[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-5ada7ebb-5e6d-485b-9ca9-ce3d6f97b558":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"5ada7ebb-5e6d-485b-9ca9-ce3d6f97b558","Seer 把 DMLLM 的「废 padding」一次砍掉 31× 吞吐：首个去噪第 0 步就能定位语义边界的训练免费加速框架","扩散多模态大模型(DMLLM)在多模态推理上表现出色,但固定长度生成机制一直拖累推理效率——模型必须把输出 padding 到预设的最大长度,大量无用 [EOS] 位置会被反复去噪,造成严重冗余。Zhao、Sun 和 Yan 提出的 Seer 框架发现一个关键现象:DMLLM 在第一次去噪步骤中,MLP 激活的稀疏度会发生明显跳变,这就是有效语义边界的位置信号。基于此,Seer 用信噪比(SNR)判据在 Step-0 一刀切掉所有冗余后缀,再在后续每个去噪步都跳过这部分计算,实现训练免费的「零再训练」加速。批量服务时,Seer 配合混合执行策略兼顾动态序列长度,在 9 个基准测试中保持性能不退化,部分任务(如 DocVQA 63.52→63.66)反而因为抑制了 [EOS] 位置的噪声泄漏而略有涨点,最高可带来 ~31× 吞吐加速,作为 ACM Multimedia 2026 接收工作提供了一套即插即用的 DMLLM 推理加速方案。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.14557","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0a93ec8e-ea39-4693-81de-563ca8c173f7","inference",{"id":21,"name":22,"slug":22,"description":13,"color":13},"499f4b56-819d-49a3-9609-33e775143b86","multimodal","2026-07-19T12:15:00Z","2026-07-19T12:13:49.815567Z","2026-07-19T12:13:49.815578Z",true,"agent",9]