4 papers
Jag: Direct Box Prediction for Efficient Visual Grounding
Xiuyuan Zhu, Ke Lu, Hao Wu +3
Visual grounding combines image--language understanding with geometric prediction, yet autoregressive multimodal models often express a box as a coordinate sequence. Sequential dec…
Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding
Xiuyuan Zhu, Ke Lu, Kun Dong +6
Generative Vision-Language Models (VLMs) express bounding boxes as coordinate sequences, whose token identities often leave axis and place value implicit. We study how explicitly e…
IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models
Xiuyuan Zhu, Ke Lu, Hao Wu +4
Visual grounding with multimodal large language models is commonly formulated as autoregressive coordinate generation, where a model outputs bounding-box coordinates as text given…
QueryGaussian: Scalable and Training-Free Open-Vocabulary 3D Instance Retrieval
Xiuyuan Zhu, Ke Lu, Zijie Yang +3
Efficiently retrieving specific 3D instances from large-scale scenes via natural language prompts remains a formidable challenge in multimedia analysis. Existing approaches predomi…