4 papers
A Head Camera Is (Almost) All You Need: An Electronics-Free UMI Glove Labelled and Observed by One Moving Camera
Yosub Shin, Yuan Liu, Igor Molybog
Handheld demonstration devices decouple data collection from the robot, but conventional designs burden the hand with a wrist camera, cables and a pose tracker (SLAM, an IMU, a VR…
m2sv: A Scalable Benchmark for Map-to-Street-View Spatial Reasoning
Yosub Shin, Michael Buriek, Igor Molybog
Vision--language models (VLMs) achieve strong performance on many multimodal benchmarks but remain brittle on spatial reasoning tasks that require aligning abstract overhead repres…
Data-Efficient Curation for Multimodal Reasoning under Fixed Training Protocols
Yosub Shin, Michael Buriek, Boris Sobolev +5
We study data curation for multimodal reasoning in a fixed-protocol fine-tuning regime, where the base model, optimizer, training schedule, and evaluation pipeline are held constan…
Beyond Audio and Pose: A General-Purpose Framework for Video Synchronization
Yosub Shin, Igor Molybog
Video synchronization-aligning multiple video streams capturing the same event from different angles-is crucial for applications such as reality TV show production, sports analysis…