6 papers
ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs
Xin Wu, Zhixuan Liang, Yue Ma +3
Multimodal Large Language Models (MLLMs) have significantly advanced the landscape of embodied AI, yet transitioning to synchronized bimanual coordination introduces formidable cha…
ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment
Yiyang Chen, Xuanhua He, Xiujun Ma +1
Training-free video object editing aims to achieve precise object-level manipulation, including object insertion, swapping, and deletion. However, it faces significant challenges i…
SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design
Wenxin Tang, Jingyu Xiao, Wenxuan Jiang +8
Manual slide creation is labor-intensive and requires expert prior knowledge. Existing natural language-based LLM generation methods struggle to capture the visual and structural n…
MultiBooth: Towards Generating All Your Concepts in an Image from Text
Chenyang Zhu, Kai Li, Yue Ma +2
This paper introduces MultiBooth, a novel and efficient technique for multi-concept customization in image generation from text. Despite the significant advancements in customized…
ListConRanker: A Contrastive Text Reranker with Listwise Encoding
Junlong Liu, Yue Ma, Ruihui Zhao +3
Reranker models aim to re-rank the passages based on the semantics similarity between the given query and passages, which have recently received more attention due to the wide appl…
InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences
Chenyang Zhu, Kai Li, Yue Ma +5
Recent advances in Customized Concept Swapping (CCS) enable a text-to-image model to swap a concept in the source image with a customized target concept. However, the existing meth…