{"ID":2877316,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.21046","arxiv_id":"2508.21046","title":"CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing \u0026 Sparsification","abstract":"Recent Vision-Language-Action (VLA) models built on pre-trained Vision-Language Models (VLMs) require extensive post-training, resulting in high computational overhead that limits scalability and deployment.We propose CogVLA, a Cognition-Aligned Vision-Language-Action framework that leverages instruction-driven routing and sparsification to improve both efficiency and performance. CogVLA draws inspiration from human multimodal coordination and introduces a 3-stage progressive architecture. 1) Encoder-FiLM based Aggregation Routing (EFA-Routing) injects instruction information into the vision encoder to selectively aggregate and compress dual-stream visual tokens, forming a instruction-aware latent representation. 2) Building upon this compact visual encoding, LLM-FiLM based Pruning Routing (LFP-Routing) introduces action intent into the language model by pruning instruction-irrelevant visually grounded tokens, thereby achieving token-level sparsity. 3) To ensure that compressed perception inputs can still support accurate and coherent action generation, we introduce V-L-A Coupled Attention (CAtten), which combines causal vision-language attention with bidirectional action parallel decoding. Extensive experiments on the LIBERO benchmark and real-world robotic tasks demonstrate that CogVLA achieves state-of-the-art performance with success rates of 97.4% and 70.0%, respectively, while reducing training costs by 2.5-fold and decreasing inference latency by 2.8-fold compared to OpenVLA. CogVLA is open-sourced and publicly available at https://github.com/JiuTian-VL/CogVLA.","short_abstract":"Recent Vision-Language-Action (VLA) models built on pre-trained Vision-Language Models (VLMs) require extensive post-training, resulting in high computational overhead that limits scalability and deployment.We propose CogVLA, a Cognition-Aligned Vision-Language-Action framework that leverages instruction-driven routing...","url_abs":"https://arxiv.org/abs/2508.21046","url_pdf":"https://arxiv.org/pdf/2508.21046v3","authors":"[\"Wei Li\",\"Renshan Zhang\",\"Rui Shao\",\"Jie He\",\"Liqiang Nie\"]","published":"2025-08-28T17:50:58Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":610367,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2877316,"paper_url":"https://arxiv.org/abs/2508.21046","paper_title":"CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing \u0026 Sparsification","repo_url":"https://github.com/JiuTian-VL/CogVLA","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}