The Hoi! dataset will be presented as a Highlight paper during CVPR 2026 in Denver!
Excited to share that our papers Hoi! A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation and FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning have been accepted to #CVPR2026 🎉
I will be serving as a Poster Chair for ECCV 2026 in Malmö—looking forward to an exciting conference!
Our paper Video Perception Models for 3D Scene Synthesis has been accepted to #NeurIPS2025 🎉
Heading to #BMVC? Check out our paper MonoTracker: Monocular RGB-Only 6D Tracking of Unknown Objects!
Attending #ICCV? Come by our poster on 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection!
Going to #IROS2025 in China? Stop by our poster Lost and Found: Updating Dynamic 3D Scene Graphs from Egocentric Observations!
SpotLight: Robotic Scene Understanding through Interaction and Affordance Detection accepted to #Humanoids2025 in Korea—see you there!
Our work CroCoDL: Cross-device Collaborative Dataset for Localization will be presented at #CVPR2025 in Nashville—come say hi at our poster!