Eunhyeok Park

Venues

Frequent coauthors

Papers

1. DreamCatcher: Efficient Multi-Concept Customization via Representation Finetuning
   WACV 2026 ·

   Jungwon Lee

   DBLP profile ↗ORCID search ↗
2. Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient
   WACV 2026 ·

   Hyunho Kook

   DBLP profile ↗ORCID search ↗
3. AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models
   EMNLP 2025 ·

   Sangjun Lee

   DBLP profile ↗ORCID search ↗
4. Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse
   VLDB 2025 ·

   Jinwoo Hwang

   DBLP profile ↗ORCID search ↗
5. Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs
   EMNLP 2025 ·

   Sungjae Lee

   DBLP profile ↗ORCID search ↗
6. GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
   NeurIPS 2025 ·

   Yeonjoon Jung

   DBLP profile ↗ORCID search ↗
7. Grouped Speculative Decoding for Autoregressive Image Generation
   ICCV 2025 ·

   Junhyuk So

   DBLP profile ↗ORCID search ↗
8. HOT: Hadamard-based Optimized Training
   CVPR 2025 ·

   Seonggon Kim

   DBLP profile ↗ORCID search ↗
9. Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
   NeurIPS 2025 ·

   Junhyuk So

   DBLP profile ↗ORCID search ↗
10. Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
    ICML 2025 ·

    Juncheol Shin

    DBLP profile ↗ORCID search ↗
11. PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models
    CVPR 2025 ·

    Junhyuk So

    DBLP profile ↗ORCID search ↗
12. PTQ4VM: Post-Training Quantization for Visual Mamba
    WACV 2025 ·

    Younghyun Cho

    DBLP profile ↗ORCID search ↗
13. PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality
    EMNLP 2025 ·

    Byeongho Yu

    DBLP profile ↗ORCID search ↗
14. SEAL: Scaling to Emphasize Attention for Long-Context Retrieval
    ACL 2025 ·

    Changhun Lee

    DBLP profile ↗ORCID search ↗
15. FRDiff : Feature Reuse for Universal Training-Free Acceleration of Diffusion Models
    ECCV 2024 ·

    Junhyuk So

    DBLP profile ↗ORCID search ↗
16. OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models
    AAAI 2024 ·

    Changhun Lee

    DBLP profile ↗ORCID search ↗
17. QEFT: Quantization for Efficient Fine-Tuning of LLMs
    EMNLP 2024 ·

    Changhun Lee

    DBLP profile ↗ORCID search ↗