3 citations · 3 across the 7 of their papers we have counts for
6 papers · 1 filter
Cache Locally, Recompute Selectively for Streaming Video Understanding
Junhyeok Lee, Sangyoon Lee, Jaeho Lee
Streaming video understanding (SVU) requires video-LLMs to process incoming video continuously while answering user queries with low latency. Recent methods reduce query-time cost…
ixi-sLM: On-Device sLM for AI Call Agent Service
Han-Sang Lee, Kyuho Lee, Juneyoung Park +10
Running an AI call agent on-device makes it private, network-independent, and free of per-query cloud cost, but shipping one as a real-world service imposes constraints a cloud dep…
FoRA: Fisher-orthogonal Rank Adaptation for Parameter-Efficient Fine-Tuning
Juneyoung Park, Seongbae Lee, Han-Sang Lee +6
Parameter-efficient fine-tuning(PEFT) has largely focused on LoRA and its accuracy-oriented variants, leaving the original goal of reducing trainable parameters has receivedcompara…
Decoder-Free Distillation for Quantized Image Restoration
S. M. A. Sharif, Abdur Rehman, Seongwan Kim +1
Quantization-Aware Training (QAT), combined with Knowledge Distillation (KD), holds immense promise for compressing models for edge deployment. However, joint optimization for prec…
LCSB: Layer-Cyclic Selective Backpropagation for Memory-Efficient On-Device LLM Fine-Tuning
Juneyoung Park, Eunbeen Yoon, Seongwan Kim. Jaeho Lee
Memory-efficient backpropagation (MeBP) has enabled first-order fine-tuning of large language models (LLMs) on mobile devices with less than 1GB memory. However, MeBP requires back…
Memory-Efficient Structured Backpropagation for On-Device LLM Fine-Tuning
Juneyoung Park, Yuri Hong, Seongwan Kim +1
On-device fine-tuning enables privacy-preserving personalization of large language models, but mobile devices impose severe memory constraints, typically 6--12GB shared across all…