1 citations · 1 across the 11 of their papers we have counts for
12 papers
AdvDex: Learning Dexterous Manipulation from Human Demonstrations via Joint-Aligned Actions and Adversarial Learning
Zhiyue Zhao, Jingyi Wu, Hairuo Liu +5
Dexterous manipulation is a fundamental capability for embodied intelligence, but scaling it remains difficult because robot demonstrations are expensive to collect and action spac…
Geo-Align: Video Generation Alignment via Metric Geometry Reward
Zizun Li, Haoyu Guo, Runzhe Teng +2
Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rely on Supervised Fine-Tuning…
Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
Yifan Wang, Tong He
Camera-controlled video generation has made substantial progress, enabling generated videos to follow prescribed viewpoint trajectories. However, existing methods usually learn cam…
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
Haoyi Zhu, Haozhe Liu, Yuyang Zhao +6
We introduce SANA-WM, an efficient 2.6B-parameter open-source world model natively trained for one-minute generation, synthesizing high-fidelity, 720p, minute-scale videos with pre…
Learning Primitive Embodied World Models: Towards Scalable Robotic Learning
Qiao Sun, Liujia Yang, Wei Tang +12
While video-generation-based embodied world models have gained increasing attention, their reliance on large-scale embodied interaction data remains a key bottleneck. The scarcity,…
: Permutation-Equivariant Visual Geometry Learning
Yifan Wang, Jianjun Zhou, Haoyi Zhu +7
We introduce , a feed-forward neural network that offers a novel approach to visual geometry reconstruction, breaking the reliance on a conventional fixed reference view. Prev…
VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
Yating Wang, Haoyi Zhu, Mingyu Liu +3
In this paper, we introduce an innovative vector quantization based action tokenizer built upon the largest-scale action trajectory dataset to date, leveraging over 100 times more…
DeepVerse: 4D Autoregressive Video Generation as a World Model
Junyi Chen, Haoyi Zhu, Xianglong He +8
World models serve as essential building blocks toward Artificial General Intelligence (AGI), enabling intelligent agents to predict future states and plan actions by simulating co…
CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning
Jiange Yang, Yansong Shi, Haoyi Zhu +6
Unsupervised learning of latent motion from Internet videos is crucial for robot learning. Existing discrete methods generally mitigate the shortcut learning caused by extracting e…
Aether: Geometric-Aware Unified World Modeling
Aether Team, Haoyi Zhu, Yifan Wang +8
The integration of geometric reconstruction and generative modeling remains a critical challenge in developing AI systems capable of human-like spatial reasoning. This paper propos…
Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning
Jiange Yang, Haoyi Zhu, Yating Wang +3
Learning from multiple domains is a primary factor that influences the generalization of a single unified robot system. In this paper, we aim to learn the trajectory prediction mod…
SPA: 3D Spatial-Awareness Enables Effective Embodied Representation
Haoyi Zhu, Honghui Yang, Yating Wang +3
In this paper, we introduce SPA, a novel representation learning framework that emphasizes the importance of 3D spatial awareness in embodied AI. Our approach leverages differentia…