Researcher

Xiaofan Li

World Model Tech Lead, X Square Robot

Role and affiliation as stated on the event page. Publication count is the co-author cluster pinned by a paper listed on their own site among 57 arXiv papers published under this name.

Recent work

• ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation
• When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
• Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
• Artemis: Structured Visual Reasoning for Perception Policy Learning
• Agentic Learner with Grow-and-Refine Multimodal Semantic Memory
• FaithFusion: Harmonizing Reconstruction and Generation via Pixel-wise Information Gain

From the resolved cluster. Most recent submission 2026-07-30.

Works on

Papers in this index

Matched on author name across this corpus only. Common names can collide, so tell us if one is wrong.