{"ID":2921130,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-04T06:21:04.369492701Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.01790","arxiv_id":"2606.01790","title":"STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models","abstract":"Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-value (KV) cache that grows linearly with interaction steps. For instance, UI-TARS-1.5-7B consumes 76 GB of GPU memory on merely five screenshots, approaching the capacity of mainstream 80 GB accelerators. Existing KV compression methods share two structural assumptions: aggregating visual-token importance into a single shared saliency map, and applying a fixed top-B cutoff to the fused score distribution. Pilot measurements refute both: spatial specialization lives at the attention-subspace level and migrates across layers, while the score distribution drifts in shape along a trajectory. We propose STaR-KV (Spatio-Temporal Adaptive Re-weighting), a training-free KV cache compression framework that calibrates token importance along three axes: (i) subspace-aware scoring driven by online spatial mutual information; (ii) a temporal stability discount that suppresses redundant cache entries from persistently attended subspaces; and (iii) an entropy-derived temperature that adaptively reshapes the score distribution. Across four GUI benchmarks, STaR-KV achieves the strongest average accuracy among state-of-the-art KV compression methods (e.g., GUIKV, SnapKV) at matched budgets, with no compression-stage FLOPs overhead (-0.07%) and cutting peak GPU memory by nearly 40% at a 20% KV-cache budget. Code is available at https://github.com/kawhiiiileo/STaR-KV.","short_abstract":"Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-value (KV) cache that grows linearly with interaction steps. For instance, UI-TARS-1.5-7B consumes 76 GB of GPU memory on merely five screenshots, approaching the capacity...","url_abs":"https://arxiv.org/abs/2606.01790","url_pdf":"https://arxiv.org/pdf/2606.01790v1","authors":"[\"Yuhang Han\",\"Wenzheng Yang\",\"Yujie Chen\",\"Xiangqi Jin\",\"Yaojie Zhang\",\"Siteng Huang\",\"Linfeng Zhang\"]","published":"2026-06-01T07:10:00Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":612564,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T02:42:49.606572591Z","DeletedAt":null,"paper_id":2921130,"paper_url":"https://arxiv.org/abs/2606.01790","paper_title":"STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models","repo_url":"https://github.com/kawhiiiileo/STaR-KV","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}