cs.CVNov 17, 2026

Cross-Modal StateKV Injection for Communication in Multi-LLM Systems across Temporal Segments

Authors: Xiaoqian Zhang, Zhihao Zhang

Organizations: Department of Ultrasound & Faculty of Medical Imaging Technology, Ruijin Hospital, College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China · School of Mathematics, Shanghai University of Finance and Economics, Shanghai, China · School of Computing and Artificial Intelligence, Shanghai University of Finance and Economics, Shanghai, China

Abstract

Video understanding with multiple multimodal language models requires a communication interface that can transfer complementary visual observations. Text-based communication is interpretable, but introduces an intermediate generation stage and can omit information relevant to subsequent reasoning. We study Cross-Modal StateKV Injection, a provider--carrier framework that communicates through key--value (KV) states at visual-token positions. Provider models observe complementary video frames; their visual KV states are aligned and projected into the carrier representation space and integrated through gated residual updates. Injection preserves the carrier KV-cache sequence length, while retaining the additional computation required by the providers and the communication module. The reported experiments on MLVU and Video-MME compare carrier-only inference, text-based communication, and StateKV with two provider architectures. Results show modest, task-dependent accuracy gains and lower reported latency than the evaluated text-communication baseline, with some categories remaining unchanged or decreasing. Increasing provider-side frame coverage offers additional gains on selected tasks without extending the carrier cache. These findings motivate further study of visual KV communication under explicitly controlled observation and computation budgets.

Figures & tables

Explore similar work

CardsList
  1. Linear Scaling Video VLMs for Long Video Understanding

    May 29, 2026Cristobal Eyzaguirre, Jiajun Wu, Juan Carlos NieblesStreaming Video UnderstandingEfficient VLM Inference

  2. Benchmarking Visual State Tracking in Multimodal Video Understanding

    Jun 2, 2026Sihyun Yu, Nanye Ma, Pinzhi Huang +8Multimodal Large Language ModelsVideo Reasoning

  3. HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference

    Apr 7, 2026Bowen Zeng, Feiyang Ren, Jun Zhang +4KV-Cache CompressionEfficient Multimodal Inference