18 citations · 20 across the 9 of their papers we have counts for
10 papers
Representation Fréchet Loss for Visual Generation
Jiawei Yang, Zhengyang Geng, Xuan Ju +2
We show that Fréchet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decou…
LOME: Learning Human-Object Manipulation with Action-Conditioned Egocentric World Model
Quankai Gao, Jiawei Yang, Qiangeng Xu +2
Learning human-object manipulation presents significant challenges due to its fine-grained and contact-rich nature of the motions involved. Traditional physics-based animation requ…
Latent Denoising Makes Good Tokenizers
Jiawei Yang, Tianhong Li, Lijie Fan +2
Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a co…
InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models
Yifan Lu, Xuanchi Ren, Jiawei Yang +8
We present InfiniCube, a scalable method for generating unbounded dynamic 3D driving scenes with high fidelity and controllability. Previous methods for scene generation either suf…
OmniRe: Omni Urban Scene Reconstruction
Ziyu Chen, Jiawei Yang, Jiahui Huang +9
We introduce OmniRe, a comprehensive system for efficiently creating high-fidelity digital twins of dynamic real-world scenes from on-device logs. Recent methods using neural field…
Parallelized Spatiotemporal Binding
Gautam Singh, Yue Wang, Jiawei Yang +4
While modern best practices advocate for scalable architectures that support long-range interactions, object-centric models are yet to fully embrace these architectures. In particu…
Denoising Vision Transformers
Jiawei Yang, Katie Z Luo, Jiefeng Li +6
We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs i…
Rethinking Directional Integration in Neural Radiance Fields
Congyue Deng, Jiawei Yang, Leonidas Guibas +1
Recent works use the Neural radiance field (NeRF) to perform multi-view 3D reconstruction, providing a significant leap in rendering photorealistic scenes. However, despite its eff…
Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Maps
Katie Z Luo, Xinshuo Weng, Yan Wang +5
Autonomous driving has traditionally relied heavily on costly and labor-intensive High Definition (HD) maps, hindering scalability. In contrast, Standard Definition (SD) maps are m…
EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
Jiawei Yang, Boris Ivanovic, Or Litany +8
We present EmerNeRF, a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. Grounded in neural fields, EmerNeRF simultaneously capt…