ActionSplice: In-Flight Action Editing for Interactive World Models
Pardis Taghavi, Tingyu Guo, Jonas Lossner +2
Chunk-autoregressive video world models typically generate each chunk under one action. When an action changes during sampling, waiting until the next chunk delays the response, wh…
Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models
Pardis Taghavi, Reza Langari, Gaurav Pandey
Block-sparse attention accelerates video transformers by grouping queries and keys and computing attention only between selected groups. However, it faces two challenges: (1) queri…
Toward Unified Multimodal Representation Learning for Autonomous Driving
Ximeng Tao, Dimitar Filev, Gaurav Pandey
Contrastive Language-Image Pre-training (CLIP) has shown impressive performance in aligning visual and textual representations. Recent studies have extended this paradigm to 3D vis…
3DGS-ReLoc: 3D Gaussian Splatting for Map Representation and Visual ReLocalization
Peng Jiang, Gaurav Pandey, Srikanth Saripalli
This paper presents a novel system designed for 3D mapping and visual relocalization using 3D Gaussian Splatting. Our proposed method uses LiDAR and camera data to create accurate…