◇ GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

{
  "schema_version": "0.5",
  "entry_id": "ASR-PAPER-20261013-2609-39601",
  "record_type": "paper",
  "title": "今日论文 · GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives",
  "observed_at": "2026-10-13",
  "source": {
    "name": "huggingface.co/api/daily_papers",
    "url": "https://huggingface.co/api/daily_papers?limit=10",
    "snapshot_hash": "595adb2a453fb84cd4a3c880de643382c4638068121fc923b0c89450817e3f47",
    "fetched_at": "2026-10-13T07:12:21+00:00"
  },
  "confidence": "medium",
  "human_stream": {
    "summary": "Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet vision-language-action (VLA) and world-action models (WAMs) take perception from general-purpose vision-language and video-generation backbones, which still fail in these settings. We introduce GroundingPI, a 4B",
    "key_points": [
      "论文 ID 2609.39601",
      "作者 Qize Yu、Lianrui Fan、Boyu Chen、Jiaqi Liang、Xini Ding、Yue Chen",
      "发布 2026-09-30T00:00:00.000Z"
    ],
    "note": "来源为 HuggingFace daily papers 公开 API；完整阅读请走原文链接。",
    "what_it_is": "今日论文《今日论文 · GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives》（Qize Yu、Lianrui Fan、Boyu Chen、Jiaqi Liang、Xini Ding、Yue Chen），来自 HF Daily Papers 公开源。",
    "worth_it": "进入 HF 每日精选说明有社区关注度；是否与你的问题相关需要读原文判断，本条目不评价研究质量。",
    "how_to_start": "先读摘要，需要再读全文（https://huggingface.co/papers/2609.39601）；对照论文 ID（2609.39601）可找实现与讨论。",
    "evidence": [
      "论文 ID 2609.39601",
      "作者 Qize Yu、Lianrui Fan、Boyu Chen、Jiaqi Liang、Xini Ding、Yue Chen"
    ],
    "cautions": "摘要来自作者原文，未做同行评议级核验；引用请以正式发表版本为准。"
  },
  "ai_stream": {
    "structured": {
      "paper_id": "2609.39601",
      "title": "GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives",
      "authors": [
        "Qize Yu",
        "Lianrui Fan",
        "Boyu Chen",
        "Jiaqi Liang",
        "Xini Ding",
        "Yue Chen",
        "Zetian Song",
        "Yuran Wang",
        "Yi Zou",
        "Kaixuan Wang",
        "Tianxing Chen",
        "Wenxuan Song",
        "Bohan Zhou",
        "Mingleyang Li",
        "Siqiao Huang",
        "Yuqi Ye",
        "Caigao Jiang",
        "Wei Wei",
        "Ruihai Wu",
        "Hang Zhang",
        "Yixiao Ge",
        "Shuchang Zhou",
        "Shilong Liu",
        "Xianming Liu",
        "Ping Luo",
        "Shiyu Huang"
      ],
      "published_at": "2026-09-30T00:00:00.000Z",
      "url": "https://huggingface.co/papers/2609.39601",
      "source_label": "hf-daily-papers"
    },
    "raw": [
      {
        "paper_id": "2609.39601",
        "title": "GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives",
        "authors": [
          "Qize Yu",
          "Lianrui Fan",
          "Boyu Chen",
          "Jiaqi Liang",
          "Xini Ding",
          "Yue Chen",
          "Zetian Song",
          "Yuran Wang",
          "Yi Zou",
          "Kaixuan Wang",
          "Tianxing Chen",
          "Wenxuan Song",
          "Bohan Zhou",
          "Mingleyang Li",
          "Siqiao Huang",
          "Yuqi Ye",
          "Caigao Jiang",
          "Wei Wei",
          "Ruihai Wu",
          "Hang Zhang",
          "Yixiao Ge",
          "Shuchang Zhou",
          "Shilong Liu",
          "Xianming Liu",
          "Ping Luo",
          "Shiyu Huang"
        ],
        "summary": "Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet vision-language-action (VLA) and world-action models (WAMs) take perception from general-purpose vision-language and video-generation backbones, which still fail in these settings. We introduce GroundingPI, a 4B grounding foundation model that generates points and boxes as quantized coordinates in a shared vocabulary. Training combines multimodal and spatial pretraining, supervised fine-tuning, and reinforce",
        "published_at": "2026-09-30T00:00:00.000Z",
        "submitted_on_daily_at": null,
        "url": "https://huggingface.co/papers/2609.39601"
      }
    ]
  },
  "token_cost": {
    "total": 0.0,
    "currency": "USD",
    "breakdown": {
      "crawl": 0.0,
      "clean": 0.0,
      "elevate": 0.0,
      "verify": 0.0
    }
  },
  "machine_verified": true,
  "review": {
    "status": "agent_reviewed",
    "reviewer": "pipeline-validate",
    "reviewed_at": "2026-10-13T07:13:10+00:00",
    "comments": "schema 0 error + 溯源一致 + 成本达标"
  },
  "provenance": {
    "extracted_by": "codex",
    "extracted_at": "2026-10-13T07:12:43+00:00",
    "pipeline": "collect_hf_papers.py + build_entries.py v0.2（规则管线）",
    "access_urls": [
      "https://huggingface.co/api/daily_papers?limit=10"
    ],
    "card_generated_at": "2026-10-13T07:12:43+00:00",
    "card_pipeline": "enrich_human_stream.py v0.1（规则模板，零 Token）"
  }
}