12 papers
Context Blindness in DPO: Mitigating Object Hallucination in MLLMs via Context-Calibrated Preference Optimization
Byungoh Ko, Jinyoung Park, Jongha Kim +3
Multimodal large language models (MLLMs) have made rapid progress, yet they still exhibit object hallucination, generating plausible but incorrect descriptions that are inconsisten…
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…
RegFormer: Transferable Relational Grounding for Efficient Weakly-Supervised Human-Object Interaction Detection
Jihwan Park, Chanhyeong Yang, Jinyoung Park +2
Weakly-supervised Human-Object Interaction (HOI) detection is essential for scalable scene understanding, as it learns interactions from only image-level annotations. Due to the la…
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…
DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO
Jinyoung Park, Jeehye Na, Jinyoung Kim +1
Recent works have demonstrated the effectiveness of reinforcement learning (RL)-based post-training for enhancing the reasoning capabilities of large language models (LLMs). In par…
Improving Large Molecular Language Model via Relation-aware Multimodal Collaboration
Jinyoung Park, Minseong Bae, Jeehye Na +1
Large language models (LLMs) have demonstrated their instruction-following capabilities and achieved powerful performance on various tasks. Inspired by their success, recent works…