13 papers
LogiShot: Logically Coherent Cross-Shot Video Generation
Shuai Guo, Yuhang Yang, Zeyu Zhang +4
Generating cross-shot videos that are logically connected is essential for content creation. Currently, most cross-shot video-generation workflows, such as short-drama production,…
Dual-Pathway Geometry-Aware MLLM for Spatial Intelligence
Yufei Zheng, Xuhan Zhu, Zide Liu +9
Spatial understanding of the physical world from 2D visual inputs hinges on two complementary forms of geometric knowledge: holistic 3D structural perception and fine-grained metri…
TIE: Time Interval Encoding for Video Generation over Events
Zhilei Shu, Shangwen Zhu, Zihang Liang +10
Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events -- a regime in which 68% of general clips and ove…
Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
Chenfeng Wang, Wei He, Xuhan Zhu +10
In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent…
Stereo World Model: Camera-Guided Stereo Video Generation
Yang-Tian Sun, Zehuan Huang, Yifan Niu +4
We present StereoWorld, a camera-conditioned stereo world model that jointly learns appearance and binocular geometry for end-to-end stereo video generation.Unlike monocular RGB or…
End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction
Haoyu Zhang, Wei Zhai, Yuhang Yang +2
Monocular 4D human-object interaction (HOI) reconstruction - recovering a moving human and a manipulated object from a single RGB video - remains challenging due to depth ambiguity…
EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning
Chengjun Yu, Xuhan Zhu, Chaoqun Du +4
Multimodal large language models (MLLMs) are increasingly considered as a foundation for embodied agents, yet it remains unclear whether they can reliably reason about the long-ter…
Event-based Visual Deformation Measurement
Yuliang Wu, Wei Zhai, Yuxin Cui +3
Visual Deformation Measurement (VDM) aims to recover dense deformation fields by tracking surface motion from camera observations. Traditional image-based methods rely on minimal i…
OmniVaT: Single Domain Generalization for Multimodal Visual-Tactile Learning
Liuxiang Qiu, Hui Da, Yuzhen Niu +3
Visual-tactile learning (VTL) enables embodied agents to perceive the physical world by integrating visual (VIS) and tactile (TAC) sensors. However, VTL still suffers from modality…
TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions
Guangyi Han, Wei Zhai, Yuhang Yang +2
Hand-object interaction (HOI) is fundamental for humans to express intent. Existing HOI generation research is predominantly confined to fixed grasping patterns, where control is t…
GRACE: Estimating Geometry-level 3D Human-Scene Contact from 2D Images
Chengfeng Wang, Wei Zhai, Yuhang Yang +2
Estimating the geometry level of human-scene contact aims to ground specific contact surface points at 3D human geometries, which provides a spatial prior and bridges the interacti…
VideoGen-Eval: Agent-based System for Video Generation Evaluation
Yuhang Yang, Ke Fan, Shangkun Sun +7
The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot sho…
SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets
Yuhang Yang, Fengqi Liu, Yixing Lu +8
3D human digitization has long been a highly pursued yet challenging task. Existing methods aim to generate high-quality 3D digital humans from single or multiple views, but remain…