11 papers
H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models
Dingyi Rong, Yue Shi, Chaofan Ma +6
Large-scale manipulation data is essential for robot learning, yet collecting robot demonstrations remains expensive and difficult to scale. Meanwhile, abundant egocentric human ma…
RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation
Dayu Xia, Yue Shi, Yao Mu +7
Vision-language models (VLMs) are increasingly explored as visual critics, reward generators, and failure detectors in robotic manipulation. These roles implicitly require models t…
Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning
Chaofan Ma, Zhenjie Mao, Yuhuan Yang +5
Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory. Existing methods rely on single-turn inf…
GenMask: Adapting DiT for Segmentation via Direct Mask Generation
Yuhuan Yang, Xianwei Zhuang, Yuxuan Cai +6
Recent approaches for segmentation have leveraged pretrained generative models as feature extractors, treating segmentation as a downstream adaptation task via indirect feature ret…
UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing
Dianyi Wang, Chaofan Ma, Feng Han +8
Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabil…
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
Dianyi Wang, Ruihang Li, Feng Han +17
Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment foot…