4 papers
GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Models
Qi Qin, Jiajie Zhu, Dali Chen +6
Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and memory costs, hindering lar…
From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents
Zijie Zhuang, Changxin Lao, Pengbo Xu +13
Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajectories to guide later decisions.…
SciForma: Structure-Faithful Generation of Scientific Diagrams
Yuxuan Luo, Peng Zhang, Xinjie Zhang +3
Structural fidelity is essential to scientific methodology diagrams. To communicate research logic, these diagrams must faithfully render components, directional relations, and tex…
AgenticDataBench: A Comprehensive Benchmark for Data Agents
Zhaoyan Sun, Shan Zhong, Daizhou Wen +10
Data science aims to derive actionable insights from heterogeneous raw data, unlocking the value of the massive amounts of data generated in modern society. Automating this process…