SFHand presents the first streaming language-guided autoregressive framework for 3D hand forecasting, achieving up to 35.8% gains over prior methods and 13.4% better downstream embodied task performance.
Vidbot: Learning generalizable 3d actions from in-the-wild 2d human videos for zero-shot robotic manipulation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
IGen generates realistic visuomotor training data including actions and temporally coherent visuals from unstructured open-world images via 3D reconstruction and VLM reasoning.
citing papers explorer
-
SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting
SFHand presents the first streaming language-guided autoregressive framework for 3D hand forecasting, achieving up to 35.8% gains over prior methods and 13.4% better downstream embodied task performance.
-
IGen: Scalable Data Generation for Robot Learning from Open-World Images
IGen generates realistic visuomotor training data including actions and temporally coherent visuals from unstructured open-world images via 3D reconstruction and VLM reasoning.