◇ GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

{
  "schema_version": "0.5",
  "entry_id": "ASR-PAPER-20261013-2609-39600",
  "record_type": "paper",
  "title": "今日论文 · GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed",
  "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": "Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens. We view grounding as visual evidence extraction: objects, locations, and spatial relations are jointly constrained by the image and query, yet their dependencies do not imply an intrinsic left-to-right generation order. This distinction makes bidirectiona",
    "key_points": [
      "论文 ID 2609.39600",
      "作者 Qize Yu、Lianrui Fan、Bowen Ping、Xini Ding、Zetian Song、Junbo Niu",
      "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 · GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed》（Qize Yu、Lianrui Fan、Bowen Ping、Xini Ding、Zetian Song、Junbo Niu），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/2609.39600）；对照论文 ID（2609.39600）可找实现与讨论。",
    "evidence": [
      "论文 ID 2609.39600",
      "作者 Qize Yu、Lianrui Fan、Bowen Ping、Xini Ding、Zetian Song、Junbo Niu"
    ],
    "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": "2609.39600",
      "title": "GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed",
      "authors": [
        "Qize Yu",
        "Lianrui Fan",
        "Bowen Ping",
        "Xini Ding",
        "Zetian Song",
        "Junbo Niu",
        "Kaixuan Wang",
        "Tianxing Chen",
        "Yue Chen",
        "Minghua He",
        "Yuran Wang",
        "Jie Huang",
        "Haojun Zhang",
        "Min Chen",
        "Hao Li",
        "Wenxuan Song",
        "Ruihai Wu",
        "Xianming Liu",
        "Shilong Liu",
        "Shuchang Zhou",
        "Ping Luo",
        "Shiyu Huang"
      ],
      "published_at": "2026-09-30T00:00:00.000Z",
      "url": "https://huggingface.co/papers/2609.39600",
      "source_label": "hf-daily-papers"
    },
    "raw": [
      {
        "paper_id": "2609.39600",
        "title": "GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed",
        "authors": [
          "Qize Yu",
          "Lianrui Fan",
          "Bowen Ping",
          "Xini Ding",
          "Zetian Song",
          "Junbo Niu",
          "Kaixuan Wang",
          "Tianxing Chen",
          "Yue Chen",
          "Minghua He",
          "Yuran Wang",
          "Jie Huang",
          "Haojun Zhang",
          "Min Chen",
          "Hao Li",
          "Wenxuan Song",
          "Ruihai Wu",
          "Xianming Liu",
          "Shilong Liu",
          "Shuchang Zhou",
          "Ping Luo",
          "Shiyu Huang"
        ],
        "summary": "Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens. We view grounding as visual evidence extraction: objects, locations, and spatial relations are jointly constrained by the image and query, yet their dependencies do not imply an intrinsic left-to-right generation order. This distinction makes bidirectional diffusion a natural fit, allowing spatial hypotheses to emerge in parallel and be jointly refined through iterative denoising. We introduce GroundAnything, a 4B-parameter grounding foundation model ",
        "published_at": "2026-09-30T00:00:00.000Z",
        "submitted_on_daily_at": null,
        "url": "https://huggingface.co/papers/2609.39600"
      }
    ]
  },
  "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）"
  }
}