Ax Shuo Xing, Junyuan Hong, Yifan Wang, Runjin Chen, Zhenyu Zhang, Ananth Grama, Zhengzhong Tu, Zhangyang Wang 4/23/2026

LLMs Can Get "Brain Rot": A Pilot Study on Twitter/X

Pilot study testing hypothesis that continual exposure to junk web text induces cognitive decline in LLMs using controlled Twitter/X corpus experiments.

Ax Michal \v{S}tef\'anik, Timothee Mickus, Marek Kadl\v{c}\'ik, Bertram H{\o}jer, Michal Spiegel, Ra\'ul V\'azquez, Aman Sinha, Josef Kucha\v{r}, Philipp Mondorf, Pontus Stenetorp 4/23/2026

Language Models Learn Universal Representations of Numbers and Here's Why You Should Care

Analysis showing LLMs develop universal sinusoidal representations of numbers across different families, with representations largely interchangeable across models.

Ax Rishiraj Saha Roy, Chris Hinze, Luzian Hahn, Fabian Kuech 4/23/2026

CEDAR: Context Engineering for Agentic Data Science

CEDAR agentic system automating data science tasks via context engineering, handling complexity, data size, and computational constraints.

Ax Mikael M{\o}ller H{\o}gsgaard, Chirag Pabbaraju 4/23/2026

Agnostic Language Identification and Generation

Theoretical work relaxing realizability assumptions in language identification and generation tasks, establishing statistical rates without distribution constraints.

Ax Jun Han, Shuo Zhang, Wei Li, Zhi Yang, Yifan Dong, Tu Hu, Jialuo Yuan, Xiaomin Yu, Yumo Zhu, Fangqi Lou, Xin Guo, Zhaowei Liu, Tianyi Jiang, Ruichuan An, Jingping Liu, Biao Wu, Rongze Chen, Kunyi Wang, Yifan Wang, Sen Hu, Xinbing Kong, Liwen Zhang, Ronghao Chen, Huacan Wang 4/23/2026

QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining

QuantaAlpha is an evolutionary LLM-driven agentic framework for financial alpha mining with multi-round search and experience reuse capabilities.

Ax Zezhou Wang, Youjie Li, Zhiqi Lin, Jiacheng Yang, Cong Xie, Guanyu Feng, Zheng Zhong, Ziyue Huang, Hongyu Zhu, Zhi Zhang, Yanghua Peng, Xin Liu 4/23/2026

veScale-FSDP: Flexible and High-Performance FSDP at Scale

Developer tool for flexible and high-performance fully sharded data parallel training, enabling block-wise quantization and structure-aware methods at scale.

Ax Jasmine Brazilek, Miles Tidmarsh 4/23/2026

Alignment midtraining for animals

Study on robustness of value alignment through finetuning with synthetic documents, releasing Animal Harm Benchmark for evaluating model compassion.