6 citations · 6 across the 13 of their papers we have counts for
14 papers
StyleComposer: Training-Free Multi-Reference Style Composition
Sanghyeok Lee, Jihye Kang, Namhyuk Ahn
The style of a painting is not monolithic: color, texture, and structure may come from different sources. Existing reference-guided methods transfer them as one style signal, leavi…
Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations
Beomjun Kim, Seong Hyeon Park, Seunghoon Sim +3
Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real ro…
DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning
Joonmyung Choi, Sanghyeok Lee, Jongha Kim +4
Recent advances in vision-language models have demonstrated remarkable performance across diverse multi-modal tasks, including document question answering that leverages structured…
MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models
Dohwan Ko, Jinyoung Park, Seoung Choi +3
Mixture-of-Experts (MoE) has emerged as an effective approach to reduce the computational overhead of Transformer architectures by sparsely activating a subset of parameters for ea…
HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG
Jinyoung Park, Sanghyeok Lee, Omar Zia Khan +2
Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling lar…
TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing
Jongha Kim, Minseong Bae, Sanghyeok Lee +2
Table images present unique challenges for effective and efficient understanding due to the need for question-specific focus and the presence of redundant background regions. Exist…
Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding
Kyungryul Back, Seongbeom Park, Milim Kim +6
Large Vision-Language Models (LVLMs) have recently shown promising results on various multimodal tasks, even achieving human-comparable performance in certain cases. Nevertheless,…
Compositional Image Synthesis with Inference-Time Scaling
Minsuk Ji, Sanghyeok Lee, Namhyuk Ahn
Despite their impressive realism, modern text-to-image models still struggle with compositionality, often failing to render accurate object counts, attributes, and spatial relation…
Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization
Jihwan Park, Taehoon Song, Sanghyeok Lee +2
Vision-Language Models (VLMs) have been widely used in various visual recognition tasks due to their remarkable generalization capabilities. As these models grow in size and comple…
Representation Shift: Unifying Token Compression with FlashAttention
Joonmyung Choi, Sanghyeok Lee, Byungoh Ko +3
Transformers have demonstrated remarkable success across vision, language, and video. Yet, increasing task complexity has led to larger models and more tokens, raising the quadrati…
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim
For the deployment of neural networks in resource-constrained environments, prior works have built lightweight architectures with convolution and attention for capturing local and…
Robust Multimodal 3D Object Detection via Modality-Agnostic Decoding and Proximity-based Modality Ensemble
Juhan Cha, Minseok Joo, Jihwan Park +3
Recent advancements in 3D object detection have benefited from multi-modal information from the multi-view cameras and LiDAR sensors. However, the inherent disparities between the…
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers
Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim
Vision Transformer (ViT) has emerged as a prominent backbone for computer vision. For more efficient ViTs, recent works lessen the quadratic cost of the self-attention layer by pru…
vid-TLDR: Training Free Token merging for Light-weight Video Transformer
Joonmyung Choi, Sanghyeok Lee, Jaewon Chu +2
Video Transformers have become the prevalent solution for various video downstream tasks with superior expressive power and flexibility. However, these video transformers suffer fr…