Past Graduate Students #

Seungwoo Son #

M.S. @ POSTECH EE (22.03–24.08): “The role of masking for efficient supervised knowledge distillation of vision transformers”
Expertise. Model compression of large transformers, using quantization and distillation
Next step. Samsung Research
linkedin, mail

#

Hagyeong Lee #

M.S. @ POSTECH EE (22.09–24.08): “Neural image compression with text-guided encoding for both pixel-level and perceptual fidelity”
Expertise. Multimodal data compression
Next step. (TBD)
webpage, mail, twitter

#

Jiwoon Lee #

M.S. @ POSTECH EE (22.03–24.02): “Semi-ensemble: A simple approach to over-parameterized model interpolation”
Expertise Model Merging, federated Learning and knowledge distillation
Next step. FASOO
mail

#

Junwon Seo #

M.S. @ POSTECH EE (22.03–24.02): “In search of a data transformation that accelerates neural field training”
Expertise. Fast training of neural fields
Next step. LivsMed (전문연구요원)
mail

#

Past Interns #

Seoyun Jeong (Summer ‘24)
Collaborative Decoding with Compressed Models

Yewon Hwang (Summer ‘24)
Quantizing Diffusion Model

Sangbeom Ha (Summer ‘23–Spring ‘24)
Large-Scale Model Quantization

Inkwan Hwang (Fall ‘23–Summer ‘24; now at 🫡)
Large-Scale Model Pruning
webpage

Taesun Yeom (Winter ‘23–Spring ‘24; Now at EffL)
Training and Inference Efficiency for Neural Fields

Minhee Lee (Winter ‘23)
Speculative Decoding

Jegwang Ryu (Summer ‘23, Spring ‘24; Now at EffL)
Accelerated Training by Masking

Seunghyun Kim (Spring ‘24; Now at EffL)
Efficient RAG LLM

Wonjun Cho (Spring ‘24)
Model Compression

Subeom Heo (Spring–Summer ‘24)
Accelerating Video Diffusion Models

Jeonghyun Choi (Winter ‘23)
Properties of Data Augmentation

Minjae Park (Winter ‘23; now at EffL)
Faster State-Space Models

Minyoung Kang (Fall–Winter ‘23)
Neural Cellular Automata

Yousung Roh (Fall ‘23–Winter ‘23)
Byte-Processing Neural Networks

Jiyun Bae (Summer–Fall ‘23; now at EffL)
Visual Prompt Tuning

Sangyoon Lee (Summaer–Fall ‘23; now at EffL)
Fast Neural Field Generation

Dohyun Kim (Summer ‘23; now at 🫡)
Zeroth Order Optimization

Juyun Wee (Spring ‘23 → EffL)
Time-Series Modeling with Transformers

Soochang Song (Winter ‘22 – Spring ‘23; now exchange student at 🇫🇷)
Model Interpolation with SIRENs

Jeonghun Cho (Winter ‘22)
Pruning Models under Challenging Scenarios

Seyeon Park (Winter ‘21 → Yonsei)
Efficient Attentions for Language Models

Hagyeong Lee (Winter ‘21 → EffL)
Data Compression with Implicit Neural Representations