SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual GroundingOctober 1, 2025·Jiawen Lin,Shiran Bian,Yihang Zhu,Wenbin Tan,Yachao ZhangYuan Xie,Yanyun Qu· 0 min read URL Cite DOITypeConference paperPublicationProceedings of the 33rd ACM International Conference on MultimediapublicationsLast updated on October 1, 2025 AuthorsYuan XieChair ProfessorFang Professor of Engineering | Chair Professor | IEEE/ACM/AAAS Fellow ← How Do Errors Impact NN Accuracy on Non-Ideal Analog PIM? Fast Evaluation via an Error-Injected Robustness Metric October 1, 2025Matrix: Multi-Cipher Structures Dataflow for Parallel and Pipelined TFHE Accelerator September 19, 2025 →
,·
0 min read