8 papers
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
Yalun Dai, Hao Li, Shulin Tian +8
Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely remain tied to static, stateless inf…
IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer
Zhengyu Zou, Hao Li, Kuixuan Jiao +7
Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spa…
PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning
Shaoxuan Li, Zhixuan Zhao, Hanze Deng +9
We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning. PerceptionComp is designed so that no single moment is su…
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
Yuanyuan Gao, Hao Li, Yifei Liu +14
The pursuit of spatial intelligence fundamentally relies on access to large-scale, fine-grained 3D data. However, existing approaches predominantly construct spatial understanding…
BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model
Haosheng Li, Weixin Mao, Zihan Lan +6
Vision-Language-Action (VLA) models have achieved significant breakthroughs by leveraging Large Vision Language Models (VLMs) to jointly interpret instructions and visual inputs. H…
OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer
Haosong Peng, Hao Li, Yalun Dai +8
General 3D foundation models have started to lead the trend of unifying diverse vision tasks, yet most assume RGB-only inputs and ignore readily available geometric cues (e.g., cam…
IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
Hao Li, Zhengyu Zou, Fangfu Liu +8
Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions, enabling coherent and accurate understanding of complex scenes. Howe…
From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors
Zhengshen Zhang, Hao Li, Yalun Dai +10
Existing vision-language-action (VLA) models act in 3D real-world but are typically built on 2D encoders, leaving a spatial reasoning gap that limits generalization and adaptabilit…