---
markdown_generated_at: "2026-10-14"
title: "QIF 2025 South Korea"
url: "https://www.qualcomm.com/research/university-relations/innovation-fellowship/2025-south-korea"
description: "Rules and details for the Qualcomm Innovation Fellowship for South Korea in 2025."
canonicalUrl: "https://www.qualcomm.com/research/university-relations/innovation-fellowship/2025-south-korea"
---

# QIF 2025 South Korea

## 2025 South Korea Program Details

Qualcomm Technologies, Inc. proudly announces the launch of Qualcomm Innovation Fellowship 2025 Korea program.
The program is a qualified paper scholarship selection program and open to Master or PhD students at specific universities in South Korea.

Winner

Finalist Selections

Program Information

## 2025 South Korea Winners

![](https://s7d1.scene7.com/is/image/dmqualcommprod/qif-2025-winners-banner?$QC_Responsive$&fmt=png-alpha)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/qif-2025-winners?$QC_Responsive$&fmt=png-alpha)

| Application number | Paper title | Student(s) | University |
|---|---|---|---|
| QIFK2025_5 | RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models | Yeongtak Oh | Seoul National University |
| QIFK2025_7 | HOT: Hadamard-based Optimized Training | Seonggon-Kim | POSTECH |
| QIFK2025_10 | By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting | Hyungjun Yoon | KAIST |
| QIFK2025_27 | Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs | Jeongseok Hyun | Yonsei University |
| QIFK2025_34 | Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation | Phillip Yuseung Lee | KAIST |
| QIFK2025_35 | Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think | Sihyun Yu | KAIST |
| QIFK2025_59 | DoMIX: An Efficient Framework for Exploiting Domain Knowledge in Fine-Tuning | Dohoon-Kim | Seoul National University |
| QIFK2025_72 | Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior | Hyoseok Lee | KAIST |
| QIFK2025_74 | Distilling Dataset into Neural Field | Donghyeok Shin | KAIST |
| QIFK2025_78 | Flat Reward In Policy Parameter Space Implies Robust Reinforcement Learning | Hyunkyu-Lee | UNIST |
| QIFK2025_89 | Temporal Alignment-Free Video Matching for Few-shot Action Recognition | SuBeen Lee | Sungkyunkwan University |
| QIFK2025_107 | FACIL: Flexible DRAM Address Mapping for SoC-PIM Cooperative On-device LLM Inference | Seong Hoon Seo | Seoul National University |
| QIFK2025_116 | L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models | Hyesung Jeon | Seoul National University |
| QIFK2025_119 | SAFE: Finding Sparse and Flat Minima to Improve Pruning | Dongyeop Lee | POSTECH |
| QIFK2025_121 | Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration | Junseong-Kim | POSTECH |

## Fellowship Winners and Finalists

The Qualcomm Innovation Fellowship began in 2009, and has continued to grow with the addition of more universities, more candidates, and expansion to our research centers internationally. Take a look at a list of all our fellowship winners and finalists from years past:

[Winners](https://www.qualcomm.com/research/university-relations/innovation-fellowship/winners)

[Finalists](https://www.qualcomm.com/research/university-relations/innovation-fellowship/finalists)