5 papers
CorrRisk-WM: Corridor-Conditioned Risk World Modeling for Safety-Critical Trajectory Planning
Tingyu Guo, Reza Langari
Safe local planning requires forecasting surrounding-agent motion and evaluating candidate-specific risks, since identical agent motion can pose different risks to different ego tr…
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…
Training a Student Expert via Semi-Supervised Foundation Model Distillation
Pardis Taghavi, Tian Liu, Renjie Li +2
Foundation models deliver strong perception but are often too computationally heavy to deploy, and adapting them typically requires costly annotations. We introduce a semi-supervis…
NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Driving
Ximeng Tao, Pardis Taghavi, Dimitar Filev +2
Vision-language models (VLMs) have emerged as a promising direction for end-to-end autonomous driving (AD) by jointly modeling visual observations, driving context, and language-ba…