Lattice AI Research

Research focus

Inference & Quantization (2)Training Efficiency & Optimization (2)Natural Language Processing (1)Recommendation & Information Retrieval (1)

Frequent co-authors

Hyeonseok Moon (2)Heuiseok Lim (2)Heuiseok Lim (2)Jeongho Yoon (1)

Papers (2)

Apr 8, 2026

1w ago·also Samsung Mobile eXperience Business

Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation

LLMs can now perform inference without ever seeing raw text, opening the door to privacy-preserving applications without sacrificing performance.

Jeongho Yoon, Chanhee Park, Yongchan Chun +5

Inference & Quantization Natural Language Processing Training Efficiency & Optimization

Apr 6, 2026

1w ago·also Samsung Mobile eXperience Business

Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval

Forget just mining hard negatives: the secret to better knowledge distillation for retrieval lies in matching the *entire* score distribution of your teacher model.

Youngjoon Jang, Youngjoon Jang, Seongtae Hong +4

Inference & Quantization Recommendation & Information Retrieval Training Efficiency & Optimization

Search

Hyeonseok Moon

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)