Picture for Sungnyun Kim

Sungnyun Kim

MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation

Add code
Mar 14, 2025
Viaarxiv icon

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Add code
Mar 10, 2025
Viaarxiv icon

DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models

Add code
Oct 04, 2024
Figure 1 for DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models
Figure 2 for DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models
Figure 3 for DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models
Figure 4 for DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models
Viaarxiv icon

Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning

Add code
Aug 23, 2024
Viaarxiv icon

Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition

Add code
Jul 04, 2024
Viaarxiv icon

FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning

Add code
Jun 04, 2024
Viaarxiv icon

DistiLLM: Towards Streamlined Distillation for Large Language Models

Add code
Feb 06, 2024
Figure 1 for DistiLLM: Towards Streamlined Distillation for Large Language Models
Figure 2 for DistiLLM: Towards Streamlined Distillation for Large Language Models
Figure 3 for DistiLLM: Towards Streamlined Distillation for Large Language Models
Figure 4 for DistiLLM: Towards Streamlined Distillation for Large Language Models
Viaarxiv icon

STaR: Distilling Speech Temporal Relation for Lightweight Speech Self-Supervised Learning Models

Add code
Dec 14, 2023
Viaarxiv icon

DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion Models

Add code
May 24, 2023
Viaarxiv icon

Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification

Add code
May 23, 2023
Figure 1 for Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification
Figure 2 for Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification
Figure 3 for Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification
Figure 4 for Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification
Viaarxiv icon