11 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…
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…
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…
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…