10 papers
Saliency-Aware Model Merging
Jungin Park, Jiyoung Lee, Kwanghoon Sohn
Model merging aims to consolidate multiple task-specific models fine-tuned on different datasets into a unified architecture that performs cross-domain proficiency. Current data-fr…
V-LynX: Token Interface Alignment for Video+X LLMs
Jungin Park, Jiyoung Lee, Kwanghoon Sohn
This study introduces an intriguing phenomenon in Video LLMs: rather than merely translating frames into textual embeddings, Video LLMs establish a continuous manifold, token inter…
Learning What To Hear: Boosting Sound-Source Association For Robust Audiovisual Instance Segmentation
Jinbae Seo, Hyeongjun Kwon, Kwonyoung Kim +2
Audiovisual instance segmentation (AVIS) requires accurately localizing and tracking sounding objects throughout video sequences. Existing methods suffer from visual bias stemming…
Descriptive Image-Text Matching with Graded Contextual Similarity
Jinhyun Jang, Jiyoung Lee, Kwanghoon Sohn
Image-text matching aims to build correspondences between visual and textual data by learning their pairwise similarities. Most existing approaches have adopted sparse binary super…
Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization
Jungin Park, Jiyoung Lee, Kwanghoon Sohn
Video summarization aims to select keyframes that are visually diverse and can represent the whole story of a given video. Previous approaches have focused on global interlinkabili…
Faster Parameter-Efficient Tuning with Token Redundancy Reduction
Kwonyoung Kim, Jungin Park, Jin Kim +2
Parameter-efficient tuning (PET) aims to transfer pre-trained foundation models to downstream tasks by learning a small number of parameters. Compared to traditional fine-tuning, w…