Back to AIBriefs
AnalysisAI Models

ViCoStream achieves 100+ FPS for streaming video LLMs

Arxiv CS.CV (computer vision)

ViCoStream enables streaming VideoLLMs to process video at over 100 FPS with stage-wise coordinated inference. The method balances video-ingestion throughput and query-time latency for real-time deployment.

SCR-Guided Difficulty-Aware Optimization for Infrared Small Target Detection6 days agoYunus Sevim, Beh\c{c}et U\u{g}ur T\"oreyin
Multi-Modal Hyper-Graph Fusion for Low-Light Crowd Counting6 days agoHao-Yuan Ma, Li Zhang, Yushi Qiu, Jie Gao, Yan Zhang, Bangjun Wang
VFACamou: View-Fused Adversarial Camouflage for Environment-Adaptive Physical Evasion5 days agoShihui Yan, Hu Liu, Junyu Shi, Zihui Zhu, Ziqi Zhou, Yufei Song, Youming Geng, Minghui Li, Shengshan Hu
FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification5 days agoXuanhao Qi, Tom H. Luan, Yukang Zhang, Jinkai Zheng, Zhou Su, Shuwei Li, Lei Tan
Domain Generalizable Adaptation of 3D Vision-Language Models via Regularized Fine-Tuning6 days agoSneha Paul, Zachary Patterson, Nizar Bouguila
Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMs6 days agoChengwen Liu, Zhe Huang, Jisheng Dang, Hong Peng, Qi Tian, Tat-Seng Chua
Hierarchical Multi-Modal Retrieval for Knowledge-Grounded News Image Captioning6 days agoMinh-Loi Nguyen, Xuan-Vu Le, Long-Bao Nguyen, Hoang-Bach Ngo, Trung-Nghia Le
UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation6 days agoLin Zhang, Sicheng Mo, Zefan Cai, Jinhong Lin, Zihao Lin, Jiuxiang Gu, Krishna Kumar Singh, Yuheng Li, Yin Li
NEST: Narrative Event Structures in Time for Long Video Understanding5 days agoAli Asgarov, Kaushik Narasimhan, Najibul Haque Sarker, Hani Alomari, Chia-Wei Tang, Anushka Sivakumar, Zaber Ibn Abdul Hakim, Shaurya Mallampati, Chris Thomas
Native Active Perception as Reasoning for Omni-Modal Understanding6 days agoZhenghao Xing, Ruiyang Xu, Yuxuan Wang, Jinzheng He, Ziyang Ma, Qize Yang, Yunfei Chu, Jin Xu, Junyang Lin, Chi-Wing Fu, Pheng-Ann Heng
QueryGaussian: Scalable and Training-Free Open-Vocabulary 3D Instance Retrieval5 days agoXiuyuan Zhu, Ke Lu, Zijie Yang, Chao Yue, Jian Xue, Dongming Zhang
Budget-Aware Adaptive Adversarial Patches for Black-Box Object Detection6 days agoPedram MohajerAnsari, Amir Salarpour, David Fernandez, Mert D. Pes\'e
Addressing Detail Bottlenecks in Latent Diffusion for RGB-to-SWIR Image Translation5 days agoKaili Wang, Martin Dimitrievski, Jose Maria Salvador, Ben Stoffelen, David Van Hamme, Lore Goetschalckx
ReA-OVCD: Reliability-Aware Open-Vocabulary Change Detection via Semantic and Spatial Refinement5 days agoHongming Zhu, Huaji Chen, Bowen Du, Sicong Liu, Qin Liu
·
Jun 19, 4:00 AM
ViCoStream achieves 100+ FPS for streaming video LLMs — AIBriefs