activity
20242026
collaborators

5 papers

cs.LG2026

LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models

Yuanrui Wang, Xingxuan Zhang, Han Yu +7

Tabular foundation models (TFMs) increasingly rival tree ensembles, but their performance is often compute-inefficient: with standard affine scalar tokenization, each feature injec…

cs.LG2026

Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning

Xinyan Han, Yan Lu, Xiaoyu Lin +5

Tabular data synthesis aims to generate high-quality data while preserving privacy. However, we find that existing tabular generative models exhibit a clear tradeoff in the small-d…

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.CV2025

UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis

Yuanrui Wang, Cong Han, Yafei Li +8

Text-to-image generation has greatly advanced content creation, yet accurately rendering visual text remains a key challenge due to blurred glyphs, semantic drift, and limited styl…

cs.CV2024

ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts

Sinan Du, Guosheng Zhang, Keyao Wang +7

Parameter-efficient transfer learning (PETL) has become a promising paradigm for adapting large-scale vision foundation models to downstream tasks. Typical methods primarily levera…