collaborators

8 papers

physics.flu-dyn2026

TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning

Yilong Dai, Yiming Sun, Yiheng Chen +4

Turbulence is a central testbed for machine learning on physical dynamics because its governing laws are known exactly. However, most existing studies remain in 2D, while 3D turbul…

cs.RO2026

TacGen: Touch Is a Necessary Dimension of Physical-World Representation -- Addressing Tactile Data Scarcity with Scalable Vision-to-Touch Alignment and Generation

Wanghao Ye, Aarosh Das, Sihan Chen +19

Touch resolves the physical-property ambiguity left by vision: exploratory contact recovers shape, texture, compliance, and material, and visuo-haptic object representations conver…

physics.flu-dyn2026

Physics-Preserving Latent Compression for Zero-Shot Resolution Transfer in 3D Turbulence

Yilong Dai, Yiming Sun, Yiheng Chen +4

High-resolution turbulence modeling is essential for scientific computing, but remains constrained by the cost of direct numerical simulation and the scarcity of full-resolution da…

cs.HC2026

StreetDesignAI: Broadening Designer Perspectives Through Multi-Persona Evaluation of Cycling Infrastructure

Ziyi Wang, Yilong Dai, Duanya Lyu +5

Designing cycling infrastructure requires balancing the competing needs of diverse user groups, yet designers often struggle to anticipate how different cyclists experience the sam…

cs.AI2026

From Image Generation to Infrastructure Design: a Multi-agent Pipeline for Street Design Generation

Chenguang Wang, Xiang Yan, Yilong Dai +2

Realistic visual renderings of street-design scenarios are essential for public engagement in active transportation planning. Traditional approaches are labor-intensive, hindering…

cs.LG2026

Learning PDE Solvers with Physics and Data: A Unifying View of Physics-Informed Neural Networks and Neural Operators

Yilong Dai, Shengyu Chen, Ziyi Wang +4

Partial differential equations (PDEs) are central to scientific modeling. Modern workflows increasingly rely on learning-based components to support model reuse, inference, and int…