publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. Data Pruning
    prior_update.png
    Prior-based Noisy Text Data Filtering: Fast and Strong Alternative For Perplexity
    Yeongbin Seo, Gayoung Kim, Jaehyung Kim, and Jinyoung Yeo
    In ICLR, 2026
    arXiv Code
  2. Diffusion LM
    Renoise Consistency: Unlocking Efficient Self-Correction for Diffusion Large Language Models
    Jihoon Lee, Yeongbin Seo, and Jaehyung Kim
    In NeurIPS, 2026
    arXiv
  3. Hallucination
    aqe.png
    Quantifying Genuine Awareness in Hallucination Prediction: Disentangling Question-Side Shortcuts
    Yeongbin Seo, Dongha Lee, and Jinyoung Yeo
    In ICLR Workshop (Agentic AI in the Wild, From Hallucinations to Reliable Autonomy), 2026
    arXiv Code

2025

  1. Diffusion LM
    diffusion_4.png
    Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
    Yeongbin Seo, Dongha Lee, Jaehyung Kim, and Jinyoung Yeo
    In NeurIPS spotlight (3.19%), 2025
    arXiv Code

2024

  1. Continual Learning
    TAALM.png
    Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning
    Yeongbin Seo, Dongha Lee, and Jinyoung Yeo
    In NeurIPS, 2024
    arXiv Code