FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainabilityby…
Reverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linkingby Zhengfei Xu, Sijia Zhao, Yanchao Hao, Xiaolong…
Re-Attentional Controllable Video Diffusion Editingby Yuanzhi Wang, Yong Li, Mengyi Liu, Xiaoya Zhang, Xin Liu,…
DriveGazen: Event-Based Driving Status Recognition using Conventional Cameraby Xiaoyin YangFirst submitted to arxiv on: 16…
Attention with Dependency Parsing Augmentation for Fine-Grained Attributionby Qiang Ding, Lvzhou Luo, Yixuan Cao, Ping…
Embodied CoT Distillation From LLM To Off-the-shelf Agentsby Wonje Choi, Woo Kyung Kim, Minjong Yoo,…
EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splattingby…
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMsby Yuchen Fu, Zifeng…
Automated Image Captioning with CNNs and Transformersby Joshua Adrian Cahyono, Jeremy Nathan JusufFirst submitted to…
Enhance Vision-Language Alignment with Noiseby Sida Huang, Hongyuan Zhang, Xuelong LiFirst submitted to arxiv on:…