1 citations · 1 across the 20 of their papers we have counts for
18 papers · 1 filter
Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models
Juncheng Ma, Jiaxin Li, Jiankai Tu +30
Egocentric human video offers a scalable source of manipulation priors for robot learning, yet translating raw data scale into generalizable robot policies demands rigorous data cu…
RADIANT: Object-Centric Feed-Forward Global Illumination
Sarah Zhang, Zhiyang Dou, Minghao Guo +2
Feed-forward neural renderers synthesize global illumination across novel 3D scenes without per-scene optimization or runtime ray tracing. Existing transformer-based renderers toke…
An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond
Wenbo Zhang, Kaixuan Wang, Yutao Ouyang +9
Embodied AI systems are often organized into System 1 and System 2. System 1 is typically a pretrained policy that generates actions at high frequency, whereas System 2 is often in…
Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation
Jiaben Chen, Sixun Dong, Qinhong Zhou +4
Long-form narrative-to-film generation requires shot-level controllability and cross-clip consistency in both visual identity and character behavior-requirements that remain diffic…
UniMate: One Unified Model to Animate Diverse Skeletons
Linzhan Mou, Jiahui Lei, Zhiyang Dou +4
Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Existing learned animators are to…
HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Weiliang Chen, Haowen Sun, Jun Gao +40
A benchmark should deliver more than a scalar score: what makes an evaluation trustworthy is the reasoning that justifies the score. This is especially critical for world models, w…
GeoBridge: Decoupled Semantic Conditioning for Generative Image Geolocalization
Zhiyang Dou, Xumeng Han, Fengde Peng +4
Multimodal large language models (MLLMs) have advanced image geolocalization mainly by improving how they reason about geographic cues. How that reasoning isdecoded into coordinate…
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
Juncheng Ma, Jianxin Bi, Yufan Deng +19
Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robot trajectories remai…
RigidFormer: Learning Rigid Dynamics using Transformers
Zhiyang Dou, Minghao Guo, Haixu Wu +3
Learning-based simulation of multi-object rigid-body dynamics remains difficult because contact is discontinuous and errors compound over long horizons. Most existing methods remai…
Soft Anisotropic Diagrams for Differentiable Image Representation
Laki Iinbor, Zhiyang Dou, Wojciech Matusik
We introduce Soft Anisotropic Diagrams (SAD), an explicit and differentiable image representation parameterized by a set of adaptive sites in the image plane. In SAD, each site spe…
TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation
Hongyu Zhang, Yufan Deng, Zilin Pan +6
Generating high-quality videos from complex temporal descriptions that contain multiple sequential actions is a key unsolved problem. Existing methods are constrained by an inheren…
Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data
Ke Fan, Shunlin Lu, Minyue Dai +6
Generating diverse and natural human motion sequences based on textual descriptions constitutes a fundamental and challenging research area within the domains of computer vision, g…
ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model
Shunlin Lu, Jingbo Wang, Zeyu Lu +6
The scaling law has been validated in various domains, such as natural language processing (NLP) and massive computer vision tasks; however, its application to motion generation re…
Towards Interactive Global Geolocation Assistant
Zhiyang Dou, Zipeng Wang, Xumeng Han +3
Global geolocation, which seeks to predict the geographical location of images captured anywhere in the world, is one of the most challenging tasks in the field of computer vision.…
ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts
Xumeng Han, Longhui Wei, Zhiyang Dou +6
Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multipl…
Dynamic Realms: 4D Content Analysis, Recovery and Generation with Geometric, Topological and Physical Priors
Zhiyang Dou
My research focuses on the analysis, recovery, and generation of 4D content, where 4D includes three spatial dimensions (x, y, z) and a temporal dimension t, such as shape and moti…
LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment
Peishan Cong, Ziyi Wang, Zhiyang Dou +7
Language-guided scene-aware human motion generation has great significance for entertainment and robotics. In response to the limitations of existing datasets, we introduce LaserHu…
Boosting Segment Anything Model Towards Open-Vocabulary Learning
Xumeng Han, Longhui Wei, Xuehui Yu +6
The recent Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model, showcasing potent zero-shot generalization and flexible prompting. Despite SAM fi…