10 papers
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
Congmin Zheng, Jiachen Zhu, Jianghao Lin +6
Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…
daVinci-LLM:Towards the Science of Pretraining
Yiwei Qin, Yixiu Liu, Tiantian Mi +12
The foundational pretraining phase determines a model's capability ceiling, as post-training struggles to overcome capability foundations established during pretraining, yet it rem…
Data Darwinism Part II: DataEvolve -- AI can Autonomously Evolve Pretraining Data Curation
Tiantian Mi, Dongming Shan, Zhen Huang +6
Data Darwinism (Part I) established a ten-level hierarchy for data processing, showing that stronger processing can unlock greater data value. However, that work relied on manually…
Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training
Yiwei Qin, Zhen Huang, Tiantian Mi +5
Data quality determines foundation model performance, yet systematic processing frameworks are lacking. We introduce Data Darwinism, a ten-level taxonomy (L0-L9) that conceptualize…
Interaction as Intelligence: Deep Research With Human-AI Partnership
Lyumanshan Ye, Xiaojie Cai, Xinkai Wang +23
This paper introduces "Interaction as Intelligence" research series, presenting a reconceptualization of human-AI relationships in deep research tasks. Traditional approaches treat…
Generative AI Act II: Test Time Scaling Drives Cognition Engineering
Shijie Xia, Yiwei Qin, Xuefeng Li +11
The first generation of Large Language Models - what might be called "Act I" of generative AI (2020-2023) - achieved remarkable success through massive parameter and data scaling,…