3 citations · 10 across the 12 of their papers we have counts for
13 papers
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…
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…
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,…
DIVE: Diversified Iterative Self-Improvement
Yiwei Qin, Yixiu Liu, Pengfei Liu
Recent advances in large language models (LLMs) have demonstrated the effectiveness of Iterative Self-Improvement (ISI) techniques. However, continuous training on self-generated d…
O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?
Zhen Huang, Haoyang Zou, Xuefeng Li +7
This paper presents a critical examination of current approaches to replicating OpenAI's O1 model capabilities, with particular focus on the widespread but often undisclosed use of…
O1 Replication Journey: A Strategic Progress Report -- Part 1
Yiwei Qin, Xuefeng Li, Haoyang Zou +8
This paper introduces a pioneering approach to artificial intelligence research, embodied in our O1 Replication Journey. In response to the announcement of OpenAI's groundbreaking…
OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
Zhen Huang, Zengzhi Wang, Shijie Xia +25
The evolution of Artificial Intelligence (AI) has been significantly accelerated by advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), gradually showc…
InFoBench: Evaluating Instruction Following Ability in Large Language Models
Yiwei Qin, Kaiqiang Song, Yebowen Hu +7
This paper introduces the Decomposed Requirements Following Ratio (DRFR), a new metric for evaluating Large Language Models' (LLMs) ability to follow instructions. Addressing a gap…
Searching for Effective Multilingual Fine-Tuning Methods: A Case Study in Summarization
Yiwei Qin, Graham Neubig, Pengfei Liu
Recently, a large number of tuning strategies have been proposed to adapt pre-trained language models to downstream tasks. In this paper, we perform an extensive empirical evaluati…
T5Score: Discriminative Fine-tuning of Generative Evaluation Metrics
Yiwei Qin, Weizhe Yuan, Graham Neubig +1
Modern embedding-based metrics for evaluation of generated text generally fall into one of two paradigms: discriminative metrics that are trained to directly predict which outputs…