19 papers
Code2Worlds-2: Physically Plausible Agent Harness for Embodied World Simulation
Haoyu Zhang, Siming Li, Zeyu Zhang +3
Recent coding large language models (LLMs) can synthesize dynamic 4D worlds from natural language, but the resulting content remains a visual artifact. It lacks physical semantics…
Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis
Sixu Yan, Shikang Wang, Binhua Huang +11
This paper proposes AdaRoboVLG, a task-adaptive Vision-Language-Grasp (VLG) framework that supports generalizable grasp synthesis across different robotic hands. Unlike existing VL…
GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning
Haoyu Wang, Guoqing Ma, Zeyu Zhang +3
Generalist vision-language-action systems need object-centric 3D evidence and reusable manipulation experience to plan reliable robot trajectories. GeneralVLA provides a hierarchic…
SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction
Yiran Wang, Zeyu Zhang, Yuanming Li +2
High-quality 4D head avatars from one or a few source portraits are central to telepresence, AR/VR, and digital-human interaction. 3D Gaussian Splatting (3DGS) has emerged as the d…
MotionVLA: Vision-Language-Action Model for Humanoid Motion
Nonghai Zhang, Siyu Zhai, Yanjun Li +5
Generating realistic humanoid motion from scene images and text involves both low-frequency pose semantics and high-frequency physical dynamics. However, many existing methods toke…
DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects
Tianshan Zhang, Yijia Duan, Yanjun Li +2
Dexterous interaction with articulated objects is important for household, assistive, and humanoid manipulation, where multi-finger hands can provide compliant contact patterns bey…
PresentAgent-2: Towards Generalist Multimodal Presentation Agents
Wei Wu, Ziyang Xu, Zeyu Zhang +2
Presentation generation is moving beyond static slide creation toward end-to-end presentation video generation with research grounding, multimodal media, and interactive delivery.…
Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction
Haoyu Zhang, Zeyu Zhang, Zedong Zhou +2
Transformer-based 3D reconstruction has emerged as a powerful paradigm for recovering geometry and appearance from multi-view observations, offering strong performance across chall…
Dynamic Execution Commitment of Vision-Language-Action Models
Feng Chen, Xianghui Wang, Yuxuan Chen +4
Vision-Language-Action (VLA) models predominantly adopt action chunking, i.e., predicting and committing to a short horizon of consecutive low-level actions in a single forward pas…
LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models
Zicheng Duan, Jiatong Xia, Zeyu Zhang +7
Recent generative video world models aim to simulate visual environment evolution, allowing an observer to interactively explore the scene via camera control. However, they implici…
MWM: Mobile World Models for Action-Conditioned Consistent Prediction
Han Yan, Zishang Xiang, Zeyu Zhang +1
World models enable planning in imagined future predicted space, offering a promising framework for embodied navigation. However, existing navigation world models often lack action…
MMA: Multimodal Memory Agent
Yihao Lu, Wanru Cheng, Zeyu Zhang +1
Long-horizon multimodal agents depend on external memory; however, similarity-based retrieval often surfaces stale, low-credibility, or conflicting items, which can trigger overcon…
Light4D: Training-Free Extreme Viewpoint 4D Video Relighting
Zhenghuang Wu, Kang Chen, Zeyu Zhang +1
Recent advances in diffusion-based generative models have established a new paradigm for image and video relighting. However, extending these capabilities to 4D relighting remains…
Code2Worlds: Empowering Coding LLMs for 4D World Generation
Yi Zhang, Yunshuang Wang, Zeyu Zhang +1
Achieving spatial intelligence requires moving beyond visual plausibility to build world simulators grounded in physical laws. While coding LLMs have advanced static 3D scene gener…
GeneralVLA: Generalizable Vision-Language-Action Models with Knowledge-Guided Trajectory Planning
Guoqing Ma, Siheng Wang, Zeyu Zhang +2
Large foundation models have shown strong open-world generalization to complex problems in vision and language, but similar levels of generalization have yet to be achieved in robo…
AnyDepth: Depth Estimation Made Easy
Zeyu Ren, Zeyu Zhang, Wukai Li +2
Monocular depth estimation aims to recover the depth information of 3D scenes from 2D images. Recent work has made significant progress, but its reliance on large-scale datasets an…
SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation
Yiling Wang, Zeyu Zhang, Yiran Wang +1
Text-to-motion (T2M) generation with diffusion backbones achieves strong realism and alignment. Safety concerns in T2M methods have been raised in recent years; existing methods re…
DragMesh: Interactive 3D Generation Made Easy
Tianshan Zhang, Zeyu Zhang, Hao Tang
While generative models have excelled at creating static 3D content, the pursuit of systems that understand how objects move and respond to interactions remains a fundamental chall…
EgoLCD: Egocentric Video Generation with Long Context Diffusion
Liuzhou Zhang, Jiarui Ye, Yuanlei Wang +6
Generating long, coherent egocentric videos is difficult, as hand-object interactions and procedural tasks require reliable long-term memory. Existing autoregressive models suffer…