5 papers
SymbolicLM: Training Language Models as Symbolic Regressors
Jun Yao, Yingfan Hua, Ruikun Li +4
Large Language Models (LLMs) have shown promising capabilities in scientific reasoning, yet scientific discovery ultimately requires deriving precise laws directly from observation…
Pixel2Phys: Distilling Governing Laws from Visual Dynamics
Ruikun Li, Jun Yao, Yingfan Hua +5
Discovering physical laws directly from high-dimensional visual data is a long-standing human pursuit but remains a formidable challenge for machines, representing a fundamental go…
Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning
Yuhao Zhou, Yiheng Wang, Xuming He +26
Scientific discoveries increasingly rely on complex multimodal reasoning based on information-intensive scientific data and domain-specific expertise. Empowered by expert-level sci…
MLLM-based Discovery of Intrinsic Coordinates and Governing Equations from High-Dimensional Data
Ruikun Li, Yan Lu, Shixiang Tang +2
Discovering governing equations from scientific data is crucial for understanding the evolution of systems, and is typically framed as a search problem within a candidate equation…
FuncGenFoil: Airfoil Generation and Editing Model in Function Space
Jinouwen Zhang, Junjie Ren, Qianhong Ma +9
Aircraft manufacturing is the jewel in the crown of industry, in which generating high-fidelity airfoil geometries with controllable and editable representations remains a fundamen…