Papers

Papers by categories in reversed chronological order.

2025

  1. arxiv
    rlr.png
    Real-Time Reasoning Agents in Evolving Environments
    Yule Wen*, Yixin Ye*, Yanzhe Zhang, Diyi Yang, and Hao Zhu
    2025
    arXiv Website GitHub stars
  2. arxiv
    generativeaiactii.png
    Generative AI Act II: Test Time Scaling Drives Cognition Engineering
    Shijie Xia, Yiwei Qin, Xuefeng Li, Yan Ma, Run-Ze Fan, Steffi Chern, Haoyang Zou, Fan Zhou, Xiangkun Hu, Jiahe Jin, Yanheng He, Yixin Ye, Yixiu Liu, and Pengfei Liu
    2025
    arXiv
  3. COLM
    limo.png
    LIMO: Less is More for Reasoning
    Yixin Ye*, Zhen Huang*, Yang Xiao, Ethan Chern, Shijie Xia, and Pengfei Liu
    In Conference on Language Models – COLM , 2025
    arXiv GitHub stars

2024

  1. arxiv
    o1-journey.png
    O1 Replication Journey: A Strategic Progress Report – Part 1
    Yiwei Qin*, Xuefeng Li*, Haoyang Zou*, Yixiu Liu*, Shijie Xia*, Zhen Huang, Yixin Ye, Weizhe Yuan, Hector Liu, Yuanzhi Li, and Pengfei Liu
    2024
    arXiv GitHub stars
  2. NeuralIPS
    olympicarena.png
    OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
    Zhen Huang, Zengzhi Wang, Shijie Xia, Xuefeng Li, Haoyang Zou, Ruijie Xu, Run-Ze Fan, Lyumanshan Ye, Ethan Chern, Yixin Ye, Yikai Zhang, Yuqing Yang, Ting Wu, Binjie Wang, Shichao Sun, Yang Xiao, Yiyuan Li, Fan Zhou, Steffi Chern, Yiwei Qin, Yan Ma, Jiadi Su, Yixiu Liu, Yuxiang Zheng, Shaoting Zhang, Dahua Lin, Yu Qiao, and Pengfei Liu
    In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2024
    arXiv Website GitHub stars
  3. ECCV
    dissonance.png
    Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions
    Jin Gao, Lei Gan*, Yuankai Li*, Yixin Ye, and Dequan Wang
    In Computer Vision – ECCV, 2024
    arXiv
  4. ECCV
    lost-in-translation.png
    Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion Models
    Juntu Zhao, Junyu Deng*, Yixin Ye*, Chongxuan Li, Zhijie Deng, and Dequan Wang
    In Computer Vision – ECCV, 2024
    arXiv