Song-Chun Zhu
2 papers · 0 citations
Most-cited papers
- Spatio-temporal Self-supervised Representation Learning For 3D Point Clouds2021 · 177 citations
- LEO-VL: Efficient Scene Representation For Scalable 3D Vision-language Learning2025
- Siv-bench: A Video Benchmark For Social Interaction Understanding And Reasoning2026
- Siv-bench: A Video Benchmark For Social Interaction Understanding And Reasoning2026
- Videoartgs: Building Digital Twins Of Articulated Objects From Monocular Video2025
- Grounding Before Generalizing: How AI Differs From Humans In Causal Transfer2026
- Grounding Before Generalizing: How AI Differs From Humans In Causal Transfer2026
Topics