38 papers
From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion
Cheng Chen, Yuyu Guo, Pengpeng Zeng +4
Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection that links only the output of the vision encoder to the input of the…
TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity
Xiao Cai, Pengpeng Zeng, Ji Zhang +3
Precise spatial fidelity in Image-to-3D multi-instance generation is critical for downstream real-world applications. Recent work attempts to address this by fine-tuning pre-traine…
Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning
Cheng Chen, Pengpeng Zeng, Yuyu Guo +3
Low-Rank Adaptation (LoRA) has emerged as a promising paradigm for Continual Learning. It independently updates its low-rank factors ( and ), creating a composite update to t…
Reversible Inversion for Training-Free Exemplar-guided Image Editing
Yuke Li, Lianli Gao, Ji Zhang +5
Exemplar-guided Image Editing (EIE) aims to modify a source image according to a visual reference. Existing approaches often require large-scale pre-training to learn relationships…
Policy Contrastive Decoding for Robotic Foundation Models
Shihan Wu, Xu Luo, Ji Zhang +4
Robotic foundation models, or generalist robot policies, hold immense potential to enable flexible, general-purpose and dexterous robotic systems. Despite their advancements, our e…
SINDI: An Efficient Index for Sparse Vector Approximate Maximum Inner Product Search
Ruoxuan Li, Xiaoyao Zhong, Jiabao Jin +7
Sparse vector Maximum Inner Product Search (MIPS) is crucial in multi-path retrieval for Retrieval-Augmented Generation (RAG). Recent inverted index-based and graph-based algorithm…