AI.info
Cordelia Schmid
Explore Cordelia Schmid on AI.info.
- MINERVA-Cultural: A Benchmark for Cultural and Multilingual Long Video Reasoning
- Guardian: Detecting Robotic Planning and Execution Errors with Vision-Language Models
- FOM-Nav: Frontier-Object Maps for Object Goal Navigation
- VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation
- CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects