08:15 — 09:00
Invited talk
NVIDIA
SIL-Wheel: A Multi-Modal Search and Curation Platform for Physical AI Systems
09:00 — 09:45
09:45 — 10:15
Oral session I
Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Models
Jihun Kim
AGT-CV: An Aerial-Ground Team Cross-View Dataset for Heterogeneous Robot Teams in Unstructured Environments
Knut Peterson
10:15 — 11:00
11:00 — 12:30
Poster session
Boards 261–311 · All accepted papers
12:30 — 13:30
Lunch
13:30 — 14:15
Invited talk
Johns Hopkins University
Fine-Grained Skill-Specific Evaluation and Targeted Curriculum for Efficient Learning
14:15 — 15:00
Oral session II
BabyLand-72: Synthetic-to-Real Multi-View Infant Facial Landmark Estimation
José Carlos Reyes Hernández
Diffuse the Object, Keep Its Label: Curating Detector Training Data from a Few Unlabeled Photographs via VLM-Built 3D Vegetation Scenes
Mario Malizia
Speed-Variation Distillation for Generative Modeling
Sukit Seripanitkarn
15:00 — 15:45
Invited talk
Carnegie Mellon University
Automating Training Data Design with Metagradient Descent
15:45 — 16:00
Coffee break
16:00 — 16:45
16:45 — 17:30
Invited talk · Closing speaker
Columbia University
World Models as Data Engines for Robotics
17:30 — 17:40
Closing remarks