Yifan Shen

CoDA: Co-Evolution of Data Engines and Action Policies

Tianjiao Yu, Zhilin Ou, Yifan Shen, et al.

AssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly

Zhiyuan Qi, Jierui Li, Yifan Shen, et al.

SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation

Tianjiao Yu, Xinzhuo Li, Yifan Shen, et al.

ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

Tianjiao Yu, Xinzhuo Li, Yifan Shen, et al.

DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising

Tianjiao Yu, Xinzhuo Li, Muntasir Wahed, et al.

DreamPartGen is a new AI system that generates 3D objects from text descriptions while understanding them as meaningful parts (like legs, arms, body), similar to how humans think about objects. Unlike previous methods that just focus on shape, this approach ensures each part's appearance matches the text description and that parts work together coherently, resulting in more realistic and interpretable 3D models.