Picture for Sangmin Bae

Sangmin Bae

Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA

Add code
Oct 28, 2024
Viaarxiv icon

Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models

Add code
Oct 14, 2024
Viaarxiv icon

Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL

Add code
Jul 20, 2024
Viaarxiv icon

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

Add code
Jul 04, 2024
Viaarxiv icon

Block Transformer: Global-to-Local Language Modeling for Fast Inference

Add code
Jun 04, 2024
Figure 1 for Block Transformer: Global-to-Local Language Modeling for Fast Inference
Figure 2 for Block Transformer: Global-to-Local Language Modeling for Fast Inference
Figure 3 for Block Transformer: Global-to-Local Language Modeling for Fast Inference
Figure 4 for Block Transformer: Global-to-Local Language Modeling for Fast Inference
Viaarxiv icon

Why In-Context Learning Transformers are Tabular Data Classifiers

Add code
May 22, 2024
Viaarxiv icon

RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification

Add code
May 05, 2024
Figure 1 for RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification
Figure 2 for RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification
Figure 3 for RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification
Figure 4 for RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification
Viaarxiv icon

Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification

Add code
Dec 15, 2023
Figure 1 for Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification
Figure 2 for Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification
Figure 3 for Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification
Figure 4 for Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification
Viaarxiv icon

Fine-Tuning the Retrieval Mechanism for Tabular Deep Learning

Add code
Nov 13, 2023
Viaarxiv icon

Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance

Add code
Nov 11, 2023
Figure 1 for Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance
Figure 2 for Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance
Figure 3 for Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance
Figure 4 for Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance
Viaarxiv icon