41 citations · 82 across the 18 of their papers we have counts for
19 papers
Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding
Jiwan Kim, Kibum Kim, Wonjoong Kim +2
Recently, visual token pruning has been studied to handle the vast number of visual tokens in Multimodal Large Language Models. However, we observe that while existing pruning meth…
Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs
Kibum Kim, Jiwan Kim, Kyle Min +4
Video Large Language Models (Video LLMs) incur high inference latency due to a large number of visual tokens provided to LLMs. To address this, training-free visual token pruning h…
CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs
Jiwan Kim, Kibum Kim, Sangwoo Seo +1
Recently, efficient Multimodal Large Language Models (MLLMs) have gained significant attention as a solution to their high computational complexity, making them more practical for…
IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectra
Heewoong Noh, Namkyeong Lee, Gyoung S. Na +2
Spectral analysis provides crucial clues for the elucidation of unknown materials. Among various techniques, infrared spectroscopy (IR) plays an important role in laboratory settin…
Disentangling and Generating Modalities for Recommendation in Missing Modality Scenarios
Jiwan Kim, Hongseok Kang, Sein Kim +2
Multi-modal recommender systems (MRSs) have achieved notable success in improving personalization by leveraging diverse modalities such as images, text, and audio. However, two key…
Token-Efficient Item Representation via Images for LLM Recommender Systems
Kibum Kim, Sein Kim, Hongseok Kang +7
Large Language Models (LLMs) have recently emerged as a powerful backbone for recommender systems. Existing LLM-based recommender systems take two different approaches for represen…
Weakly Supervised Video Scene Graph Generation via Natural Language Supervision
Kibum Kim, Kanghoon Yoon, Yeonjun In +4
Existing Video Scene Graph Generation (VidSGG) studies are trained in a fully supervised manner, which requires all frames in a video to be annotated, thereby incurring high annota…
Training Robust Graph Neural Networks by Modeling Noise Dependencies
Yeonjun In, Kanghoon Yoon, Sukwon Yun +3
In real-world applications, node features in graphs often contain noise from various sources, leading to significant performance degradation in GNNs. Although several methods have…
Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models
Yeonjun In, Wonjoong Kim, Kanghoon Yoon +5
As the use of large language model (LLM) agents continues to grow, their safety vulnerabilities have become increasingly evident. Extensive benchmarks evaluate various aspects of L…
Lost in Sequence: Do Large Language Models Understand Sequential Recommendation?
Sein Kim, Hongseok Kang, Kibum Kim +6
Large Language Models (LLMs) have recently emerged as promising tools for recommendation thanks to their advanced textual understanding ability and context-awareness. Despite the c…
RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning
Kanghoon Yoon, Kibum Kim, Jaehyung Jeon +3
Scene Graph Generation (SGG) research has suffered from two fundamental challenges: the long-tailed predicate distribution and semantic ambiguity between predicates. These challeng…
Debiased Graph Poisoning Attack via Contrastive Surrogate Objective
Kanghoon Yoon, Yeonjun In, Namkyeong Lee +2
Graph neural networks (GNN) are vulnerable to adversarial attacks, which aim to degrade the performance of GNNs through imperceptible changes on the graph. However, we find that in…
Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation
Jaehyeong Jeon, Kibum Kim, Kanghoon Yoon +1
The scene graph generation (SGG) task involves detecting objects within an image and predicting predicates that represent the relationships between the objects. However, in SGG ben…
Self-Guided Robust Graph Structure Refinement
Yeonjun In, Kanghoon Yoon, Kibum Kim +2
Recent studies have revealed that GNNs are vulnerable to adversarial attacks. To defend against such attacks, robust graph structure refinement (GSR) methods aim at minimizing the…
Adaptive Self-training Framework for Fine-grained Scene Graph Generation
Kibum Kim, Kanghoon Yoon, Yeonjun In +3
Scene graph generation (SGG) models have suffered from inherent problems regarding the benchmark datasets such as the long-tailed predicate distribution and missing annotation prob…
LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation
Kibum Kim, Kanghoon Yoon, Jaehyeong Jeon +4
Weakly-Supervised Scene Graph Generation (WSSGG) research has recently emerged as an alternative to the fully-supervised approach that heavily relies on costly annotations. In this…
MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation
Kibum Kim, Dongmin Hyun, Sukwon Yun +1
The long-tailed problem is a long-standing challenge in Sequential Recommender Systems (SRS) in which the problem exists in terms of both users and items. While many existing studi…
Unbiased Heterogeneous Scene Graph Generation with Relation-aware Message Passing Neural Network
Kanghoon Yoon, Kibum Kim, Jinyoung Moon +1
Recent scene graph generation (SGG) frameworks have focused on learning complex relationships among multiple objects in an image. Thanks to the nature of the message passing neural…
LTE4G: Long-Tail Experts for Graph Neural Networks
Sukwon Yun, Kibum Kim, Kanghoon Yoon +1
Existing Graph Neural Networks (GNNs) usually assume a balanced situation where both the class distribution and the node degree distribution are balanced. However, in real-world si…