32 citations · 58 across the 17 of their papers we have counts for
17 papers
Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization
Jiaming Zhou, Qihang Zhang, Gangwei Xu +9
Zero-shot cross-task generalization, where a policy must execute manipulation tasks never seen during training, remains a central challenge in robot learning. In large language mod…
4DAnyone: Create Anyone in 4D from a Casual Monocular Video
Yudong Jin, Tao Xie, Qihang Zhang +6
We present 4DAnyone, a framework for reconstructing 4D humans from an uncalibrated monocular video by generating reconstruction-grade multiview-consistent videos and lifting them i…
Native Video-Action Pretraining for Generalizable Robot Control
Qihang Zhang, Lin Li, Luyao Zhang +26
The advent of video-action models offers a promising path for robot control. Nevertheless, we argue that repurposing video generative models designed for digital content creation i…
RepWAM: World Action Modeling with Representation Visual-Action Tokenizers
Junke Wang, Qihang Zhang, Shuai Yang +5
This work presents RepWAM, a representation-centric world action model (WAM) built on representation visual-action tokenizers. Existing WAMs typically inherit reconstruction-orient…
Next Forcing: Causal World Modeling with Multi-Chunk Prediction
Gangwei Xu, Qihang Zhang, Jiaming Zhou +4
Autoregressive video generation has emerged as a powerful paradigm for World Action Models (WAMs). However, existing approaches suffer from slow training convergence and limited co…
3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting
Qihang Zhang, Yinghao Xu, Chaoyang Wang +4
Scene image editing is crucial for entertainment, photography, and advertising design. Existing methods solely focus on either 2D individual object or 3D global scene editing. This…
Urban Scene Diffusion through Semantic Occupancy Map
Junge Zhang, Qihang Zhang, Li Zhang +3
Generating unbounded 3D scenes is crucial for large-scale scene understanding and simulation. Urban scenes, unlike natural landscapes, consist of various complex man-made objects a…
SceneWiz3D: Towards Text-guided 3D Scene Composition
Qihang Zhang, Chaoyang Wang, Aliaksandr Siarohin +7
We are witnessing significant breakthroughs in the technology for generating 3D objects from text. Existing approaches either leverage large text-to-image models to optimize a 3D r…
BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation
Qihang Zhang, Yinghao Xu, Yujun Shen +3
Generating large-scale 3D scenes cannot simply apply existing 3D object synthesis technique since 3D scenes usually hold complex spatial configurations and consist of a number of o…
Learning Modulated Transformation in GANs
Ceyuan Yang, Qihang Zhang, Yinghao Xu +3
The success of style-based generators largely benefits from style modulation, which helps take care of the cross-instance variation within data. However, the instance-wise stochast…
GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding
Jihao Liu, Tai Wang, Boxiao Liu +3
Multi-view camera-based 3D detection is a challenging problem in computer vision. Recent works leverage a pretrained LiDAR detection model to transfer knowledge to a camera-based s…
Towards Smooth Video Composition
Qihang Zhang, Ceyuan Yang, Yujun Shen +2
Video generation requires synthesizing consistent and persistent frames with dynamic content over time. This work investigates modeling the temporal relations for composing video w…
Generative Category-Level Shape and Pose Estimation with Semantic Primitives
Guanglin Li, Yifeng Li, Zhichao Ye +4
Empowering autonomous agents with 3D understanding for daily objects is a grand challenge in robotics applications. When exploring in an unknown environment, existing methods for o…
F3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks
Xintian Wu, Qihang Zhang, Yiming Wu +4
Formulated as a conditional generation problem, face animation aims at synthesizing continuous face images from a single source image driven by a set of conditional face motion. Pr…
Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining
Qihang Zhang, Zhenghao Peng, Bolei Zhou
Deep visuomotor policy learning, which aims to map raw visual observation to action, achieves promising results in control tasks such as robotic manipulation and autonomous driving…
MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning
Quanyi Li, Zhenghao Peng, Lan Feng +3
Driving safely requires multiple capabilities from human and intelligent agents, such as the generalizability to unseen environments, the safety awareness of the surrounding traffi…
Improving the Generalization of End-to-End Driving through Procedural Generation
Quanyi Li, Zhenghao Peng, Qihang Zhang +2
Over the past few years there is a growing interest in the learning-based self driving system. To ensure safety, such systems are first developed and validated in simulators before…