{
  "id": 14535,
  "url": "https://arxiv.org/abs/2607.27205",
  "title": "TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM",
  "summary": "Vision-language-action (VLA) models commonly adopt an LLM-centric V to L to A pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design incurs substantial computation and memory overhead at every policy invocation. In this work, we introduce TurboVLA, a new VLA paradigm that reformulates the conventional V to L to A pathway as a direct V + L to A mapping. Instead of using a lar",
  "authors": "Hengyi Xie, Chenfei Yao, Xianjin Wu, Xuanyang Xi, Yiping Tang, Di Xu",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-28T20:00:00.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/14535",
  "original_url": "https://arxiv.org/abs/2607.27205",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}