Ismini Lourentzou

CoDA: Co-Evolution of Data Engines and Action Policies

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

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

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

DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation

Haoran Yuan, Zekai Wang, Boning Shao, et al.

One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing

Adheesh Sunil Juvekar, Onkar Kishor Susladkar, Kiet A. Nguyen, et al.

GraphVid: Interactive Graph-Controllable Video Generation

Vedant Shah, Onkar Susladkar, Tushar Prakash, et al.

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

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

ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning

Yanjun Zhao, Ruizhong Qiu, Tianxin Wei, et al.

RewardFlow: Generate Images by Optimizing What You Reward

Onkar Susladkar, Dong-Hwan Jang, Tushar Prakash, et al.

VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs

Haoran Yuan, Weigang Yi, Zhenyu Zhang, 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.