PulseAugur
实时 12:22:08
English(EN) Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation

新论文探讨视觉和4D生成模型的效率问题

两篇新研究论文探讨了视觉和4D资产自回归生成方面的进展。第一篇论文“Where to Refine, When to Stop”提出了一种名为LD-Pruning的无训练框架,通过识别和移除冗余计算来显著降低视觉自回归模型的推理延迟。第二篇论文“MORPHOS”提出了一个用于从视频生成动态3D资产的新型自回归框架,支持多种表示并提高时间一致性。 AI

影响 这些论文引入了提高视觉和4D内容创作中自回归生成模型效率和能力的新技术。

排序理由 两篇在arXiv上发表的学术论文,详细介绍了生成模型的新方法。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Changwang Mei, Peisong Wang, Zekun Li, Changsheng Li, Shuang Qiu, Qinghao Hu, Gang Li, Yifan Zhang, Zhihui Wei, Jian Cheng ·

    Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation

    arXiv:2606.00310v1 Announce Type: new Abstract: Visual Autoregressive (VAR) models deliver high-quality image generation but suffer from significant inference latency at high resolutions. Recent acceleration approaches most rely on heuristic measures with layer features to prune …

  2. arXiv cs.CV TIER_1 English(EN) · Minkyung Kwon, Jinhyeok Choi, Youngjin Shin, Jaeyeong Kim, JongMin Lee, Seungryong Kim ·

    MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents

    arXiv:2606.02491v1 Announce Type: new Abstract: We present MORPHOS, a novel autoregressive framework that generates dynamic 3D assets from videos across diverse representations, including meshes, 3D Gaussians, and radiance fields. Existing methods are typically limited to a singl…