Picture for Yohei Nakata

Yohei Nakata

DFM: Interpolant-free Dual Flow Matching

Add code
Oct 11, 2024
Viaarxiv icon

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Add code
Oct 06, 2024
Figure 1 for SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Figure 2 for SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Figure 3 for SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Figure 4 for SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Viaarxiv icon

Fisher-aware Quantization for DETR Detectors with Critical-category Objectives

Add code
Jul 03, 2024
Figure 1 for Fisher-aware Quantization for DETR Detectors with Critical-category Objectives
Figure 2 for Fisher-aware Quantization for DETR Detectors with Critical-category Objectives
Figure 3 for Fisher-aware Quantization for DETR Detectors with Critical-category Objectives
Figure 4 for Fisher-aware Quantization for DETR Detectors with Critical-category Objectives
Viaarxiv icon

ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding

Add code
Jun 02, 2024
Viaarxiv icon

VeCAF: VLM-empowered Collaborative Active Finetuning with Training Objective Awareness

Add code
Jan 15, 2024
Viaarxiv icon

Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation

Add code
Dec 27, 2023
Viaarxiv icon

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting

Add code
Dec 14, 2023
Viaarxiv icon

Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flow

Add code
May 16, 2023
Viaarxiv icon

Cross-Domain Object Detection with Mean-Teacher Transformer

Add code
May 03, 2022
Figure 1 for Cross-Domain Object Detection with Mean-Teacher Transformer
Figure 2 for Cross-Domain Object Detection with Mean-Teacher Transformer
Figure 3 for Cross-Domain Object Detection with Mean-Teacher Transformer
Figure 4 for Cross-Domain Object Detection with Mean-Teacher Transformer
Viaarxiv icon

RandomNet: Towards Fully Automatic Neural Architecture Design for Multimodal Learning

Add code
Mar 02, 2020
Figure 1 for RandomNet: Towards Fully Automatic Neural Architecture Design for Multimodal Learning
Figure 2 for RandomNet: Towards Fully Automatic Neural Architecture Design for Multimodal Learning
Figure 3 for RandomNet: Towards Fully Automatic Neural Architecture Design for Multimodal Learning
Figure 4 for RandomNet: Towards Fully Automatic Neural Architecture Design for Multimodal Learning
Viaarxiv icon