…Shuai Wang , , , , , Abstract UniDDT addresses key challenges in unified multimodal models by leveraging a Noisy ViT encoder and LLM for semantic encoding while using separate diffusion decoders to balance visual understanding and…
…Unifying Egocentric Human and Robotic Data for VLA Pretraining Published on Jun 15 Submitted by Siyuan on Jun 17 CUHK Authors: , , , , , , , , , , Abstract A unified Vision-Language-Action pretraining framework leverages heterogeneous data…
…A Unified Video-Action World Model for Robotic Manipulation Published on May 31 Submitted by Jianlan Luo on Jun 2 Authors: , , , , , , , , , , , , , , , , , , , Abstract A unified video-action world model integrates policy learning, video…
Papers arxiv:2604.26694 Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising Published on Apr 29 Submitted by taesiri on Apr 30 Authors: , , , , , , , , , Abstract X-WAM is a unified…
…Unifying Heterogeneous Evaluation Criteria via Agent Skill Published on Jun 2 Submitted by Siyuan Huang on Jun 9 Authors: , , , Siyuan Huang , , , , , , , , , Abstract Skill-RM presents a unified reward modeling framework that treats…
…Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning Published on May 12 Submitted by Jindong Wang on May 13 The College of William & Mary Authors: , , , , Abstract Unified multimodal models can…
…Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness (2026) AniGen: Unified $S^3$ Fields for Animatable 3D Asset Generation (2026) Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed…
…A Unified Plugin Framework for Controllable Diffusion Published on Apr 27 Submitted by Yingda Chen on Apr 30 Authors: Zhongjie Duan , , Yingda Chen Abstract Diffusion Templates presents a unified framework that decouples…
…Unified Discrete Vision-Action Token Editing for World-Policy Learning Published on Jun 4 Submitted by taesiri on Jun 5 Xiaomi Research Authors: , , , , , , , , , , , , Abstract Discrete-WAM introduces a unified discrete latent vision…
…With natural language as a unified action interface, it predicts physically grounded future visual trajectories from current observations across robotic manipulation, autonomous driving, indoor navigation, and human-to-robot transfer. This unified…