14 citations · 21 across the 4 of their papers we have counts for
5 papers
Residual Vector-based Reconstruction as Long-Context Recall Regardless of Context Window Size
MyungHoon Ryu, XinYu Piao, Jong-Kook Kim
Large language models (LLMs) process long contexts, including long documents and lengthy conversations, but face token-level memory usage that increases proportionally to input len…
P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems
Myunghoon Ryu, Geunpyo Park, Sungjoon Lee +2
Cloud-local LLM inference can use the reasoning capability of large cloud models, but cloud-bound requests must exclude personally identifiable information (PII). Existing privacy-…
CroMe: Multimodal Fake News Detection using Cross-Modal Tri-Transformer and Metric Learning
Eunjee Choi, Junhyun Ahn, XinYu Piao +1
Multimodal Fake News Detection has received increasing attention recently. Existing methods rely on independently encoded unimodal data and overlook the advantages of capturing int…
Dataloader Parameter Tuner: An Automated Dataloader Parameter Tuner for Deep Learning Models
JooYoung Park, DoangJoo Synn, XinYu Piao +1
Deep learning has recently become one of the most compute/data-intensive methods and is widely used in many research areas and businesses. One of the critical challenges of deep le…
Enabling Large Batch Size Training for DNN Models Beyond the Memory Limit While Maintaining Performance
XinYu Piao, DoangJoo Synn, JooYoung Park +1
Recent deep learning models are difficult to train using a large batch size, because commodity machines may not have enough memory to accommodate both the model and a large data ba…