Kexian Tang — accepted AI-conference papers

2026

SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection

Kexian Tang, Jiani Wang, Shaowen Wang, Kaifeng Lyu

ICML 2026poster

While large language models (LLMs) are pretrained on massive amounts of data, their knowledge coverage remains incomplete in specialized, data-scarce domains, motivating extensive efforts to study synthetic data generation for knowledge injection. We propose **SPA** (**S**caling **P**rompt-engineere…

Cited by 0 Source ↗Scholar ↗

2025

Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing

Xiangyu Zhao, Peiyuan Zhang, Kexian Tang, Xiaorong Zhu, Hao Li, Wenhao Chai +7

NeurIPS 2025oral

Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in following complex instructions, preserving appearance consistency, and supporting flexible input formats. To study this…

Cited by 0 Source ↗code ↗Scholar ↗