5 papers
TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers
Bin Yu, Shijie Lian, Xiaopeng Lin +8
The fundamental premise of Vision-Language-Action (VLA) models is to harness the extensive general capabilities of pre-trained Vision-Language Models (VLMs) for generalized embodie…
PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence
Xiaopeng Lin, Shijie Lian, Bin Yu +10
Robotic generalization relies on physical intelligence: the ability to reason about state changes, contact-rich interactions, and long-horizon planning under egocentric perception…
DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry
Changti Wu, Shijie Lian, Zihao Liu +3
Solid geometry problem solving demands spatial mathematical reasoning that integrates spatial intelligence and symbolic reasoning. However, most existing multimodal mathematical re…
TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model
Bin Yu, Xinming Wang, Shijie Lian +6
Large language models (LLMs) have shown remarkable progress in complex reasoning tasks, largely enabled by test-time scaling (TTS) paradigms that allocate additional compute during…
Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks
Shijie Lian, Changti Wu, Laurence Tianruo Yang +4
Spatial intelligence spans a rich suite of abilities, including visualising and transforming shapes, mentally rotating objects, judging relational positions and containment, and es…