collaborators

5 papers

cs.LG2026

SkillTFM: Gated Skill Evolution for Training-Free Adaptation of Tabular Foundation Models

Yi He, Zhengkang Guan, Anpeng Wu +3

Tabular data are ubiquitous in real-world applications and are crucial for data-driven prediction and decision-making across science, industry, finance, healthcare, and public serv…

cs.LG2026

DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms

Yikang Chen, Zhengkang Guan, Haoyuan Qian +5

The paper presents DAG-FM, a transformer‑based foundation model that discovers causal directed acyclic graphs from tabular data by sequentially predicting leaf and parent nodes and…

cs.LG2026

A Knowledge-Informed Pretrained Model for Causal Discovery

Wenbo Xu, Yue He, Yunhai Wang +4

Causal discovery has been widely studied, yet many existing methods rely on strong assumptions or fall into two extremes: either depending on costly interventional signals or parti…

cs.LG2025

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence

Xingxuan Zhang, Gang Ren, Han Yu +35

We argue that progress toward general intelligence requires complementary foundation models grounded in language, the physical world, and structured data. This report presents Limi…

cs.LG2025

Environment Inference for Learning Generalizable Dynamical System

Shixuan Liu, Yue He, Haotian Wang +4

Data-driven methods offer efficient and robust solutions for analyzing complex dynamical systems but rely on the assumption of I.I.D. data, driving the development of generalizatio…