Jaehong Yoon

8

Papers

38

Total Citations

1

Affiliations

Affiliations

University of North Carolina at Chapel Hill

Papers (8)

ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models

CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion

Progressive Fourier Neural Representation for Sequential Video Compilation

STELLA: Continual Audio-Video Pre-training with SpatioTemporal Localized Alignment

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation

Multimodal Representation Learning by Alternating Unimodal Adaptation

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens